Search

Accurate and fast detection of abnormal hydroponic lettuce leaves is primary technology for robotic sorting. Yellow and rotten leaves are main types of abnormal leaves in hydroponic lettuce. This study aims to demonstrate a feasibility of detecting yellow and rotten leaves of hydroponic lettuce by machine learning models, i.e. Multiple Linear Regression (MLR), K-Nearest Neighbor (KNN), and Support Vector Machine (SVM). One-way analysis of variance was applied to reduce RGB, HSV, and L*a*b* features number of hydroponic lettuce images. Image binarization, image mask, and image filling methods were employed to segment hydroponic lettuce from an image for models testing. Results showed that G, H, and a* were selected from RGB, HSV, and L*a*b* for training models. It took about 20.25 s to detect an image with 3 024 × 4 032 pixels by KNN, which was much longer than MLR (0.61 s) and SVM (1.98 s). MLR got detection accuracies of 89.48% and 99.29% for yellow and rotten leaves, respectively, while SVM reached 98.33% and 97.91%, respectively. SVM was more robust than MLR in detecting yellow and rotten leaves of hydroponic. Thus, it was possible for abnormal hydroponic lettuce leaves detection by machine learning methods.

Plant height and width is an essential phenotypic parameter that can be used not only as an indicator of overall plant growth but also used to estimate the advanced parameters such as the design of agricultural machines, estimation of yield, and site-specific applications. Presently, chili plant height and width are mostly measured manually, which is laborious and time-consuming process. The goal of this study was to develop and evaluate a real-time phenotyping system using an image processing approach to measure chili plant height and width under field conditions. The image processing algorithm was developed and compiled in the open-source computer vision library (OpenCV) and Python language using PyCharm as an integrated development environment (IDE). The developed image processing algorithm was evaluated in both static and field conditions in two plots of chili plants. The developed system was able to capture a valid image of the chili plant under field conditions and accurately estimate the height and width of the plant with a RMSE in the ranges of 0.30-0.60 cm. The height and width measured by the proposed image processing algorithm were strongly correlated (R2 = 0.80–0.95) with manually measured values. Furthermore, the image processing approach has much more advanced features to measure the more complex geometric traits of plants.

Purpose Cone-beam CT (CBCT) has been widely utilized in image-guided radiotherapy. Planning CT (pCT)-aided CBCT scatter correction could further enhance image quality and extend CBCT application to dose calculation and adaptive planning. Nevertheless, existing pCT-based approaches demand accurate registration between pCT and CBCT, leading to limited imaging performance and increased computational cost when large anatomical discrepancies exist. In this work, we proposed a robust and fast CBCT scatter correction method using local filtration technique and rigid registration between pCT and CBCT (LF-RR). Methods First of all, the pCT was rigidly registered with CBCT, then forward projection was performed on registered pCT to create scatter-free projections. The raw scatter signals were obtained via subtracting the scatter-free projections from the measured CBCT projections. Based on frequency and intensity threshold criteria, reliable scatter signals were selected from the raw scatter signals, and further filtered for global scatter estimation via local filtration technique. Finally, corrected CBCT was reconstructed with the projections generated by subtracting the scatter estimation from the raw CBCT projections using FDK algorithm. The LF-RR method was evaluated via comparison with another pCT-based scatter correction method based on Median and Gaussian filters (MG method). Results Proposed method was first validated on an anthropomorphic pelvis phantom, and showed satisfied performance on scatter removal even when anatomical mismatches were intentionally created on pCT. The quantitative analysis was further performed on four clinical CBCT images. Compared with the uncorrected CBCT, CBCT corrected by MG with rigid registration (MG-RR), MG with deformable registration (MG-DR), and LF-RR reduced the CT number error from 79 ± 35 to 25 ± 18 , 17 ± 13 and 7 ± 3 HU for adipose and from 115 ± 61 to 36 ± 22 , 30 ± 24 , 7 ± 3 HU for muscle, respectively. After correction, the spatial non-uniformity (SNU) of CBCT corrected with MG-RR, MG-DR and LF-RR was 51 ± 13 , 60 ± 21 , and 21 ± 9 HU for adipose, and 50 ± 22 , 57 ± 41 , and 25 ± 6 HU for muscle, respectively. Meanwhile, the contrast-to-noise ratio (CNR) between muscle and adipose was increased by a factor of 2.70, 2.89 and 2.56, respectively. Using the LF-RR method, the scatter correction of 656 projections can be finished within 10 s and the corrected volumetric images (200 slices) can be obtained within 2 min. Conclusion We developed a fast and robust pCT-based CBCT scatter correction method which exploits the local-filtration technique to promote the accuracy of scatter estimation and is resistant to pCT-to-CBCT registration uncertainties. Both phantom and patient studies showed the superiority of the proposed correction in imaging accuracy and computational efficiency, indicating promisingfuture clinical application.

The geometric and color features of agricultural material along with related physical properties are critical to characterize and express its physical quality. The experiments were conducted to classify the physical characteristics like size, shape, color and texture and then workout the relationship between manual observations and using image processing techniques for weight and volume of the four wheat refractions i.e. sound, damaged, shriveled and broken grains of wheat variety PBW 725. A flatbed scanner was used to acquire the images and digital image processing method was used to process the images and output of image analysis was compared with the actual measurements data using digital vernier caliper. A linear relationship was observed between the axial dimensions of refractions between manual measurement and image processing method with R2 in the range of 0.798–0.947. The individual kernel weight and thousand grain weight of the refractions were observed to be in the range of 0.021–0.045 and 12.56–46.32 g respectively. Another linear relationship was found between individual kernel weight and projected area estimated using image processing methodology with R2 in the range of 0.841–0.920. The sphericity of the refractions varied in the range of 0.52–0.71. Analyses of the captured images suggest ellipsoid shape with convex geometry while the same observation was recorded by physical measurements also. A linear relationship was observed between the volume of refractions derived from measured dimensions and calculated from image with R2 in the range of 0.845–0.945. Various color and grey level co-variance matrix texture features were extracted from acquired images using the open-source Python programming language and OpenCV library which can exploit different machine and deep learning algorithms to properly classify these refractions.

In this document, we propose the recognition of powdery mildew in cucumber leaves based on image processing. Two cucumber cycles were established and infested with powdery mildew. As the disease developed, photos were taken to perform the analysis. Two hundred photographs were manually preprocessed eliminating the background and leaving only leaves infested with the disease. The images were segmented using three threshold binarization techniques: gray scale binarization, RGB binarization and K-means algorithm with initially located centroids. The results were compared between the different methods. The gray scale binarization as well as the RGB binarization allowed locating the disease based on a percentage of the lighter shades, although the latter method analyzes each one of the different color layers. The K-means algorithm identified groups with similar characteristics around provided centers. A false positive detection test was also performed with 25 previously processed photographs. The experimental results show that the proposed gray scale binarization method better results for the recognition of the disease than the other methods.

It is of a great importance in modern agriculture to study fast, automatic, inexpensive and accurate method of diagnosing plant diseasesTherefore, timely and accurately diagnosis of the disease in the fields is one of the most important factors in dealing with plant diseases. For this reason, in the present study, the image processing method study, has been examined for diagnosing the two important diseases of rice and tomato, brown spots and leaf blasts. In this study, firstly the data section is treated using improved k-means segmentation, after preprocessing. Secondly, comprehensive features are extracted and the disease areas are demarcated. An improved genetic algorithm is used in the feature selection step. Finally, images are categorized using the k-nearest neighbor’s algorithm (k-NN) classifier. The accuracy of the proposed method for the rice data set is 99.12 and for the tomato data set is 97.29, which shows a very good performance compared to other methods.

The increase in computational power in recent years has opened a new door for image processing techniques. Three-dimensional object recognition, identification, pose estimation, and mapping are becoming popular. The need for real-world objects to be mapped into three-dimensional spatial representation is greatly increasing, especially considering the heap jump we obtained in the past decade in virtual reality and augmented reality. This paper discusses an algorithm to convert an array of captured images into estimated 3D coordinates of their external mappings. Elementary methods for generating three-dimensional models are also discussed. This framework will help the community in estimating three-dimensional coordinates of a convex-shaped object from a series of two-dimension images. The built model could be further processed for increasing the resemblance of the input object in terms of its shapes, contour, and texture.

Laborious fruit thinning is required for attaining high-quality Medjoul dates. Thinning automation can significantly reduce labor and improve efficiency. An image processing apparatus developed for robotic Medjoul thinning is presented. Instance segmentation based on Mask R-CNN was applied to identify the fruit bunch components: spikelets and rachis. Motion planning parameters were extracted using the derived masks: rachis center point (RCP), rachis orientation angle, and spikelets remaining length. RCP and rachis orientation angle were computed geometrically, spikelets remaining length was estimated with a convolutional neural network (CNN) and a deep neural network (DNN). Instance segmentation results were accurate, especially for spikelets, for low intersection over union (IoU) (0.3 IoU, fruit determined for thinning identification, spikelets: 98%, rachises: 73%). However, only 66% of the rachises were correctly matched to spikelets. The segmentation of all spikelets and rachises in the images was of medium quality for low IoU (0.3 IoU, F1, spikelets: 0.67, rachis: 0.77), where both precision and recall dropped for higher IoUs. RCP and rachis orientation angle were accurately estimated (0.3 IoU, error, RCP: 2.2 cm, rachis orientation angle: 5.0°). Spikelets remaining length estimation using CNN resulted in better performance than DNN (0.3 IoU, error, CNN: 19.7%, DNN: 24.6%). Spikelets segmentation results are suitable for thinning automation. However, rachis segmentation and matching the rachis and spikelets may still require human intervention during run-time. RCP and rachis orientation angle estimation errors are acceptable, while spikelets remaining length estimation errors are acceptable only for preliminary motion planning and mandate additional tuning during motion execution.

In order to achieve the accuracy of mango grading, a mango grading system was designed by using the deep learning method. The system mainly includes CCD camera image acquisition, image preprocessing, model training, and model evaluation. Aiming at the traditional deep learning, neural network training needs a large number of sample data sets; a convolutional neural network is proposed to realize the efficient grading of mangoes through the continuous adjustment and optimization of super-parameters and batch size. The ultra-lightweight SqueezeNet related algorithm is introduced. Compared with AlexNet and other related algorithms with the same accuracy level, it has the advantages of small model scale and fast operation speed. The experimental results show that the convolutional neural network model after super-parameters optimization and adjustment has excellent effect on deep learning image processing of small sample data set. Two hundred thirty-four Jinhuang mangoes of Panzhihua were picked in the natural environment and tested. The analysis results can meet the requirements of the agricultural industry standard of the People’s Republic of China—mango and mango grade specification. At the same time, the average accuracy rate was 97.37%, the average error rate was 2.63%, and the average loss value of the model was 0.44. The processing time of an original image with a resolution of 500 × 374 was only 2.57 milliseconds. This method has important theoretical and application value and can provide a powerful means for mango automatic grading.

Purpose This study aimed to develop and validate new metrics to objectively assess the lipid layer thickness (LLT) through the analysis of grey intensity values obtained from the Placido disk pattern reflected onto the tear film. Methods Ocular surface parameters were measured using Oculus Keratograph 5 M in 94 healthy volunteers (43.8 ± 26.8 years). Subjects’ LLT was subjectively classified into 4 groups using an interferometry-based grading scale. New metrics based on the intensity of the Placido disk images were calculated and compared between groups. The repeatability of the new metrics and their diagnostic ability was analysed through receiver operating characteristics (ROC) curves. The level of agreement between the new objective tool and the existing subjective classification scale was analysed by means accuracy, weighted Kappa index and F-measure. Results Mean pixel intensity, median pixel intensity and relative energy at 5.33 s after blinking achieved the highest performance, with a correlation with LLT between r = 0.655 and 0.674 (p F-measure between 0.86 and 0.87. Conclusion The analysis of grey intensity values in videokeratography can be used as an objective tool to assess LLT. These new metrics could be included in a battery of clinical tests as an easy, repeatable, objective and accessible method to improve the detection and monitoring of dry eye disease and meibomian gland dysfunction.

PURPOSE Automatizing the scoring of the cytokinesis-blocked micronucleus assay spares a lot of valuable time. The dose-effect relationship can be applied reliably for dose estimation if the quality of the slides is the same from the perspective of the used image processing algorithm. This aspect brings in additional requirements against the quality of the slides compared to the conventional visual scoring. MATERIALS AND METHODS An add-in software was created to the non-fluorescent RS-MN automatic MN scoring system which is capable of measuring quantitatively the degree of typical anomalies. The image processing is less reliable when the presence of these anomalies is more frequent. The behavior of the designed sample quality parameters (SQPs) was tested on in vitro irradiated peripheral blood samples (0, 1, and 2 Gy) obtained from a healthy donor and also on samples from patients undergoing low dose-rate brachytherapy. RESULTS We examined 20 different SQPs and identified two that are independent and correlate significantly with the error of the fully automatic MN frequency. One is related to the size of the cells and the other reflects the homogeneity of the environment. An equation was established which presents a connection between the error of the auto MN frequency and the SQPs. By adding a fourth cleaning step to the conventional sample preparation and changing the pre-dripping temperature of the slide, the SQP can be modified, and consequently, the sample quality can be improved. The gain in accuracy is 54 ± 10 MN per 1000 binucleated cells, which corresponds to the effects of 0.5 Gy. Around the lowest limit of detection (

In Zheng (J. Glob. Opt. 79:431-445;2021) the authors described a global optimization algorithm for multivariate continuous functions and applied it to an image processing problem. While the algorithm was shown to converge for all continuous functions, the convergence rate was not established. In this paper we assume that the objective function is smooth, and establish the asymptotic convergence rate when the algorithm is applied to such a function.

Tinggi tanaman merupakan salah satu parameter utama pertumbuhan tanaman pakcoy yang dibudidaya secara hidroponik. Oleh karena itu perlu dilakukan pengukuran tinggi tanaman dimana membutuhkan waktu relatif lama jika di ukur secara manual. Maka solusi dari permasalahan ini adalah pengukuran otomatis menggunakan pengolahan citra utuk menggantikan tenaga manusia. Tujuan dari penelitian ini adalah merancang dan memonitoring ketinggian tanaman pakcoy sistem hidroponik menggunakan teknologi pengolahan citra dan kamera 3D Kinect v2 terintegrasi dengan komputer. Penelitian ini terdapat dua pengukuran yaitu dengan cara manual menggunakan penggaris, dan pengambilan citra menggunakan kinect v2 dengan resolusi kamera 1920 x 1080 piksel, Sampel tanaman pakcoy yang digunakan pada penelitian ini pada umur 2,3 dan 4 minggu sebanyak 60 sampel. Pengambilan citra dilakukan pada sore hari yaitu dimulai pada jam 15.00-17.00. Data citra depth yang dihasilkan diolah menggunakan software Halcon HDevelop 20.05 Student Edition dengan memasukkan algoritma dan diidentifikasi menggunakan metode Distance Transform dan Watersheds Segmentation berfungsi untuk memisahkan antara objek dengan latar belakang ( background ) dan membuat batas antara satu objek dengan objek lainnya yang bersentuhan ataupun berhimpit, untuk menentukan jarak tiap-tiap daun yang terdeteksi dengan kamera kinect v2 digunakan metode histogram pada pengolahan citra. Berdasarkan hasil pengujian menggunakan teknologi pengolahan citra digital sensor kinect v2 telah terbukti mampu untuk mengumpulkan data tinggi tanaman pakcoy. Persentase akurasi pada pengukuran tinggi tanaman secara actual dan kinect v2 dengan metode Root mean squre error (RMSE) yaitu

Purpose We performed quantitative analysis of differences in deformable image registration (DIR) and deformable dose accumulation (DDA) computed on CBCT datasets reconstructed using the standard (Feldkamp‐Davis‐Kress: FDK_CBCT) and a novel iterative (iterative_CBCT) CBCT reconstruction algorithms. Methods Both FDK_CBCT and iterative_CBCT images were reconstructed for 323 fractions of treatment for 10 prostate cancer patients. Planning CT images were deformably registered to each CBCT image data set. After daily dose distributions were computed, they were mapped to planning CT to obtain deformed doses. Dosimetric and image registration results based CBCT images reconstructed by two algorithms were compared at three levels: (A) voxel doses over entire dose calculation volume, (B) clinical constraint results on targets and sensitive structures, and (C) contours propagated to CBCT images using DIR results based on three algorithms (SmartAdapt, Velocity, and Elastix) were compared with manually delineated contours as ground truth. Results (A) Average daily dose differences and average normalized DDA differences between FDK_CBCT and iterative_CBCT were ≤1 cGy. Maximum daily point dose differences increased from 0.22 ± 0.06 Gy (before the deformable dose mapping operation) to 1.33 ± 0.38 Gy after the deformable dose mapping. Maximum differences of normalized DDA per fraction were up to 0.80 Gy (0.42 ± 0.19 Gy). (B) Differences in target minimum doses were up to 8.31 Gy (−0.62 ± 4.60 Gy) and differences in critical structure doses were 0.70 ± 1.49 Gy. (C) For mapped prostate contours based on iterative_CBCT (relative to standard FDK_CBCT), dice similarity coefficient increased by 0.10 ± 0.09 (p

Microscope vision analysis is applied in many fields. The traditional way is to use the human eye to observe and manually focus to obtain the image of the observed object. However, with the observation object becoming more and more subtle, the magnification of the microscope is required to be larger and larger. The method of manual focusing cannot guarantee the best focusing position of the microscope in use. Therefore, in this paper, we are studying the existing autofocusing technology and the autofocusing method of microscope based on image processing, which is different from the traditional manual focusing method. The autofocusing method of microscope based on image processing does not need the information such as the target position and the focal length of optical system, to directly focus the collected image. First of all, in order to solve the problem of large computation and difficult real time of traditional wavelet based image sharpness evaluation algorithm, this paper proposes an improved wavelet based image sharpness evaluation algorithm; secondly, in view of the situation that the window selected by traditional focusing window selection method is fixed, this paper adopts an adaptive focusing window selection method to increase the focusing window. Finally, this paper studies the extremum search strategy. In order to avoid the interference of the local extremum in the focusing curve, this paper proposes an improved hill-climbing algorithm to achieve the accuracy of focusing search. The simulation results show that the improved wavelet transform image definition evaluation algorithm can improve the definition evaluation performance, and the improved mountain climbing algorithm can reduce the impact of local extremum and improve the accuracy of the search algorithm. All in all, it can be concluded that the method based on image processing proposed in this paper has a good focusing effect, which can meet the needs of anti-interference and extreme value search of microscope autofocus.

Health is the most important aspect of any human being. With the increasing pace of life, the focus on health was decreasing. This has created a wide number of problems like obesity, diabetes, hypertension, etc. Fruits contain a major source of energy, vitamin, nutrients which should be the vital part of diet. This paper presents a nutrition measurement system which calculates the precise quantity of moisture, protein, fiber, carbohydrates and fats present in the fruit. The system works without any complex hardware and weighing scale. It calculates the precise mass of fruit using two images digital images of the same fruit.

The measurement of crop nutrition is considerably significant in agricultural practices, especially in the application of mechanized variable rate fertilization. Feature extraction and model building are two important links in crop nutrition measurement by digital image. In this paper, a feature set of fusion multi-colour space in field prototype is extracted and an evaluation approach using stepwise-based ridge regression (SBRR) that uses correlation-based evaluation method is employed. First the image features of three known colour spaces are extracted, meanwhile a new colour space named rgb is constructed according to the characteristics that RGB colour space easily affected by light. Then the SBRR with nested cross validation is used to find the best evaluation model. By performance evaluation, the optimal SBRR model is obtained ( R 2 = 0.718 RMSE = 5.111). Additionally, compared with two other nutritional evaluation approach named back-propagation artificial neural network (BP-ANN) and k-nearest neighbors (KNN), SBRR achieves better performance in both R2 and RMSE. Furthermore the proposed model’s reliability is verified using the image dataset taken from the same wheat field in the next year. The R 2 and RMSE values are 0.794 and 4.304, respectively. The comparisons and verification show that our proposed SBRR approach can achieve better experimental results and can be considered a reliable and low-cost alternative for estimating the chlorophyll content of wheat leaves in field.

This study aimed to evaluate and compare the accuracy of average faces constructed by different methods. Original three-dimensional facial images of 26 adults in Chinese ethnicity were imported into Di3DView and MorphAnalyser for image processing. Six average faces (Ave_D15, Ave_D24, Ave_MG15, Ave_MG24, Ave_MO15, Ave_MO24) were constructed using “surface-based registration” method with different number of landmarks and template meshes. Topographic analysis was performed, and the accuracy of six average faces was assessed by linear and angular parameters in correspondence with arithmetic means calculated from individual original images. Among the six average faces constructed by the two systems, Ave_MG15 had the highest accuracy in comparison with the conventional method, while Ave_D15 had the least accuracy. Other average faces were comparable regarding the number of discrepant parameters with clinical significance. However, marginal and non-registered areas were the most inaccurate regions using Di3DView. For MorphAnalyser, the type of template mesh had an effect on the accuracy of the final 3D average face, but additional landmarks did not improve the accuracy. This study highlights the importance of validating software packages and determining the degree of accuracy, as well as the variables which may affect the result.

The notion of fuzzy set theory has not so far been districted over medical diagnosis. There are some added applications, for example, in image processing, pattern identification, and many medical devices. In this research article, we introduced a new mediative fuzzy ranking technique as the fuzzy extension in decision making. The proposed mediative fuzzy logic-based technique is more relevant and applicable to incomplete and doubtful situations or some contradictions present in the expert knowledge. The value of the contradictory degree for mediative fuzzy sets used in the extension principle is defined. The proposed mediative fuzzy ranking method is easily implemented in the medical field, and the proposed mediative fuzzy extension-based measured technique is useful to medical experts and doctors in many decision-making situations; the entire work is illustrated with numerical examples. We have also given some future aspects of mediative fuzzy extension in the interpretation of type-2 intuitionistic fuzzy sets.

BACKGROUND: In archived diffusion tensor imaging (DTI) studies, a reversed-phase encoding (PE) scan required to correct the distortion in single-shot echo-planar imaging (EPI) may not have been acquired. Furthermore, DTI tractography is adversely affected by incorrect white matter segmentation due to leukoencephalopathy (LE). All these issues need to be addressed. PURPOSE: To propose and evaluate a modified DTI processing pipeline with DIstortion COrrection using pseudo T(2)-weighted images (DICOT) to overcome limitations in existing acquisition protocols. STUDY TYPE: Retrospective feasibility. SUBJECTS: DICOT was assessed in simulated data and 84 acute lymphoblastic leukemia (ALL) patients with reversed PE acquired. The pipeline was then tested in 522 scans from 261 ALL patients without a reversed PE acquired. FIELD STRENGTH/SEQUENCE: A 3 T; diffusion-weighted EPI; 3D magnetization prepared rapid acquisition gradient echo (MPRAGE). STATISTICAL TESTS: Repeated measures analysis of variance and Tukey post hoc tests were performed to compare fractional anisotropy (FA) values obtained by different methods. ASSESSMENT: FA and corresponding absolute error maps were obtained using TOPUP, DICOT, INVERSION (Inverse contrast Normalization for VERy Simple registratION) and NO CORR (no correction). Each method was assessed by comparing to TOPUP. The pipeline in the ALL patients was evaluated based on the failure rate of the distortion correction using the global correlation values. RESULTS: Using DICOT reduced the mean absolute errors by an average of 32% in FA in simulation datasets. In 84 patients, the error reductions were approximately 15% in FA with DICOT, while it was 5% with INVERSION. No significant differences between the TOPUP and DICOT were observed in FA with P = 0.090/0.894(AP/PA). Only 15 of 516 examinations requiring any additional manual intervention. CONCLUSION: This modified pipeline produced better results than the INVERSION. Furthermore, robust performance was demonstrated in archived patient scans acquired without an inverse PE necessary for TOPUP correction. EVIDENCE LEVEL: 3 TECHNICAL EFFICACY: Stage 2

As far as the agricultural domain is concerned, one of the most hot research areas of analysis is accurate prediction of leaf disease from the leaf images of a plant. The prediction of agricultural plant diseases bymeans of the image processing techniques will hence reduce the dependence on the farmers to safeguard their agricultural land and also their products. However, with the presence of noise, the leaf disease prediction is said to be hindered. To address this issue, in this paper, Covariance Kalman Geometric Graph-basedBernoulliClassifier (CKGG-BC) for Plant leaf disease prediction is proposed. The CKGG-BC method is split into three parts. To start with the plant leaf image provided as input, the Covariance Kalman Filtered Preprocessing modelintroduced for the image enhancement. Second, Geometric Graph-based Segmented Co-occurrence Feature Extraction model is applied to the preprocessed image to accurately segment the infected leaf areas and followed by which extracting the accurate infected leaf areas. Finally, Bernoulli Online Multiple Kernel Learning Classifier is applied for accurate plant leaf disease prediction with minimum classification error. The proposed method provides a significant refinement with respect to state-of-the-art methods. Even under complex background conditions, i.e., in the presence of noise, the averageaccuracy of the proposed method is said to be improved and hence paves mechanism for prediction of plant leaf disease in a significant manner. Experimentalresults exhibit the effectiveness of the proposed method in terms of computational overhead, accuracy, true positive rate and classification error respectively.

Multi-view image acquisition systems with two or more cameras can be rather costly due to the number of high resolution image sensors that are required. Recently, it has been shown that by covering a low resolution sensor with a non-regular sampling mask and by using an efficient algorithm for image reconstruction, a high resolution image can be obtained. In this paper, a stereo image reconstruction setup for multi-view scenarios is proposed. A scene is captured by a pair of non-regular sampling sensors and by incorporating information from the adjacent view, the reconstruction quality can be increased. Compared to a state-of-the-art single-view reconstruction algorithm, this leads to a visually noticeable average gain in PSNR of 0.74 dB., Comment: 4 pages, 5 figures, 1 table, International Conference on Image Processing (ICIP)

Increasing spatial image resolution is an often required, yet challenging task in image acquisition. Recently, it has been shown that it is possible to obtain a high resolution image by covering a low resolution sensor with a non-regular sampling mask. Due to the masking, however, some pixel information in the resulting high resolution image is not available and has to be reconstructed by an efficient image reconstruction algorithm in order to get a fully reconstructed high resolution image. In this paper, the influence of different sampling masks with a reduced randomness of the non-regularity on the image reconstruction process is evaluated. Simulation results show that it is sufficient to use sampling masks that are non-regular only on a smaller scale. These sampling masks lead to a visually noticeable gain in PSNR compared to arbitrary chosen sampling masks which are non-regular over the whole image sensor size. At the same time, they simplify the manufacturing process and allow for efficient storage., Comment: 4 pages, 5 figures, 1 table, Visual Communications and Image Processing (VCIP)

The study was aimed at the evaluation of the usefulness of textures of the outer surface from the images of apple skin and flesh for discrimination of different cultivars. The texture parameters were calculated from color channels: R, G, B, L, a, b, U, V, H, S, I, X, Y, Z. In the case of cultivar discrimination performed for the apple skin, the highest accuracies were obtained for textures from channels R, a and X. In the case of channels R and a, the apples were classified with the total accuracy of up to 93%. For channel X, the highest total accuracy was 90%. For discrimination based on the textures selected from images of a longitudinal section of apples, the total accuracy reached 100% for channels G, b and U. In the case of the cross-section images, the total accuracies were also satisfactory and reached 93% for channel G, 97% for channels b and U. The obtained results proved that the use of image processing based on textures can allow the discrimination of apple cultivars with a high probability of up to 100% in the case of textures selected from images of a longitudinal section. The results can be applied in practice for cultivar discrimination and detection of the falsification of apple cultivars. The obtained results revealed that texture features can allow for cultivar identification of apples with a very high probability in an inexpensive, objective, and fast way. Graphic abstract

In this study, vented type water trees were initiated and grown in laboratory environment. A smart test platform was used to accelerate the initiation and growth of vented type water trees. 6 kV/4 kHz voltage was applied to the specimens to initiate and grow water trees. Mel-frequency cepstral coefficients of the vented type water tree images are obtained after 2 h and 10 h of aging respectively. The insignificant regions in the vented type water tree images were removed by using morphological filtering method before MFCC feature extraction. Finally, the statistical values of these features were analyzed. Scatter plots of the standard deviations and mean values of the cepstral coefficients were plotted. As expected, it has been observed that the points in the scatter plot are clustered in a certain area. MFCC is a popular and frequently used feature extraction method in speech recognition, however there are some studies which employs MFCC as a successful feature extraction method in image processing applications. This study provides a new approach to the analysis of vented water treeing using image processing techniques. The other new approach is using MFCC as a feature extraction method in microscopic water tree images.

Purpose: To develop an accelerated postprocessing pipeline for reproducible and efficient assessment of white matter lesions using quantitative magnetic resonance fingerprinting (MRF) and deep learning. Methods: MRF using echo-planar imaging (EPI) scans with varying repetition and echo times were acquired for whole brain quantification of (Formula presented.) and (Formula presented.) in 50 subjects with multiple sclerosis (MS) and 10 healthy volunteers along 2 centers. MRF (Formula presented.) and (Formula presented.) parametric maps were distortion corrected and denoised. A CNN was trained to reconstruct the (Formula presented.) and (Formula presented.) parametric maps, and the WM and GM probability maps. Results: Deep learning-based postprocessing reduced reconstruction and image processing times from hours to a few seconds while maintaining high accuracy, reliability, and precision. Mean absolute error performed the best for (Formula presented.) (deviations 5.6%) and the logarithmic hyperbolic cosinus loss the best for (Formula presented.) (deviations 6.0%). Conclusions: MRF is a fast and robust tool for quantitative (Formula presented.) and (Formula presented.) mapping. Its long reconstruction and several postprocessing steps can be facilitated and accelerated using deep learning.

The objective of this study is to classify the rice grains of seventeen different varieties popularly planted in Vietnam. Image processing is used to extract color, morphological, and texture features of the rice grains. Five feature subsets are formed, namely, morphological, basic color, clustering color, statistical, and gray level co-occurrence matrix (GLCM). These subsets and combined sets are evaluated for classification ability with a support vector machine (SVM). A dataset of 248 features, including a total of color, morphological, and texture features classified with the SVM gives an overall accuracy of 88.29%. To decrease the number of used features and to improve the classification accuracy, the proposed method combining binary particle swarm optimization (BPSO) and the SVM, called BPSO+SVM, is applied to the dataset. In the results, classification accuracy from BPSO+SVM reaches 93.94% using only 96 selected features. The obtained result shows the proposed method achieves higher classification accuracy than the SVM alone, and the required number of features is only 39% of the total dataset. This result can be applied for developing an automatic classification and identification system of rice varieties.

This article presents a new methodology to diagnostics ten types of skin lesions based on the image’ s Fourier spectral information in an additive color model. All spectral information and correlation coefficients between the skin lesions classes conform the input signals to an Artificial Neural Network. In general, the results show the well-defined classification for all the skin lesions classes based on the high values for Accuracy, Precision, Sensitivity, and Specificity metrics performance and a reduced images misclassification percentage (≈5.9%) for the Testing sub-dataset, and less for Training (≈2.8%) and Validation (≈5.6%) sub-dataset even considering the strange objects, not-clarity, and black sections in some images analyzed. The general achieved classification Accuracy, Precision, Sensitivity, and Specificity percentages of the proposed method are 99.33 %, 94.16 %, 92.9 %, and 99.63 %, respectively. In particular, the skin lesions related to Basal Cell Carcinoma, Seborrhoeic Keratosis, and Melanocytic Nevus present the best performance regarding the Receiver Operating Characteristics, while the Pyogenic Granuloma was the worst classified.

Weed identification in vegetable plantation is more challenging than crop weed identification due to their random plant spacing. So far, little work has been found on identifying weeds in vegetable plantation. Traditional methods of crop weed identification used to be mainly focused on identifying weed directly; however, there is a large variation in weed species. This paper proposes a new method in a contrary way, which combines deep learning and image processing technology. Firstly, a trained CenterNet model was used to detect vegetables and draw bounding boxes around them. Afterwards, the remaining green objects falling out of bounding boxes were considered as weeds. In this way, the model focuses on identifying only the vegetables and thus avoid handling various weed species. Furthermore, this strategy can largely reduce the size of training image dataset as well as the complexity of weed detection, thereby enhancing the weed identification performance and accuracy. To extract weeds from the background, a color index-based segmentation was performed utilizing image processing. The employed color index was determined and evaluated through Genetic Algorithms (GAs) according to Bayesian classification error. During the field test, the trained CenterNet model achieved a precision of 95.6%, a recall of 95.0%, and a $F_{1}$ score of 0.953, respectively. The proposed index -19R + 24G -2B ≥ 862 yields high segmentation quality with a much lower computational cost compared to the wildly used ExG index. These experiment results demonstrate the feasibility of using the proposed method for the ground-based weed identification in vegetable plantation.

Seiring dengan kemajuan komputer, teknik pemrosesan gambar menjadi berkembang dengan pesat. Segmentasi citra adalah salah satu bidang dalam pemrosesan gambar untuk mengenali suatu obyek gambar. Salah satu segmentasi citra adalah ekstraksi fitur tepi (edge detection) dan kurva dari sebuah gambar. Paper ini akan memberikan informasi mengenai studi perbandingan teknik deteksi tepi dengan berbagai metode. Perbandingan metode meliputi bentuk objek yang akan dikenali tepinya, tingkat akurasi gambar, waktu eksekusi program dan output yang diberikan. Ada tujuh algoritma deteksi tepi yang digunakan, algoritma ini terbagi menjadi dua yaitu orde satu meliputi Sobel, Prewit, Robert, Isotropic, dan Compas. Sedangkan orde dua meliputi Canny dan Laplacian. Hasil percobaan dievaluasi berdasarkan nilai kemiripan dengan citra asli dengan pendekatan MSE dan PSNR. Hasil evaluasi menujukkan bahwa dari 3 citra yang di ujicoba metode canny mendapatkan 2 hasil terbaik dari ketiga citra dengan nilai MSE & PSNR pada citra 1 dan 2 sebesar 246,95 & 3,67 dB dan 249,16 & 2,55 dB.

Pollen analysis is a method used for verification of the botanical and geographical honey origin. Currently, much effort is being made to introduce automated systems with the use of image analysis programs. The automatic analysis is impeded by the insufficient depth of field of objects when using a light microscope, however, this can be avoided by using image reconstruction from images obtained from different focal planes. In this method, testing was performed on the normal focus (NF) and extended-depth-of-focus (EDF) images. These two methods were compared and statistically evaluated. The number of pollen grains and selected morphometric characteristics were compared. For EDF images, a higher number of pollen grains was obtained for the analysis, and except for the length/width ratio, a statistically significant difference was observed in the characteristics of pollen grains between the compared NF and EDF methods.

HighlightsThe proposed method detected thrips and whitefly more accurately than previous methods.The proposed method demonstrated good robustness to illumination reflections and different pest densities.Small pest detection was improved by adding large-scale feature maps and more residual units to a shallow network.Machine vision and deep learning created an end-to-end model to detect small pests on sticky traps in field conditions.Abstract. Pest detection is the basis of precise control in vegetable greenhouses. To improve the detection accuracy and robustness for two common small pests (whitefly and thrips) in greenhouses, this study proposes a novel small object detection approach based on the YOLOv4 model. Yellow sticky trap (YST) images at the original resolution (2560 × 1920 pixels) were collected using pest monitoring equipment in a greenhouse. The images were then cropped and labeled to create sub-images (416 × 416 pixels) to construct an experimental dataset. The labeled images used in this study (900 training, 100 validation, and 200 test) are available for comparative studies. To enhance the model’s ability to detect small pests, the feature map at the 8-fold downsampling layer in the backbone network was merged with the feature map at the 4-fold downsampling layer to generate a new layer and output a feature map with a size of 104 × 104 pixels. Furthermore, the residual units in the first two residual blocks were enlarged by four times to extract more shallow image features and the location information of target pests to withstand image degradation in the field. The experimental results showed that the mean average precision (mAP) for detection of whitefly and thrips using the proposed approach was improved by 8.2% and 3.4% compared with the YOLOv3 and YOLOv4 models, respectively. The detection performance slightly decreased as the pest densities increased in the YST image, but the mAP value was still 92.7% in the high-density dataset, which indicates that the proposed model has good robustness over a range of pest densities. Compared with previous similar studies, the proposed method has better potential to monitor whitefly and thrips using YSTs in field conditions. Keywords: Deep learning, Greenhouse pest management, Image processing, Pest detection, Small object, YOLOv4.

Recently, there has been an explosion of scientific literature describing the use of colorimetry for monitoring the progression or the endpoint result of colorimetric reactions. The availability of inexpensive imaging technology (e.g., scanners, Raspberry Pi, smartphones and other sub-$50 digital cameras) has lowered the barrier to accessing cost-efficient, objective detection methodologies. However, to exploit these imaging devices as low-cost colorimetric detectors, it is paramount that they interface with flexible software that is capable of image segmentation and probing a variety of color spaces (RGB, HSB, Y'UV, L*a*b*, etc.). Development of tailor-made software (e.g., smartphone applications) for advanced image analysis requires complex, custom-written processing algorithms, advanced computer programming knowledge and/or expertise in physics, mathematics, pattern recognition and computer vision and learning. Freeware programs, such as ImageJ, offer an alternative, affordable path to robust image analysis. Here we describe a protocol that uses the ImageJ program to process images of colorimetric experiments. In practice, this protocol consists of three distinct workflow options. This protocol is accessible to uninitiated users with little experience in image processing or color science and does not require fluorescence signals, expensive imaging equipment or custom-written algorithms. We anticipate that total analysis time per region of interest is ~6 min for new users and

The accurate evaluation of maize plants’ uniformity aligned with an effective improvement in germination and biomass assessment is of paramount importance for farmers. Early detection of stand count provides details on uneven emergence for farmers to make a prompt decision for replanting and applying proper agricultural inputs at defective zones. However, conventional, ground-based stand count methods are costly, time-intensive, and the accuracy of the counting method heavily depends on the selected area. This study focuses on validating the potential application of high resolution unmanned aerial vehicle (UAV) images for detecting the total number of maize plants and stand uniformity soon after maize germination. A field experiment was conducted to evaluate proper image processing algorithm for detecting the maize crop and calculating the distance between adjacent maize plants within a row. In the mosaicked images, the pixels including maize plants were segmented using two methods including excess green index (EXG) method and k-means clustering-segmentation technique. The mean accuracy using EXG method was 46%, however, the k-means clustering-segmentation method satisfactorily identified plants with mean accuracy of 91% in the field. The planting uniformity of maize plants was also evaluated based on three indices including miss index, multiple index, and coefficient of precision. Results showed that plant stand assessment using mosaicked images was closer to the values set on the planting machine. The marginal discrepancy between estimated and observed plant stand count and other indices confirms the high accuracy of UAV mosaicked images in plant density estimation for growers to make appropriate management decisions.

As the important data basis of surrounding rock classification, rock mass structural information obtained by traditional image processing and feature extraction algorithms could not be quantitatively analyzed because of the uncertainty and geometric randomness of structural planes. In this paper, based on straight line detection, intelligent scissors, and morphological edge detection algorithms, the multiple interpretation system of rock mass image including linear bunching extraction, magnetic tracking extraction, and multiparameter characterization was researched and developed, and the actual distribution information and the related probability distribution model of structural planes could be obtained directly. On the basis of this, plenty of corresponding random rating-values meeting the probability distribution models of these evaluation indices were gained by Monte Carlo Simulation. The distribution probability affiliated with different rock mass grade was attained by inductive statistics, and the robust evaluation of surrounding rock classification could be carried out. Taking the robust results as learning samples, the response model of surrounding rock grade based on Gaussian process classification was established, making the evaluation of surrounding rock subclassification more rapid and robust.

Our objective was to investigate the differences in texture features between step-and-shoot (SS) and continuous-bed-motion (CBM) imaging in phantom and clinical studies. Methods: A National Electrical Manufacturers Association body phantom was filled with 18F-FDG solution at a sphere-to-background ratio of 4:1. SS and CBM were performed using the same acquisition duration, and the data were reconstructed using 3-dimensional ordered-subset expectation maximization with time-of-flight algorithms. Texture features were extracted using the software LIFEx. A volume of interest was delineated on the 22-, 28-, and 37-mm spheres with a threshold of 42% of the maximum SUV. The voxel intensities were discretized using 2 resampling methods, namely a fixed bin size and a fixed bin number discretization. The discrete resampling values were set to 64 and 128. In total, 31 texture features were calculated with gray-level cooccurrence matrix (GLCM), gray-level run length matrix, neighborhood gray-level different matrix, and gray-level zone length matrix. The texture features of the SS and CBM images were compared for all settings using the paired t test and the coefficient of variation. In a clinical study, 27 lesions from 20 patients were examined using the same acquisition and image processing as were used during the phantom study. The percentage difference (%Diff) and correlation between the texture features from SS and CBM images were calculated to evaluate agreement between the 2 scanning techniques. Results: In the phantom study, the 11 features exhibited no significant difference between SS and CBM images, and the coefficient of variation was no more than 10%, depending on resampling conditions, whereas entropy and dissimilarity from GLCM fulfilled the criteria for all settings. In the clinical study, the entropy and dissimilarity from GLCM exhibited a low %Diff and excellent correlation in all resampling conditions. The %Diff of entropy was lower than that of dissimilarity. Conclusion: Differences between the texture features of SS and CBM images varied depending on the type of feature. Because entropy for GLCM exhibits minimal differences between SS and CBM images irrespective of resampling conditions, entropy may be the optimal feature to reduce the differences between the 2 scanning techniques.

This study is based on the principle that vegetation indexes (VIs), derived from the RGB color model obtained from digital images, can be used to characterize spectral signatures and classify Brachiaria brizantha cv. Xaraés according to nitrogen status (N). From colorimetric data obtained from leaf blade images acquired in the field, three artificial neural networks were evaluated according to the performance in the classification of N status: Feedforward Backpropagation (FFBP), Cascade Forward Backpropagation (CFBP) and Radial Base function (RBFNN). Four N fertilization rates were applied to generate contrasting N contents in the plants. The youngest completely expanded leaves from 60 tillers were detached at each regrowth cycle of 28 days, thus their images and leaf N content were obtained. Samples were then classified as deficient (>17 g N kg-1 leaf dry matter (DM), moderately deficient (from 17.1 to 20.0 g N kg-1 DM), and sufficient (> 20.1 g N kg-1 DM). The VIs were selected by principal component analysis and the performance of the networks evaluated by the accuracy. The accuracy in classification obtained by the networks were 88%, 86% and 79% for FFBP, CFBP and RBFNN, respectively, indicating that the spectral signatures can be determined from images acquired in the field. So, the proposed method could be used to develop a software that aims to monitor the status of N in real time, providing a fast and inexpensive tool for defining the time and the amount of N fertilizer, according to the pasture demand. RESUMO Este estudo baseia-se no princípio de que índices de vegetação (IVs), derivados do modelo de cores RGB obtidos de imagens digitais, podem ser usados para caracterizar assinaturas espectrais e classificar pastos de Brachiaria brizantha cv. Xaraés segundo o status de nitrogênio (N). A partir de dados colorimétricos obtidos de imagens de lâminas foliares adquiridas em campo, três redes neurais artificiais foram avaliadas quanto ao desempenho na classificação do status N: Feedforward Backpropagation (FFBP), Cascade Forward Backpropagation (CFBP) e função de Base Radial (RBFNN). Quatro taxa s de fertilização nitrogenada foram aplicadas para gerar contrastes no teor de N nos tecidos das plantas. As folhas mais jovens completamente expandidas de 60 perfilhos foram destacadas das plantas a cada ciclo de rebrotação de 28 dias, sendo as imagens das folhas e teor de N foliar determinados. As amostras foram classificadas em deficientes (> 17 g N kg-1 de matéria seca (MS)), moderadamente deficientes (de 17,1 a 20,0 g N kg-1 MS) e suficiente (> 20,1 g N kg-1 MS). Os IVs foram selecionados pela análise de componentes principais e o desempenho das redes avaliados pela acurácia. As acurácias nas classificações obtidas pelas redes foram de 88%, 86% e 79% para FFBP, CFBP e RBFNN, respectivamente, indicando que as assinaturas espectrais podem ser determinadas a partir de imagens adquiridas em campo. Assim, o método proposto pode ser utilizado para desenvolver um software de monitoramento do status de N em tempo real, fornecendo uma ferramenta rápida e econômica para definir o momento e quantidade de fertilizantes nitrogenados, conforme demanda da pastagem.

Bakurov, I., Buzzelli, M., Castelli, M., Schettini, R., & Vanneschi, L. (2020). Parameters optimization of the Structural Similarity Index. In London Imaging Meeting 2020: Future Colour Imaging (1 ed., Vol. 2020, pp. 19-23). (London Imaging Meeting). https://doi.org/10.2352/issn.2694-118X.2020.LIM-13 We exploit evolutionary computation to optimize the handcrafted Structural Similarity method (SSIM) through a datadriven approach. We estimate the best combination of luminance, contrast and structure components, as well as the sliding window size used for processing, with the objective of optimizing the similarity correlation with human-expressed mean opinion score on a standard dataset. We experimentally observe that better results can be obtained by penalizing the overall similarity only for very low levels of luminance similarity. Finally, we report a comparison of SSIM with the optimized parameters against other metrics for full reference quality assessment, showing superior performance on a different dataset. publishersversion published

The identification of water stress is a major challenge for timely and effective irrigation to ensure global food security and sustainable agriculture. Several direct and indirect methods exist for identification of crop water stress, but they are time consuming, tedious and require highly sophisticated sensors or equipment. Image processing is one of the techniques which can help in the assessment of water stress directly. Machine learning techniques combined with image processing can aid in identifying water stress beyond the limitations of traditional image processing. Deep learning (DL) techniques have gained momentum recently for image classification and the convolutional neural network based on DL is being applied widely. In present study, comparative assessment of three DL models: AlexNet, GoogLeNet and Inception V3 are applied for identification of water stress in maize (Zea mays), okra (Abelmoschus esculentus) and soybean (Glycine max) crops. A total of 1200 digital images were acquired for each crop to form the input dataset for the deep learning models. Among the three models, performance of GoogLeNet was found to be superior with an accuracy of 98.3, 97.5 and 94.1% for maize, okra and soybean, respectively. The onset of convergence in GoogLeNet models commenced after 8 epochs with 22 (maize), 31 (okra) and 15 (soybean) iterations per epoch with error rate of less than 7.5%.

Lowering the administered dose in SPECT myocardial perfusion imaging (MPI) has become an important clinical problem. In this study we investigate the potential benefit of applying a deep learning (DL) approach for suppressing the elevated imaging noise in low-dose SPECT-MPI studies. We adopt a supervised learning approach to train a neural network by using image pairs obtained from full-dose (target) and low-dose (input) acquisitions of the same patients. In the experiments, we made use of acquisitions from 1,052 subjects and demonstrated the approach for two commonly used reconstruction methods in clinical SPECT-MPI: 1) filtered backprojection (FBP), and 2) ordered-subsets expectation-maximization (OSEM) with corrections for attenuation, scatter and resolution. We evaluated the DL output for the clinical task of perfusion-defect detection at a number of successively reduced dose levels (1/2, 1/4, 1/8, 1/16 of full dose). The results indicate that the proposed DL approach can achieve substantial noise reduction and lead to improvement in the diagnostic accuracy of low-dose data. In particular, at 1/2 dose, DL yielded an area-under-the-ROC-curve (AUC) of 0.799, which is nearly identical to the AUC = 0.801 obtained by OSEM at full-dose ( ${p}$ -value = 0.73); similar results were also obtained for FBP reconstruction. Moreover, even at 1/8 dose, DL achieved AUC = 0.770 for OSEM, which is above the AUC = 0.755 obtained at full-dose by FBP. These results indicate that, compared to conventional reconstruction filtering, DL denoising can allow for additional dose reduction without sacrificing the diagnostic accuracy in SPECT-MPI.

Weed management is one of the most important aspects of crop productivity, knowing the amount and the locations of weeds has been a problem that experts have faced for several decades. This paper presents three methods for weed estimation based on deep learning image processing in lettuce crops, and we compared them to visual estimations by experts. One method is based on support vector machines (SVM) using histograms of oriented gradients (HOG) as feature descriptor. The second method was based in YOLOV3 (you only look once V3), taking advantage of its robust architecture for object detection, and the third one was based on Mask R-CNN (region based convolutional neural network) in order to get an instance segmentation for each individual. These methods were complemented with a NDVI index (normalized difference vegetation index) as a background subtractor for removing non photosynthetic objects. According to chosen metrics, the machine and deep learning methods had F1-scores of 88%, 94%, and 94% respectively, regarding to crop detection. Subsequently, detected crops were turned into a binary mask and mixed with the NDVI background subtractor in order to detect weed in an indirect way. Once the weed image was obtained, the coverage percentage of weed was calculated by classical image processing methods. Finally, these performances were compared with the estimations of a set from weed experts through a Bland&ndash, Altman plot, intraclass correlation coefficients (ICCs) and Dunn&rsquo, s test to obtain statistical measurements between every estimation (machine-human), we found that these methods improve accuracy on weed coverage estimation and minimize subjectivity in human-estimated data.

Medical image segmentation is a key topic in image processing and computer vision. Existing literature mainly focuses on single-organ segmentation. However, since maximizing the concentration of radiotherapy drugs in the target area with protecting the surrounding organs is essential for making effective radiotherapy plan, multiorgan segmentation has won more and more attention. An improved Mask R-CNN (region-based convolutional neural network) model is proposed for multiorgan segmentation to aid esophageal radiation treatment. Due to the fact that organ boundaries may be fuzzy and organ shapes are various, original Mask R-CNN works well on natural image segmentation while leaves something to be desired on the multiorgan segmentation task. Addressing it, the advantages of this method are threefold: (1) a ROI (region of interest) generation method is presented in the RPN (region proposal network) which is able to utilize multiscale semantic features. (2) A prebackground classification subnetwork is integrated to the original mask generation branch to improve the precision of multiorgan segmentation. (3) 4341 CT images of 44 patients are collected and annotated to evaluate the proposed method. Additionally, extensive experiments on the collected dataset demonstrate that the proposed method can segment the heart, right lung, left lung, planning target volume (PTV), and clinical target volume (CTV) accurately and efficiently. Specifically, less than 5% of the cases were missed detection or false detection on the test set, which shows a great potential for real clinical usage.

Pomegranate acidity is one of the important characteristics of this fruit because it determines its uses. By figuring out the pH of the pomegranate, the consumers can choose the fruit appropriate to their needs and tastes. In this study, the pH of 200 pomegranates was measured, and according to the properties extracted from the pomegranates' images, their pH was found to be not destructive. By processing pomegranate images and measured characteristics and using sensitivity analysis, the researchers identified four parameters that had the most effects on pH changes. The properties of pomegranate crown were also used for this purpose. With the help of three algorithms of artificial intelligence—the adaptive neuro-fuzzy inference system (ANFIS), artificial neural network (ANN), and response surface methodology (RSM)—a model was designed for the estimation of the pH of the pomegranate. The best result was obtained by the ANFIS model, in which the R2 and MSE values were equal to 0.984 and 0.202.

The main aim of the presented research was to assess the possibility of utilizing geometric features in object classification.Studies were conducted using X-ray images of kernels belonging to three different wheat varieties: Kama, Canadian andRosa. As a part of the work, image processing methods were used to determine the main geometric grain parameters,including the kernel area, kernel perimeter, kernel length and kernel width. The results indicate significant differencesbetween wheat varieties, and demonstrates the importance of their size and shape parameters in the classification process.The percentage of correctness of classification was about 92% when the k-Means algorithm was used. A classificationrate of 93% was obtain using the K-Nearest Neighbour and Support Vector Machines. Herein, the Rosa variety was betterrecognized, whilst the Canadian and Kama varieties were less successfully differentiated.

The objective of this study was to analyze the differences in blinking kinematics of spontaneous and voluntary blinks using for the first time a self-developed, non-invasive, and image processing–based method. The blinks of 30 subjects were recorded for 1 min with the support of an eye-tracking device based on a high-speed infrared video camera, working at 250 frames per second, under two different experimental conditions. For the first condition, subjects were ordered to look in the straightforward position at a fixation target placed 1 m in front of them, with no further instructions. For the second, subjects were additionally asked to blink only following a sound signal every 6 s. Mean complete blinks increased by a factor of 1.7 from the spontaneous to the voluntary condition while mean incomplete blinks reduced significantly by a factor of 0.4. In both conditions, closing mean and peak velocities were always significantly greater and durations significantly lower than opening ones. When comparing the values for each condition, velocities and amplitudes for the voluntary condition were always greater than the corresponding values for spontaneous. Voluntary blinks revealed significant kinematic differences compared to spontaneous, thus supporting a different supranuclear pathway organization. This study presents a new method, based on image analysis, for the non-invasive kinematic characterization of blinking.

There is yet an application for monitoring plant condition using the Normalized Difference Vegetation Index (NDVI) method for Capsicum Frutescens (C.F) or chili. This study was carried out in three phases, where the first and second phases are to create NDVI images and recognize and extract features from NDVI images. The last stage is to assess the efficiency of Neural Network (N.N.), Naïve Bayes (N.B.), and Logistic Regression (L.R.) models on the classification of chili plant health. The images of the chili plant will be captured using two types of cameras, which can be differentiated by whether or not they have an infrared filter. The images were collected to create datasets, and the NDVI images' features were extracted. The 120 NDVI images of the chili plant were divided into training and test datasets, with 70.0% training and 30.0% test. The extracted data was used to test the classification accuracy of classifiers on datasets. Finally, the N.N. model was found to have the highest classification accuracy, with 96.4 % on the training dataset and 88.9 % on the test dataset. The state of the chili plant can be predicted based on feature extraction from NDVI images by the end of the study.

Image registration is an important component of many image processing problems which often require optimizing over some set of parameters. In the image registration problem, one attempts to determine the best transformation for aligning similar images. Such problems typically require minimizing a dissimilarity measure with multiple local minima. We describe a global optimization algorithm and apply it to the problem of identifying the best transformation for aligning two images.