Search

A novel Palmprint Recognition System (PRS) using Deep Supervised Learning (DSL) classifier is proposed in this research work. To divulge the novelty, a Deep Supervised Contour Fractal Dimension Analysis Model for Palmprint Recognition (DCFPR) is put forward. That has a novel Region-based Contour Fractal Dimension (RCFD) feature extraction approach and a Deep Supervised Learning (DSL) classifier approach for acquiring the higher recognition and identification accuracy rate. To accomplish the RCFD approach, traced all the edges/contours of 2D Palmprint Region of Interest (2D-PROI) image using Canny edge detection algorithm and then split into several regions. At each region, Fractal Dimension (FD) and the Slope value (S) are computed in an idiosyncratic manner using the Box-Counting procedure and then accumulate all FDs and Ss of all regions to create a distinctive feature vector. Classify this feature vector using Deep Supervised Learning (DSL) classifier approach to authenticate the genuine person of the taken palmprint at a higher accuracy rate. In this research, the multi-spectral 2D-PROI image database derived from PolyU, Hong Kong Polytechnic University, Hong Kong. The proposed model has been examined and evaluated with various metrics and found with 98% of authentication accuracy. [ABSTRACT FROM AUTHOR]

This research was aimed to explore the application value of intelligent algorithm-based digital images in Da Vinci robot-assisted treatment of patients with gastric cancer surgery. 154 patients were included as the research objects, with 89 cases in the control group underwent laparoscopic surgery, and 65 cases in the experimental group underwent robotic surgery. According to the propensity score, the patients in two groups were pair matched (1: 1), of which 104 cases (52 cases in each group) were successfully matched. The general data of patients, the changes in the images before and after the algorithm processing, the intraoperative and postoperative conditions, the pathological examination results, and the follow-up information were observed after matching. Compared with the original images, the images processed by the thread image edge detection algorithm had the significantly improved clarity, as well as highly reduced artifacts and noises. The sensitivity, specificity, and accuracy of image-assisted diagnosis were improved remarkably, showing the differences of statistical significance (P < 0.05). The total time of surgery, intraoperative bleeding, CRP (1d and 3d after surgery), and postoperative total abdominal drainage showed the significant differences as well (P < 0.05). The surgeries of patients in both groups met R0 resection (no tumor infiltration within 1 mm of the surgical margin), but there was a significant difference in the number of lymph node dissections (P < 0.05). The overall survival rates of patients in the experimental group and the control group were 83.0% and 76.1%, respectively, 2 years after surgery, with no significant difference (P > 0.05). The thread image edge detection algorithm produced a better processing effect on the images, which greatly improved the diagnostic sensitivity, specificity, and accuracy. Compared with endoscopic surgery, robotic surgery has better postoperative recovery, safety and reliability, and obvious advantages of minimally invasive surgery. [ABSTRACT FROM AUTHOR]

Computational meta-optics brings a twist on the accelerating hardware with the benefits of ultrafast speed, ultra-low power consumption, and parallel information processing in versatile applications. Recent advent of metasurfaces have enabled the full manipulation of electromagnetic waves within subwavelength scales, promising the multifunctional, high-throughput, compact and flat optical processors. In this trend, metasurfaces with nonlocality or multi-layer structures are proposed to perform analog optical computations based on Green's function or Fourier transform, intrinsically constrained by limited operations or large footprints/volume. Here, we showcase a Fourier-based metaprocessor to impart customized highly flexible transfer functions for analog computing upon our single-layer Huygens' metasurface. Basic mathematical operations, including differentiation and cross-correlation, are performed by directly modulating complex wavefronts in spatial Fourier domain, facilitating edge detection and pattern recognition of various image processing. Our work substantiates an ultracompact and powerful kernel processor, which could find important applications for optical analog computing and image processing. Here, the authors propose a Fourier-based metaprocessor to impart customized highly flexible transfer functions for analog computing. Differentiation and cross-correlation are performed to substantiate the ultracompact and high-throughput kernel processor. [ABSTRACT FROM AUTHOR]

In the field of computer vision, image saliency target detection can not only improve the accuracy of image detection but also accelerate the speed of image detection. In order to solve the existing problems of the saliency target detection algorithms at present, such as inconspicuous texture details and incomplete edge contour display, this paper proposes a saliency target detection algorithm integrating multiple information. The algorithm consists of three processes: preprocessing process, multi-information extraction process, and fusion optimization process. The frequency domain features of the image are calculated, the algorithm calculates the frequency domain features of the image, introduces power law transform and feature normalization, improves the frequency domain features of the image, saves the information of the target region, and inhibits the information of the background region. On three public MSRA, SED2, and ECSSD image datasets, the proposed algorithm is compared with other classical algorithms in subjective and objective comparison experiments. Experimental results show that the proposed algorithm can not only accurately and comprehensively extract significant target regions but also retain more texture information and complete edge information while satisfying the human visual experience. All evaluation indexes are significantly better than the comparison algorithm, showing good reliability and adaptability. [ABSTRACT FROM AUTHOR]

In this paper, we consider the problem of feature reconstruction from incomplete X-ray CT data. Such incomplete data problems occur when the number of measured X-rays is restricted either due to limit radiation exposure or due to practical constraints, making the detection of certain rays challenging. Since image reconstruction from incomplete data is a severely ill-posed (unstable) problem, the reconstructed images may suffer from characteristic artefacts or missing features, thus significantly complicating subsequent image processing tasks (e.g., edge detection or segmentation). In this paper, we introduce a framework for the robust reconstruction of convolutional image features directly from CT data without the need of computing a reconstructed image first. Within our framework, we use non-linear variational regularization methods that can be adapted to a variety of feature reconstruction tasks and to several limited data situations. The proposed variational regularization method minimizes an energy functional being the sum of a feature dependent data-fitting term and an additional penalty accounting for specific properties of the features. In our numerical experiments, we consider instances of edge reconstructions from angular under-sampled data and show that our approach is able to reliably reconstruct feature maps in this case. [ABSTRACT FROM AUTHOR]

In order to improve the quality of edge details of remote sensing image and solve the problem of large-scale holes and edge loss in remote sensing image, a new hole filling and optimization algorithm of remote sensing image based on bilateral filtering is proposed in this paper. The compensation function of similarity discrimination and Thiele continued fraction approximate exponential function are used to improve the traditional bilateral filtering algorithm. After the threshold is determined by histogram, the image is binarized to generate hole mask. The constraint term is added to the improved bilateral filtering algorithm for further optimization. According to the characteristics that pixels with the same color have the same gray value in a certain range, the hole area of remote sensing image is filled. The experimental results show that the algorithm can accurately fill the holes in the remote sensing image, not only restore the edge of the image, but also maintain the smoothness of the image. It has good filling performance, high image quality after optimization, image signal-to-noise ratio remains above 32 dB, and time complexity is low. [ABSTRACT FROM AUTHOR]

With the usage of computer visual technology in civil engineering, pavement crack survey with imaging sensor gained wide attention in the past years. Unfortunately, it is still a challenge to achieve the satisfying results. This paper presents a pavement crack survey approach based on edge detection for laser data. At first, the LS-40 line-laser scanner is implemented to achieve 3D pavement surface data. With the advantage of the various depth information exhibited in the pavement data, an enhanced edge detection based on fractional differential is proposed for 3D crack segmentation. The proposed method could effectively enhance the crack boundary and maintain texture details, which can guarantee the high accuracy in crack segmentation. Moreover, a novel plane fitting method based on dynamic threshold is studied to calculate crack depth information. It can not only identify and remove invalid points effectively, but also accomplish plane calculation with errors in three directions. Experiments verify that the proposed approach can achieve the satisfying result and can work well in F-measure system. [ABSTRACT FROM AUTHOR]

Recently, several recurrent neural network (RNN)-based models have been proposed to delineate the outlines of buildings from very high resolution (VHR) remote sensing images. These models first use convolutional neural networks (CNNs) to recognize the boundary fragments by learning probability maps of both edges and corners and then feed them into RNN to find and link a set of sequent corners into external boundaries of buildings. However, caused by the category imbalance of edges and corners, the local ambiguity of edge detection is very serious, which significantly affects the accuracy of predicted outline corners. To tackle this challenge, this article introduces a convolutional RNN embedded with line segment information (LSI-RNN), a novel network that aims to directly detect line segment instead of edges. To achieve this, LSI-RNN utilizes an additional cotraining branch to generate an attraction field map (AFM) by neural discriminative dimensionality reduction (NDDR) layer. Consequently, the conventional classification problem of edges is converted to a regression problem of line segments, thus solving the aforementioned issues. Experimental results over three remote sensing datasets with different spatial resolutions show that the proposed method consistently outperforms other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

At image-guided radiotherapy, technique, different imaging, and monitoring systems are utilized for (i) organs border detection and tumor delineation during the treatment planning process and (ii) patient setup and tumor localization at pretreatment step and (iii) real-time tumor motion tracking for dynamic thorax tumors during the treatment. In this study, the effect of fuzzy logic is quantitatively investigated at different steps of image-guided radiotherapy. Fuzzy logic-based models and algorithms have been implemented at three steps, and the obtained results are compared with commonly available strategies. Required data are (i) real patients treated with Synchrony Cyberknife system at Georgetown University Hospital for real-time tumor motion prediction, (ii) computed tomography images taken from real patients for geometrical setup, and also (iii) tomography images of an anthropomorphic phantom for tumor delineation process. In real-time tumor tracking, the targeting error averages of the fuzzy correlation model in comparison with the Cyberknife modeler are 4.57 mm and 8.97 mm, respectively, for a given patient that shows remarkable error reduction. In the case of patient geometrical setup, the fuzzy logic-based algorithm has better influence in comparing with the artificial neural network, while the setup error averages is reduced from 1.47 to 0.4432 mm using the fuzzy logic-based method, for a given patient.Finally, the obtained results show that the fuzzy logic based image processing algorithm exhibits much better performance for edge detection compared to four conventional operators. This study is an effort to show that fuzzy logic based algorithms are also highly applicable at image-guided radiotherapy as one of the important treatment modalities for tumor delineation, patient setup error reduction, and intrafractional motion error compensation due to their inherent properties. [ABSTRACT FROM AUTHOR]

Blur classification is important for blind image restoration. It is difficult to detect blur in a single image without knowing any additional information. This paper uses edge detection methods and a deep learning convolutional neural network called Resnet-50 to classify blurry-type images. The Resnet model effectively reduces the gradient vanishing problem and uses connection skipping to train the network. Typically, images are subject to defocus blur and motion blur, which are caused by the incorrect depth of field and the movement of objects during capture. The dataset used here is the blur dataset from Kaggle, which consists of sharp images, images with blur, and motion blur. In this paper, edge detection methods are applied to images using Laplace, Sobel, Prewitt, and Roberts filters and derived features such as mean, variance, and maximum signal-to-noise ratio, which are used to train a classification algorithm for image classification. [ABSTRACT FROM AUTHOR]

Brain Tumors are the leading cause of cancer death in children. They are caused by the abnormal and uncontrolled growth of cells inside the brain or spinal canal. Classification of brain tumors using machine learning technology is very relevant for radiologists to confirm their analysis more effectively and quickly. Segmentation algorithm identified for detecting the tumor from the MRI brain scans need to detect shapeless tumor growth perfectly. Sobel edge detection is one of the widely used edge detection techniques in which only information along horizontal and vertical directions are considered. In this research, Sobel algorithm with 8-directional template is implemented for improving the detection of edges in brain tumor MRI images. The proposed algorithm is compared with other traditional edge detection algorithms. The performance of the proposed algorithm is analyzed in terms of MSE, RMSE, Entropy, SNR and PSNR. Analysis shows that 8-Sobel is comparatively the most suitable technique for analyzing brain tumor MRI images. Active contouring segmentation algorithm is applied on the edge detected images to verify the classification accuracy of segmented tumor. [ABSTRACT FROM AUTHOR]

Image self-coupling and feature interference lead to poor retrieval performance in massive image retrieval of mobile terminals. This paper proposes a massive image retrieval method of mobile terminals based on weighted aggregation depth features. The pixel big data detection model of massive images of mobile terminals is constructed, the collected pixel information of massive images of mobile terminals is restructured, the edge contour feature parameter set of massive images of mobile terminals is extracted, the feature fusion processing of massive images of mobile terminals is carried out in gradient pixel space by means of feature reconstruction and gray moment invariant feature analysis, the depth feature detection of massive images of mobile terminals is realized by using weighted aggregation method, the gradient value of pixels of massive images of each mobile terminal is calculated, and the optimized retrieval of massive images of mobile terminals is realized according to the fusion result of gradient weighted information. Simulation results show that this method has better feature clustering, stronger image detection and recognition, and anti-interference ability and improves the precision and recall of image retrieval. [ABSTRACT FROM AUTHOR]

Proposed research has focused on content-based image retrieval in medical field where the tumor is detected from the given dataset. The objective of the research is to reduce the tumor detection time. This research is considering canny based edge detection, GLCM, ANN, SVM techniques to achieve the objective. The objective of research is to study and analyze various medical image retrieval techniques and propose hybrid technique using feature extraction, feature selection, and classification techniques. Then the performance of proposed technique is evaluated and validated. In this research work, the proposed method comprises four stages. Initially, pre-processing of the images is done. During this stage, the image is resized and RGB to gray conversion is applied. The edge detection mechanism is applied afterward. In the second phase, the image features would be extracted using GLCM, then matching of images with the database is done. Then the tumor is detected according to the features extracted from the image. The third phase is to perform classification using an artificial neural network to detect the tumor and normal image. Then SVM would be applied to detect the shape of the tumor. Finally, the results of the proposed work would be compared to previous research for evaluation. [ABSTRACT FROM AUTHOR]

Detection of crack on concrete is very important for the renovation of concrete structures. Besides, little cracks that seem immaterial ought to develop and sometimes cause extraordinary basic disappointment. This issue identifies with the basic wellbeing and unwavering quality, consequently, it should be settled as ahead of schedule as plausible to stay away from additional loss. Manual review needs objectivity inside the quantitative investigation. Converting an image from RGB to grayscale, image filtering with Gaussian filter, subtraction, blurring, image segmentation, edge detection, etc. many activities of image processing with neural Network. The algorithm is composed of two parts. The First is image processing with neural networks and the second is image classification technique using machine learning algorithms. First Remove the background using filtering and improved subtraction method and morphological operation and then edge detection. Then the next step is identifying the crack and non-crack image. And if the crack image identifies. The purpose algorithm verifies the two-step tested with backpropagation neural network Thus, we tend to expand the version to identify the existence of cracks and we that teach the version to categorize the images using naïve Bayes, logistic regression, and Support Vector Machine type algorithms and decide the fine model to classify concrete photographs as crack and non-crack. [ABSTRACT FROM AUTHOR]

Computation Unit plays vital role in satellite image processing systems. Division is the least commonly used of the four basic arithmetic operations because it is too difficult to utilise. The primitive use of division is an iterative subtraction. Approximate computing is a new trend in digital design that forgoes the need for accurate computation in favour of increased speed and power performance. For error tolerant application approximate computing can reduce design complexity while increasing performance and power efficiency. This work provides new approximation compressors as well as an approach for using them to create efficient approximate multipliers. We have summed up approximate multipliers for different operand lengths using the proposed method. Detailed simulation results show that the Modified architectures achieves significant improvements in accuracy and efficiency as well as reduced area, power and latency compared to existing multiplier designs to improve the compressor efficiency recommendations are based on approximate multiplier system. The Proposed system is suitable for satellite image processing and radar image processing system with high accuracy. The proposed system is implemented in canny edge detection algorithm for measuring its performance. [ABSTRACT FROM AUTHOR]

Edges are a key feature employed in various computer vision applications namely segmentation, object recognition, feature tracking and 3D reconstruction. Edges provide key information with regards to object presence, shape, form and detail which aid in many computer vision tasks. While there are various edge detection techniques in literature, challenges in edge detection remain. Varying image contrast due to non uniform scene illumination and imaging resolution affects the edge information obtained from any given image. The edge detection results are characterised by missing edges, edge fragmentation and some false positive edges. Gradient based edge detectors are the most commonly used detectors. These detectors all suffer from aforementioned challenges. In this, paper we present an edge detection framework that aims to recover long unfragmented edges from satellite images. This is achieved by using an edge accumulator that operates on the entire edge detection parameter space. Gradient based edge detectors rely on thresholding to retrieve salient edges. This usually results in missed or noisy edges. To counter this, the accumulator is run over a wide parameter space, growing edges at each accumulator level while maintaining edge position using a localisation filter. The results are longer unbroken edges that are detected for most objects, even in shadowy regions and low contrast areas. The results show improved edge detection that preserves the form and detail of objects when compared to current gradient based detectors. [ABSTRACT FROM AUTHOR]

Coastal areas all over the world are usually exposed to intensive change and transformation processes resulting in a variety of natural, physical, and socio-economic problems. Körfez province, located along the İzmit Bay of Marmara Sea, Turkey, has been one of these coastal areas that has become a major point for industrial facilities and highly populated urbanized area since 1960s. Therefore, the analysis of the spatial changes in the land use patterns of the province has a critical role in the success of the physical planning processes and the protection of the coastal areas. In order to highlight this critical role, temporal change detection analysis for Körfez province covering a 6-year period and 5 land use classes was made using 2009 and 2015 SPOT imagery and thematic maps. Reclassified CORINE data, development plans, and land survey results were benefited for the supervised classification of the images. Four hundred eighty control points for each year were used to achieve a strong accuracy tested by Kappa coefficient. The spatio-temporal change detection results revealed a 22.5% and 2.3% decrease in agricultural lands and sea areas respectively, while there was an increase of 16.6% in forest-green areas, 6.4% in settlement areas, and 74.1% in lake areas. The results are believed to be significant input data to facilitate coastal and physical development planning over the area, and thus make sustainable land use decisions to protect the delicate landscape and coastal characteristics, while providing a sound risk management plan. [ABSTRACT FROM AUTHOR]

With the extensive application of unmanned aerial vehicles (UAVs), there is an increasing demand for fast processing of coloured UAV images. The coloured UAV image pixels are usually represented by quaternion vectors with three bands of visible light corresponding to the three imaginary parts of the pure imaginary quaternion. Accordingly, the colour image edge points can be determined based on the quaternion polar coordinating the rotation principle. Here, a quaternion‐based improved cuckoo algorithm is proposed to perform fast processing for UAVs images. In particular, a novel guiding equation is used to optimize the positions of the improved cuckoo algorithm before the Levi flight. Furthermore, a novel disturbance equation is used to obtain a varied location for the next location after the Levi flight. Comprehensive experiments are conducted to evaluate the performance of the proposed solution. The experimental results showed that the proposed method significantly reduces the image processing time and remarkably improves the quality. [ABSTRACT FROM AUTHOR]

When the traditional dark channel prior (DCP) algorithm is used for image defogging, it faces some problems such as unsatisfactory restoration of the target edge details, distortion in large‐scale and high‐brightness sky regions. To solve these problems, this paper proposes an improved dark channel defogging algorithm based on the HSI colour space, named the IDCP algorithm. First, an asymmetric mean filter window is used to obtain the modified dark channel image to improve the grey value mutation in the traditional dark channel image. Based on this work, an improved global atmospheric transmittance calculation method is proposed, which effectively improves the inapplicability of the dark channel prior in large‐scale and high‐brightness sky regions. Finally, the Laplacian operator is used to sharpen the image to enhance the target edge information. Simulation results show that the proposed algorithm can effectively solve the distortion phenomenon caused by the traditional DCP algorithm when handling large‐scale and high‐brightness sky regions, improve the target edge details, and restore the true colour of the image scene. [ABSTRACT FROM AUTHOR]

Receiving the most relevant images from image databases is a challenging and critical issue in many applications. Texture is a substantial feature of an image which depicts the spatial behavior of gray-levels in any given neighborhood. Color features uses a variety of color systems and are meaningful to differentiate image segments. Presently, many of the favorable methods for image content description use local descriptors as their starting point with several conducts. The content in an image may appear in some feature descriptor's components more accurately than other components. This paper presents an innovative idea for local image retrieval using a new methodology for feature extraction welding named Blend of Extended Features' Components (BoEFC). The paper shows that an image's content may be described individually by the feature descriptor's components or collectively through the Extended Feature Components (EFC). Retrieval options are attempted using a selection method of Feature Components then the relevant results are collected and ordered according to newly adapted feature similarity measures. The experiments were performed using a general-purpose image database which itself represent a challenge and the INRIA Holiday image database. The experiments was performed by varying the EFCs to compute recall, precision and draw the Precision-Recall (PR) curves which showed increased recall and precision with some components. In addition, calculating mAP and mAR showed increased performance due to the BoEFC blending process. [ABSTRACT FROM AUTHOR]

Fuzzy c‐means (FCM) is a time‐honored method for its simplicity of calculation and ease of understanding. However, the previous image segmentation work exploiting FCM could not achieve the ideal effect in image edge recognition of the fuzzy information or antinoise of the pixel. This paper exploits the spatial T‐spherical fuzzy c‐means model with bias correction (EM‐sTSFCMpq) to improves the effect of antinoise and image edge recognition. First, the image is transformed into a T‐spherical fuzzy set by a novel T‐spherical fuzzification technology with the processing of the bias fields. Second, the membership degree of the image is updated through the proposed T‐spherical FCM algorithm. Third, a novel calculation method of weighted combination is exploited to integrate spatial information to overcome the noise. The proposed method is applied to three‐dimensional MR image segmentation and the Berkeley segmentation datasets to illustrate the accuracy and efficiency. [ABSTRACT FROM AUTHOR]

Retinal segmentation is a prerequisite for quantifying retinal structural features and diagnosing related ophthalmic diseases. Canny operator is recognized as the best boundary detection operator so far, and is often used to obtain the initial boundary of the retina in retinal segmentation. However, the traditional Canny operator is susceptible to vascular shadows, vitreous artifacts, or noise interference in retinal segmentation, causing serious misdetection or missed detection. This paper proposed an improved Canny operator for automatic segmentation of retinal boundaries. The improved algorithm solves the problems of the traditional Canny operator by adding a multi-point boundary search step on the basis of the original method, and adjusts the convolution kernel. The algorithm was used to segment the retinal images of healthy subjects and age-related macular degeneration (AMD) patients; eleven retinal boundaries were identified and compared with the results of manual segmentation by the ophthalmologists. The average difference between the automatic and manual methods is: 2–6 microns (1–2 pixels) for healthy subjects and 3–10 microns (1–3 pixels) for AMD patients. Qualitative method is also used to verify the accuracy and stability of the algorithm. The percentage of "perfect segmentation" and "good segmentation" is 98% in healthy subjects and 94% in AMD patients. This algorithm can be used alone or in combination with other methods as an initial boundary detection algorithm. It is easy to understand and improve, and may become a useful tool for analyzing and diagnosing eye diseases. [ABSTRACT FROM AUTHOR]

Radiology is a broad subject that needs more knowledge and understanding of medical science to identify tumors accurately. The need for a tumor detection program, thus, overcomes the lack of qualified radiologists. Using magnetic resonance imaging, biomedical image processing makes it easier to detect and locate brain tumors. In this study, a segmentation and detection method for brain tumors was developed using images from the MRI sequence as an input image to identify the tumor area. This process is difficult due to the wide variety of tumor tissues in the presence of different patients, and, in most cases, the similarity within normal tissues makes the task difficult. The main goal is to classify the brain in the presence of a brain tumor or a healthy brain. The proposed system has been researched based on Berkeley's wavelet transformation (BWT) and deep learning classifier to improve performance and simplify the process of medical image segmentation. Significant features are extracted from each segmented tissue using the gray-level-co-occurrence matrix (GLCM) method, followed by a feature optimization using a genetic algorithm. The innovative final result of the approach implemented was assessed based on accuracy, sensitivity, specificity, coefficient of dice, Jaccard's coefficient, spatial overlap, AVME, and FoM. [ABSTRACT FROM AUTHOR]

With increasing spatial resolution, the differences in nonlinear radiation and geometric properties between optical and synthetic aperture radar (SAR) images will be magnified, which will lead to lower registration accuracy. This paper addresses this problem and proposes an automatic registration method for HR optical and SAR images using the uniform optimized feature and the extended phase congruency (EPC) model. First, we combine two different gradient operators and a quadtree algorithm to improve the detection performance of the multi-scale Harris detector, especially for the repeatability and uniformity of feature points in optical and SAR images with large nonlinear radiation and severe speckle noise. Next, we use the EPC model with illumination and contrast invariance to generate the multi-scale orientation index map (MS-OIM) and the multi-orientation phase congruency amplitude map (MO-PCAM) and then build a novel GLOH-like local descriptor to obtain corresponding features based on the two feature maps above. Finally, the fast sample consensus (FSC) method is utilized to remove false matches and calculate the transformation parameters of sensed image based on the piecewise linear model. The detection results on synthetic data show that the proposed detector has better repeatability and uniformity than the other three classical detectors. The registration results obtained on real data indicate that our method is effective for optical and SAR images with speckle noise interference and nonlinear radiometric differences and achieves high registration accuracy. [ABSTRACT FROM AUTHOR]

As the cocoa industry continues to grow, there is an increasing need for greater efficiency and higher levels of quality in all areas. The objective assessment of pod stem cut quality is one such critical area, as it not only directly impacts productivity but wider industry economics. Despite this, and the significance of cut quality in other agricultural applications, there is little done in the area of developing an objective and reliable assessment method. This work proposes, develops and tests a Fourier based image processing approach for assessing cut quality. The proposed Fourier Peak Index (FPI) method is implemented in MATLAB 2013 via a series of algorithms. Further, a windowed FPI (WFPI) is also developed and implemented in the same environment. Both methods are tested using a set of 40 images, comprising of 10 reference images, 15 poor cut images and 15 good cut images. The results obtained showed that the FPI method had a 93% accuracy in categorising good cuts, 60% accuracy in categorising poor cuts and an overall accuracy of approximately 77%. It was particularly noted that poor cuts with long, smooth excess bark material attached to the stems, were poorly categorised by the FPI method. Additionally, the method's effectiveness was found to be significantly influenced by image lighting, as this determined the amount of data loss during the image binarisation step. Notwithstanding, the WFPI method was found to be effective in categorising the images that were incorrectly categorised by the FPI method. The combined efforts of both methods had the potential to increase detection and categorisation accuracy to a maximum of 97%. [ABSTRACT FROM AUTHOR]

Edge is A boundary between two disjoint regions formed by a set of connected pixels. The canny edge detector is a computational edge detection operator that detects a wide range of edges in images. The determination of the threshold is the most important step in edge detection based on the Canny edge detection algorithm, on which the success of a generation of true edge maps depends. Ant colony optimization (ACO) is a society metaheuristic that can be used for a variety of optimization problems. It has been used to handle a variety of image processing issues, including image segmentation, classification, analysis, and edge detection. In this paper perform the ACO Canny edge detector, then apply ACOseperatly, For the color file (256*256) that is used in the algorithms. After analyzing the results of the algorithms, it was determined that the ACO is the better than ACO canny edge detecting algorithm. While the second method ACO Canny is better than the ACO when the evaporation rate is equal to 0.001. and The most effective factor in the algorithm's work is pheromone decay, as the best results were obtained when this parameter was reduced to 10-10. [ABSTRACT FROM AUTHOR]

The Artificial Intelligence (AI) edge detection phase is a multi-step technique for detecting edges in any images. The use of machine learning models to explore medical data and reveal insights to assist improve health outcomes and patient situations is known as edge detection in artificial intelligence. The proposed algorithm which is named as "Domain Specific ANN Heuristic Edge Detection algorithm for CNN based MRI Classification" (DAHEDA) is the amalgamation of four intertwined functional algorithms. They are Tabu Search Heuristics Symmetrical Pattern Identifier (ASHSPT), Fuzzy Symmetric Pattern Table Manager (FSPTM), ANN Edge Detection Algorithm Selector (AEDA) and CNN MRI Classifier. These algorithms are interlaced in a way to improve the MRI classification metrics without significant difference in processing speed. [ABSTRACT FROM AUTHOR]

Image segmentation is an important process in computer vision. Recently fuzzy logic based edge detection is heavily investigated as by changing the number of rules edge detection can be improved. However, due to large colour variations in the images false edges are detected and even using fuzzy rules they cannot be reduced significantly. These falsely detected edges can be controlled by using smoothen filter while controlling the degree of smoothness. This paper, presents fuzzy logic based edge detection mechanism while using Guided L0 smoothen filter for the smoothening of image under various degree of smoothens. Simulation results for edge detection is presented for Canny, Sobel, Fuzzy logic based edge detection and finally fuzzy logic edge detection with inclusion of L0 smoothen filter. The results are compared with classical and modern methods. Simulation is performed on Berkley Segmentation Database (BSD) and USC-SIPI Image Database while considering more than 100 images. The obtained F-measure is as high as 0.848. [ABSTRACT FROM AUTHOR]

There are over 180 different currencies on the globe. Each currency is distinct in terms of scale, paper, colors, patterns, text, etc. It is tough to keep track of all of the different currencies. Often, determining whether a currency is genuine or counterfeit is challenging. Many methods investigate currency recognition. In this review, the following techniques are widely used in image processing for currency recognition tools, including acquisition, image enhancement, segmentation, and object detection and recognition. This review shows the ability of image processing techniques, including pre-processing, edge detection, feature extraction, and thresholding, to recognize paper currency have been used. Thus, the outcome of this review indicates that for currency recognition the techniques that used for feature extraction are (LBP, SIFT, SURF and ROI) and choosing the best technique depends on the application. [ABSTRACT FROM AUTHOR]

The detection of fruit, including accuracy and speed is of great significance for robotic harvesting. Nevertheless, attributes such as illumination variation, occlusion, and so on have made fruit detection a challenging task. A robust YOLOFig detection model was proposed to solve detection challenges and to improve detection accuracy and speed. The YOLOFig detection model incorporated Leaky activated ResNet43 backbone with a new 2,3,4,3,2 residual block arrangement, spatial pyramid pooling network (SPPNet), feature pyramid network (FPN), complete (CIoU) loss, and distance DIoU−NMS to improve the fruit detection performance. The obtained average precision (AP) and speed (frames per second or fps) respectively under 2,3,4,3,2 residual block arranged backbone for YOLOv3b is 78.6% and 69.8 fps, YOLOv4b is 87.6% and 57.1 fps, and YOLOFig is 89.3% and 96.8 fps; under 1,2,8,8,4 residual block arranged backbone for YOLOv3 is 77.1% and 56.3 fps, YOLOv4 is 87.1% and 52.5 fps, and YOLOResNet70 is 87.3% and 79 fps; and under 3,4,6,3 residual block arranged backbone for YOLOResNet50 is 85.4% and 77.1 fps. An indication that the new residual block arranged backbone of 2,3,4,3,2 outperformed 1,2,8,8,4 on an average AP of 1.33% and detection speed of 15.2%. Finally, the compared results showed that the YOLOFig detection model performed better than other models at the same level of residual block arrangement. It can better generalize and is highly suitable for real‐time harvesting robots. [ABSTRACT FROM AUTHOR]

Morphological edge detection is a principal component in pattern recognition and machine vision. Traditional edge detection operators only take pixel mutual into consideration. However, the edges are influenced not only by pixel mutual but also by the boundary characteristics. Here, the vector co‐occurrence morphological edge detection operator is proposed, which takes the pixel and boundary information both into consideration. The vector co‐occurrence algorithm is exploited to resist the influence of the noise points and detect the edges from the colour image rather than the grey image. And, we lead to define a precise definition of the manner of sorting high‐dimensional data for the colour image. The experiment results always illustrate the advancement and practicability of our methods against the baseline method. In terms of experiments, the BSDS500 dataset is introduced to compare and analyse with other algorithms. Based on the standard benchmark index evaluation in the BSDS500 dataset, the ODS and AP of various algorithms are compared and analysed. [ABSTRACT FROM AUTHOR]

The need for line detection in images is growing rapidly due to its importance in many image processing applications. The selection of an appropriate line detection method is essential for accurate detection of line pixels, but few studies provide an analytical basis for selecting a specific line detection method. In this study, to solve the problem, a method to analytically determine the signal-to-noise ratio (SNR) of line detection methods is proposed. Three line detection methods were selected for comparison: edge-detection (ED)-based, second derivative (SD)-based, and the sum of gradient angle differences (SGAD)-based line detection methods. Then, this study quantifies the SNR of the three line detectors through error propagation and signal noise coupling. In addition, the derived SNRs are graphically visualized to explicitly compare the performance of line detectors. Then, the quantified SNRs were validated by showing that they are highly correlated with the completeness and correctness observed in the experiment with a set of natural images. The experimental results show that the proposed SNR analysis can be used to select or design a suitable line detector. [ABSTRACT FROM AUTHOR]

This study was to explore the effect of computed tomography (CT) images processed by image edge detection technology based on the improved Canny algorithm in the diagnosis of stroke patients with mobility dysfunction and to evaluate the clinical application value of early rehabilitation nursing (ERN). 114 patients who were diagnosed and treated in hospital and were suspected of having stroke movement dysfunction were selected as the research objects, and they were randomly divided into two groups, each with 57 patients. Patients in the control group were diagnosed with conventional CT examination, and the patients in observation group were diagnosed based on the CT images processed by the image edge detection technology based on the improved Canny algorithm. Patients in the observation group were divided into a group C and a group O. Patients (27 cases) in group O received rehabilitation training within 3 days after their vital signs were stabilized, and patients (30 cases) in group C received rehabilitation training within 3∼7 days after their condition was stabilized. The CT image diagnosis effects on patients of the control group and the observation group were analyzed, and the ERN effect on patients of the C group and the O group was compared. The results showed that the mean square error (MSE) of the improved Canny algorithm (233.78) was smaller than that of the traditional Canny algorithm and Sobel and Prewitt algorithm, and the peak signal-to-noise ratio (PSNR) (27.89) was greater than that of the traditional Canny algorithm and Sobel and Prewitt algorithm (P < 0.05). Compared with the control group, the sensitivity (85.00% vs. 62.12%), specificity (70.59% vs. 36.36%), and accuracy (80.70% vs. 54.39%) of the examination method of the observation group were much higher (P < 0.05). In addition, the total effective rate of patients in group O was 89.47%, which was greatly higher than that of group C (70.18%), and the scores of Meyer index and Barthel index were also higher in contrast to those of group C (P < 0.05). In conclusion, the improved Canny algorithm showed a clearer display on the edge detection of CT images and good application effect. It showed the effect of making conventional CT more accurate in the examination and diagnosis of stroke patients, and it was worthy of clinical application and promotion. The research showed that the timelier rehabilitation training, the better the treatment effect of patients. [ABSTRACT FROM AUTHOR]

Meta-lens has successfully been developed for a variety of optical functions. We demonstrate a light-field edge detection imaging system with a gallium nitride achromatic meta-lens array. It enables edge detection from one dimension to three dimensions. The designed meta-lens array consists of 60 by 60 achromatic meta-lenses, which operate in the visible range from 400 to 660 nm. All of the light field information of objects in the scene can be captured and computed. The focused edge images from one dimension to three dimensions are extracted with depth estimation by image rendering. Three dimensions edge detection is two dimensions edge imaging with depth information. The focused edge images can be obtained by the sub-image reconstruction of the light field image. Our multidimensional edge detection system by achromatic meta-lens array brings novel advantages, such as broadband detection, data volume reduction, and device miniaturization capacity. Results of our experiments show new insight into applications of biological diagnose and robotic vision. [ABSTRACT FROM AUTHOR]

In this work, we develop the Single-Input Multi-Output U-Net (SIMOU-Net), a hybrid network for foetal brain segmentation inspired by the original U-Net fused with the holistically nested edge detection (HED) network. The SIMOU-Net is similar to the original U-Net but it has a deeper architecture and takes account of the features extracted from each side output. It acts similar to an ensemble neural network, however, instead of averaging the outputs from several independently trained models, which is computationally expensive, our approach combines outputs from a single network to reduce the variance of predications and generalization errors. Experimental results using 200 normal foetal brains consisting of over 11,500 2D images produced Dice and Jaccard coefficients of 94.2 ± 5.9% and 88.7 ± 6.9%, respectively. We further tested the proposed network on 54 abnormal cases (over 3500 images) and achieved Dice and Jaccard coefficients of 91.2 ± 6.8% and 85.7 ± 6.6%, respectively. [ABSTRACT FROM AUTHOR]

In the present study, we propose an effective nonlinear anisotropic diffusion-based hyperbolic parabolic model for image denoising and edge detection. The hyperbolicparabolic model employs a second-order PDEs and has a second-time derivative to time t. This approach is very effective to preserve sharper edges and better-denoised images of noisy images. Our model is well-posed and it has a unique weak solution under certain conditions, which is obtained by using an iterative finite difference explicit scheme. The results are obtained in terms of peak signal to noise ratio (PSNR) as a metric, using an explicit scheme with forward-backward diffusivities. [ABSTRACT FROM AUTHOR]

In this article, a new wavelet-based laser peak detection algorithm is proposed having subpixel accuracy. The algorithm provides an accurate and rapid measurement platform for the rail surface corrugation with no need to any image noise elimination. The proposed rail Corrugation Measurement System (CMS) is based on the laser triangulation principle, and the accuracy of such system is mainly affected by the laser peak detection in the captured image. The intensity of each row or column of the image is taken as a 1-D discrete signal. Intensity distribution of a laser stripe in this signal follows a Gaussian pattern contaminated by the white noise. Against usual peak detection algorithms with need to prenoise-filtering process, the proposed method based on the wavelet transform is able to perform these tasks efficiently and robustly. Present wavelet-based methods for the peak detection are at pixel level, but for achieving high accuracy subpixel detection is proposed. Experiments show that the capability of the proposed method for laser peak detection is more accurate and faster than the filter-based methods, especially for low S/N ratios. Also, this technique can be utilized for any application in laser peak detection with subpixel accuracy. A prototype system based on the proposed method for the rail corrugation measurement has been designed and manufactured. Results of the rail corrugation measurement guarantee capability of the proposed methodology for accurate measurement of the rail corrugation and its potential for industrial application. [ABSTRACT FROM AUTHOR]

Fast edge detection of images can be useful for many real-world applications. Edge detection is not an end application but often the first step of a computer vision application. Therefore, fast and simple edge detection techniques are important for efficient image processing. In this work, we propose a new edge detection algorithm using a combination of the wavelet transform, Shannon entropy and thresholding. The new algorithm is based on the concept that each Wavelet decomposition level has an assumed level of structure that enables the use of Shannon entropy as a measure of global image structure. The proposed algorithm is developed mathematically and compared to five popular edge detection algorithms. The results show that our solution is low redundancy, noise resilient, and well suited to real-time image processing applications. [ABSTRACT FROM AUTHOR]

We provide a comprehensive and in-depth overview of the various approaches applicable to the recognition of Data Matrix codes in arbitrary images. All presented methods use the typical "L" shaped Finder Pattern to locate the Data Matrix code in the image. Well-known image processing techniques such as edge detection, adaptive thresholding, or connected component labeling are used to identify the Finder Pattern. The recognition rate of the compared methods was tested on a set of images with Data Matrix codes, which is published together with the article. The experimental results show that methods based on adaptive thresholding achieved a better recognition rate than methods based on edge detection. [ABSTRACT FROM AUTHOR]

In recent years, with the rapid development of image processing research, the study of nonstandard images has gradually become a research hotspot, for example, fabric images, remote sensing images, and gear images. Some of the remote sensing images have a complex background and low illumination compared with standard images and are easy to be mixed with noise during acquisition; some of the fabric images have rich texture information, which adds difficulty to the related processing, and are also easy to be mixed with noise during acquisition. In this paper, we propose a fractional-order adaptive P -Laplace equation image edge detection algorithm for the problem of image edge detection in which the edge and texture information of the image is lost. The algorithm can apply for the order adaptively to filter the noise according to the noise distribution of the image, and the adaptive diffusion factor is determined by both the fractional-order curvature and fractional-order gradient of the iso-illumination line and combined with the iterative approach to realize the fine-tuning of the noisy image. The experimental results demonstrate that the algorithm can remove the noise while preserving the texture and details of the image. A fractional-order partial differential equation image edge detection model with a fractional-order fidelity term is proposed for Gaussian noise. The model incorporates a fractional-order fidelity term because this fidelity term smoothes out the rougher parts of the image while preserving the texture in the original image in greater detail and eliminating the step effect produced by other models such as the Perona-Malik (PM) and Rudin-Osher-Fatemi (ROF) models. By comparing with other algorithms, the image edge detection effect is measured with the help of evaluation metrics such as peak signal-to-noise ratio and structural similarity, and the optimal value is selected iteratively so that the image with the best edge detection result is retained. A convolutional mask image edge detection model based on adaptive fractional-order calculus is proposed for the scattered noise in medical images. The adaption is mainly reflected in the model algorithm by constructing an exponential parameter relation that is closely related to the image, which can dynamically adjust the parameter values, thus making the model algorithm more practical. The model achieves the scattering noise removal in four steps. [ABSTRACT FROM AUTHOR]

According to the requirements of CT system parameter calibration and imaging, using OpenCV and MATLAB software, the reverse Radon transform and the Canny edge detection algorithm in the projection edge methods can determine the position and geometry of two different media in the square tray based on given data. Besides, it can apply and analyze the shape and the absorption rate of the specified point, the accuracy, and stability of the template calibration parameters by this way, which enables designing a new template and calibrating the new parameters. [ABSTRACT FROM AUTHOR]

Experimental studies of multiple shock wave interaction to study transition from regular to irregular reflection rely on the processing of a large amount of schlieren photographs. Here we present an automated algorithm to track individual shock fronts and triple points. First, correction to any optical distortions is applied to the photographs. Next, noise removal and edge detection algorithms are implemented to extract the pixel locations of the shocks. The edge detection algorithm takes advantage of the light intensity feature of the shock waves to distinguish shock fronts from background noise. This algorithm is also capable of separating entangled shock fronts through pattern recognition, which utilizes a discretization method to reduce complex shock geometries to localized linear patterns. Collectively, the algorithms can track shock wave characteristics to sub-pixel precision. This algorithm has been deployed for post processing of shock wave experiments to extract shock wave characteristics including positions and propagation velocities of shock fronts, vertical and horizontal velocities of Mach stems, and triple point trajectories during shock-shock interactions. Results show that the algorithm can process large volumes of data with minimal manual operations, making image processing more precise, efficient and productive while allowing for tracking of Mach stems and triple points. [ABSTRACT FROM AUTHOR]

Image segmentation often faces a trade-off between using higher resolution images to detect fine details, such as the edges of objects or thin structures, and lower resolution images which is more suitable for accurate segmentation of massive objects. Because low resolution images require less resources, accurate detection of small objects is often less prioritized in trying to achieve the highest accuracy. In this paper, we propose to improve the segmentation of small and thin objects by convolutional neural networks by adding a morphological element to the loss function used for training the segmentation network. The approach is tested on a traffic sign segmentation problem using the Cityscapes dataset with a training set of 2 979 images and is shown to have an advantage over the popular cross-entropy (CE) and a ground truth (GT) affinity map weighted CE as it yields higher global IoU and, more importantly, an IoU gain among the smaller traffic signs with no additional computational resources. [ABSTRACT FROM AUTHOR]

Application of Digital Image Processing on medical images could greatly contribute in the discovery of diseases and it would provide the physicians with valuable inputs in the process of diagnosing the diseases without any flaws. This is an experimental paper in which some of the filtering methods and edge detection methods have been applied and the results are being reviewed. Some of the important filtering techniques will be discussed in this paper and the results I have worked on will also be illustrated. Two types of edge detection methods have also been reviewed and their results are being illustrated. [ABSTRACT FROM AUTHOR]

The present paper introduces a Convolutional Neural Network (CNN) for the assessment of image quality without a reference image, which comes under the category of Blind Image Quality Assessment models. Edge distortions in the image are characterized as input feature vectors. This approach is in justification of the fact that subjective assessment focusses on image features that emanate from the edges and the boundaries present in the image. The earlier methods were found to use complex transformations on the image to extract the features before training or as a part of the training. The present work uses Prewitt kernel approach to extract the horizontal and vertical edge maps of the training images. These maps are then input to a simple CNN for extracting higher level features using non-linear transformations. The resultant features are mapped to image quality score by regression. The network uses Spatial Pyramid Pooling (SPP) layer to accommodate input images of varying sizes. The present proposed model was tested on popular datasets used in the domain of Image Quality Assessment (IQA). The experimental results have shown that the model competes with the earlier proposed models with simplicity of feature extraction and involvement of minimal complexity. [ABSTRACT FROM AUTHOR]

Sound transmission efficiency and beaming capability are the most important considerations in the design of single-slit lens toward high-performance acoustic imaging and detection. Here, we demonstrated numerically and experimentally enhanced sound focusing through a single subwavelength slit surrounded by grooves on both surfaces. A microscopic coupled-wave model was employed to optimize the slit-groove structure for both transmission enhancement and beam focusing. The simulated and measured results were in good agreement and readily verified the effectiveness of the proposed method in enhancing sound focusing with a single-slit lens. This work paves an alternative avenue for the design of single-slit lens, which may find potential applications in the broad field of acoustics, such as tumor boundary treatment, edge detection, and subwavelength acousto-optic modulation. [ABSTRACT FROM AUTHOR]

Micro-CT has important applications in biomedical research due to its ability to perform high-precision 3D imaging of micro-architecture in a non-invasive way. Because of the limited power of the radiation source, it is difficult to obtain a high signal-to-noise image under the requirement of temporal resolution. Therefore, low-dose CT image denoising has attracted considerable attention to improve the image quality of micro-CT while maintaining time resolution. In this paper, an end-to-end asymmetric perceptual convolutional network (APCNet) is proposed to enhance the network's ability to capture and retain image details by improving the convolutional layer and introducing an edge detection layer. Compared with the previously proposed denoising models such as DnCNN, CNN-VGG, and RED-CNN, experiments proved that our proposed method has achieved better results in both numerical indicators and visual perception. [ABSTRACT FROM AUTHOR]

The energy functional of the CV and LBF model is single, which makes the curve to get into the local minimum easily during the evolution process, and results inaccurate segmentation of the images with nonuniform grayscale and nonsmooth edges. The proposed algorithm, which is based on local entropy fitting under the constraint of nonconvex regularization term, is used to deal with such problems. In this algorithm, global information and local entropy are fitted to avoid segmentation falling into local optimum, and nonconvex regularization term is imported for constraint to protect edge smoothing. First, global information is used to evolve the approximate contour curve of the target segmentation. Then, a local energy functional with local entropy information is constructed to avoid the segmentation process from falling into a local minimum, and to precisely segment the image. Finally, nonconvex regularization terms are used in the energy functional to protect the smoothness of edge information during image segmentation process. The experimental results clearly indicate that the new algorithm can effectively resist noise, precisely segment images with nonuniform grayscale, and achieve the global optimal. [ABSTRACT FROM AUTHOR]