Search

In recent years, there has been a notable increase in interest regarding intelligent classification techniques rooted in Machine Learning within the domain of medical science. Specifically, machine learning, a pivotal area of artificial intelligence, has been extensively utilized to aid medical professionals in predicting and diagnosing various diseases. This study applies two distinct machine learning algorithms to address a medical diagnosis concern related to circular masses in breast cancer. The dataset encompasses 150 cases of breast cancer patients. The primary objective is to assess and compare the effectiveness of artificial neural networks (ANNs) and linear discriminant analysis (LDA) classifiers based on key criteria: accuracy, sensitivity, specificity, and the kappa coefficient in predicting circular masses within breast cancer. Results indicate that the performance of the ANN classifier surpasses that of the LDA model, achieving an accuracy of 97.7%, sensitivity of 95%, specificity of 100%, and a kappa coefficient of 95.31%. Additionally, the final fitted models unveil the pivotal factors significantly influencing circular masses in breast cancer, highlighting Solidity and Entropy as the most critical variables.

We study the problem of underwater debris classification and removal by remotely operated vehicles. This task is particularly important for subsea oil and gas fields exploitation. The classification of underwater debris is a challenging and difficult problem because of the complexity of underwater environments. We investigate four different algorithms based on deep convolutional neural networks for detecting and classifying marine debris. The proposed techniques are built on Keras and Tensorflow using Python programming environment. To train the algorithm for detection, various dataset information containing different types of marine debris have been established. Four distinct classifier and activation function combinations have been compared experimentally. The dataset is consist of fifteen category. The suggested approach is a modified VGGNet-16 trained on the dataset. The use of a sigmoid classifier and the Relu activation function to categories marine improves classification accuracy. The overall result indicates that classification accuracy on the testing set is satisfactory.

The ability to recognize and distinguish between various textures in an image is made possible by feature extraction, which is a fundamental step in computer vision and image processing. Traditional methods of texture analysis fall short of capturing the perceptual characteristics that give texture its meaning and identity. Because Tamura texture attributes were developed through research into the spatial and frequency components of textures, they offer a more precise and discriminating representation of textures. Tamura features capture significant visual qualities that are crucial for comprehending and interpreting texture. Tamura descriptors enable to characterization and comparison of various textures, enabling tasks like texture classification, segmentation, and retrieval. SIFT processes Tamura descriptors to extract scale-invariant features, enhancing the texture representation's capacity for discrimination. The suggested method was evaluated on numerous benchmark datasets, and the findings revealed that it outperforms conventional texture analysis methods in terms of precision, recall, and other performance measures. The qualitative evaluation further verified the interpretability and perceptual significance of the retrieved texture elements, proving their appropriateness for texture analysis tasks. The evaluation's findings show how well the suggested technique extracts texture features and how it might boost the effectiveness of numerous computer vision and image processing applications.

Recent developments in remote sensing provide very high-resolution imageries that are partially in competition with aerial images. This paper presents an evaluation of using IKONOS-2 and WorldView-2 satellite imageries for monitoring the growth of the built-up areas in the southern part of Assiut City between 2006 and 2016. In addition, a comparison between aerial orthoimage and satellite imagery was carried out. Also, a set of satellite imagery was downloaded from the Google Earth Pro application, and used in this study to determine the rate of spatial growth in the southern part of Assiut City between 2011 and 2022. The results of this study show that: Most map features can be detected and manually recognized from WorldView-2 imageries at a good level, while building detection was perfect. The applied change detection technique using IKONOS-2 imagery and WorldView-2 imagery shows that the growth of the built-up area in the south part of Assiut City between 2006 and 2016 is 783499.2 m2, representing about 16.89 % of the total test area. Recent satellite imageries from open sources such as Google Earth were used successfully to determine the rate of spatial growth of the southern part of Assiut City in the period from 2011 to 2022. The spatial growth in this period was found to be increased dramatically, especially between 2014 and 2016. Remarkable negative changes were found in the agricultural lands due to the spatial growth of the built-up area in the south direction of Assiut City.

One of the most important prognostic factors for all lung cancer patients is the accurate detection of metastases. Pathologists, as we all know, examine the body and its tissues. On the existing clinical method, they have a tedious and manual task. Recent analysis has been inspired by these aspects. Deep Learning (DL) algorithms have been used to identify lung cancer. The developed cutting-edge technologies beat pathologists in terms of cancer identification and localization inside pathology images. These technologies, though, are not medically feasible because they need a massive amount of time or computing capabilities to perceive high-resolution images. Image processing techniques are primarily employed for lung cancer prediction and early identification and therapy to avoid lung cancer. This research aimed to assess lung cancer diagnosis by employing DL algorithms and low-resolution images. The goal would be to see if Machine Learning (ML) models might be created that generate higher confidence conclusions while consuming fractional resources by comparing low and high-resolution images. A DL pipeline has been built to a small enough size from compressing high-resolution images to be fed into an or before CNN (Convolutional Neural Network) for binary classification i.e. cancer or normal. Numerous enhancements have been done to increase overall performance, providing data augmentations, including augmenting training data and implementing tissue detection. Finally, the created low-resolution models are practically incapable of handling extremely low-resolution inputs i.e. 299 x 299 to 2048 x 2048 pixels. Considering the lack of classification ability, a substantial reduction in models’ predictable times is only a marginal benefit. Due to an obvious drawback with the methodology, this is disheartening but predicted finding: very low resolutions, essentially expanding out on a slide, preserve only data about macro-cellular structures, which is usually insufficient to diagnose cancer by itself.

Digital images are often obtained with contrast distortions due to different factors that cannot be avoided on many occasions. Various research works have been introduced on this topic, yet no conclusive findings have been made. Therefore, a low-intricacy multi-step algorithm is developed in this study for rapid contrast enhancement of color images. The developed algorithm consists of four steps, in that the first two steps include separate processing of the input image by the probability density function of the standard normal distribution and the softplus function. In the third step, the output of these two approaches is combined using a modified logarithmic image processing approach. In the fourth step, a gamma-controlled normalization function is applied to fully stretch the image intensities to the standard interval and correct its gamma. The results obtained by the developed algorithm have an improved contrast with preserved brightness and natural colors. The developed algorithm is evaluated with a dataset of various natural contrast degraded color images, compared against six different techniques, and assessed using three specialized image evaluation methods, in that the proposed algorithm performed the best among the comparators according to the used image evaluation methods, processing speed and perceived quality.

In this paper different fire detection systems and techniques has been reviewed, many techniques have been developed for the purpose of early fire detection in different scenarios. The most accurate technique used among all these methods is Image Processing based Techniques. Different color models like RGB, HSI, CIE L*a*b and YCbCr have been used along with different edge detection algorithms like Sobel and Novel edge detection, finally the color segmentation technique was discussed in the review paper. All the mentioned methods in these papers have significantly proved to detect fire and flame edges in digital images with a timely manner, which has a huge impact on saving life and reducing loss of life.

Copyright of Saffron Agronomy & Technology is the property of Torbat-e-Heydarie University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The necessity for the biometrical security has been increased in order to give security and safety from the theft, frauds, etc. Iris recognition acquired a considerable value amongst all the biometrics-based systems. It is utilized used for surveillance and authentication for detecting individuals and proving an individual’s identity. The present article discusses the various stages of recognizing iris images, which include acquiring, segmenting, normalizing, extracting features, and matching. The model of a typical iris recognition system of the eye is described and the results of its work are presented. The present study will investigate the comparative performances from various methods on the feature extraction for the accuracy of the iris recognition.

Biometric images are considered as one of the major coefficients in the field of personal authentication. One of the main approaches for personal identification is based on palm print. So studying the features extracted from palm print image adopted to get high efficient system for any recognition systems. In this research two major phases are hold on, in the first phase a database was built for 100 persons by acquiring four images for both hands (4 for left hand and 4 for right hand), then processed to extract ROI (region of interest) by looking for the palm centroid then a square area is fixed based on that centroid. The pre-process play an important step for stable features. Evaluation of the seven moments for each image (8 images) follow the preprocess then stored in the database file (so each person will have 56 values), this phase called personal database preparation. The second phase is the detection phase, which requires the same steps to get 56 values then go through the database looking for the closest person to the tested one. The system evaluation measured by statistical metrics which show good result goes up to 95.7% when applied on 50 persons with different conditions. Also the effect of ROI dimension with individual hands and integrated both of them studied, and the recommended dimension is 192*192.

In this research design and manufacture of home baking machine with baking process control is followed. Therefore, the machine is designed and manufactured with the ability to produce an Iranian flatbread at each baking stage. By choosing the heat flux pattern and different thicknesses of the bed and the height of the baking chamber, the temperature and mass distribution in the three areas of the baking bed, bread and baking chamber is obtained. Image processing, texture analysis and sensory tests are used for evaluating of baked bread under different conditions. Geometrical conditions, boundary conditions and patterns of heat flux are the main factors that influence the baking process and quality of bread. The results showed that bed thickness performs better than higher thicknesses. By increasing the height of the chamber at three heights of 2, 4 and 6 cm, the mean temperature of the chamber decreases. Therefore, the height of the 2 cm chamber is the best one. In the study of bread baking with simple apparatus, it was found that the cooking time of 6 minutes and the beginning baking temperature of 160 °C are the most suitable cooking conditions. The porosity of the bread baked is much lower than that of the bakery one. The texture analysis tests showed that the hardness, gumminess, and chewiness of the heat flux pattern profile 22 had the closest values to the control bread. [ABSTRACT FROM AUTHOR]

Rampant cases related to circulation of fake currency notes have been reported worldwide. With the introduction of new banknotes (announced after demonetization) having advanced and exclusive security features, it is the need of the hour, especially for a forensic Scientists, to have an idea about these new features and the various methods to examine these features. Results presented in this paper are based on examination and comparison of original and suspected fake 2000 rupee Indian currency banknote utilizing physical examination methods and techniques such as physical, microscopic, digital image processing, etc. During the examination of original 2000 rupee banknote, it was found that some security features of this banknote are unique & exclusive and could not be forged by counterfeiters. Counterfeiter could only imitate most of the visual features of banknotes but some specific security features like OVI print, UV-fluorescent print, micro letters, etc. which are placed on all over the substrate of original banknote, could not be mimicked. However, imitation of the visual features, can at times deceives the public in general. The present case study presents a methodology which will be very useful and informative in assisting the forensic community in examination of fake currency banknotes and for future studies.

The control pests and diseases is considered one of the most important operations of Citrus in the protection stage. Today, a lot of research has been done in various fields of agriculture, including the diagnosis of plant pests and diseases by using machine vision methods. One of the problems that reduce the accuracy of the machine for detecting pests in farm conditions is the presence of adverse factors such as shade and changes in light intensity at different times of the day. In this study, in order to find the appropriate light intensity at different times of the day and increase the brightness of the shady parts of the trees, lighting by a lamp at the imaging site has been used. For detect pest-infected trees (in this snail study) has been used to Deep learning method which has been studied and evaluated by various optimization algorithms such as RMSProp, Adam and SGDm. To evaluate and test the algorithm used, 8000 images were examined in 9 farm conditions and one laboratory state In farm conditions, the lowest detection accuracy of algorithms with 64.32% related to imaging in cloudy days with light intensity of 350 to 700 lux was obtained using RMSProp algorithm, which Detection accuracy was improved up to 95.25% using SGDm algorithm by creating a light intensity controlled by a lamp (approximately 9000 lux). In laboratory conditions where the images were prepared in a controlled environment with constant light intensity, the detection accuracy was Obtained 98.73% with SGDm algorithm. [ABSTRACT FROM AUTHOR]

In this study, the effects of Farsi gum (0, 1.5% and 3%) coating containing hemp seed oil (0, 0.075% and 0.15%) on mass and volume changes of grape were investigated during storage at 4°C for 28 days. Machine vision system with learning machine methods was used to detect coated grapes from an image and estimate their mass and volume based on the image features (length, width, height and area). Four machine learning models, including linear regression (LR), artificial neural networks (ANN), radial basis function support vector regression (RBF-SVR) and Linear basis function support vector regression (LBF-SVR) were developed to predict the mass and volume of the single grape. The estimated grape mass and volume by these methods was compared statistically with actual values. The mass and volume in all treatments showed a decreasing pattern during the cold storage. The results indicated that mass and volume change decrease with Farsi gum and hemp seed oil increasing. Furthermore, according to the model evaluation results, the prediction performance of RBF-SVR model had achieved better predictive accuracy compared with the results of LR, ANN and LBF-SVR models, with R2 of 0.998 and 0.989 for mass and volume estimation, respectively, which also showed a good agreement between actual and predicted values. These results revealed that SVR model was a promising tool for estimating the mass and volume of grape during storage. [ABSTRACT FROM AUTHOR]

This paper tackles with two methods to dimensionality reduction, namely principal component analysis (PCA ) in the case of linear combinations and kernel principal component analysis method in the case of nonlinear combinations to digital image processing and analysis for useful information .And then compare the two methods and know which methods are appropriate to imaging dimensionality reduction The methods were applied to a group of satellite images of an area in the province of Basra, which represents the mouth of the Tigris and Euphrates in the Shatt al-Arab, as well as the water channels permeating Basra Governorate and the water bodies scattered around these channels.In this research, it is shown that the fourth image band is best when using the PCA method the value of it is eigen value was the biggest ,while the KPCA method showed that the third image band was the best, giving the highest latent value. Comparing the two methods using the mean error error (MSE) method, the results showed that the main KPCA method was the best.

In present investigation a twin-fluid external mixing atomizer was designed and developed for fuel atomization which is used in liquid fuel burner. The droplet sizes (SMD) in the spray which was produced through the atomizer was measured experimentally. The experiments have been performed for different liquid fuel types, as well as for air to liquid mass flow rates (ALR), to study the effects of these parameters on droplet size (SMD).The liquid fuels used during the tests are biodiesel and its blends (biodiesel-diesel Bx and biodiesel-kerosene Bkx) with three values of ALR (0.6, 0.8 and 1.0).The droplets sizes were investigated for the region near-nozzle by using imaging setup and using dispersion technique. The images viewing regions 366.6 mm2, to determine the droplet size (SMD). Matlab cod software has been used for a number of image processing techniques to identify and improve the detection of small droplets.The results showed that the increasing of biodiesel ratio in blending with diesel and kerosene increases the (SMD), and the increasing of ALR reduces the (SMD) for all experiments fuels. Also the results showed that the agreement is good of this method of SMD measurement and calculations with published studies.

In this study, three levels of flour extraction rate (80, 88 and 96 %) and amylase and xylanase (50ppm) were used in barbari bread. The moisture, specific volume, porosity, firmness (2, 24 and 72 hours after baking), crust color and sensory properties of breads were evaluated. The result showed, the moisture and a* value were increased and firmness (during 72 hours) and L* value were decreased by increasing flour extraction rate. The sample containing 80% extraction rate and amylase and xylanase had the highest specific volume and porosity. Amylase and xylanase had the positive effect on texture, specific volume, porosity and sensory properties of bread. The flour extraction rate and enzymes didn’t have significant effect (P<0.05) on b* value of samples. Finally, the evaluation of sensory properties showed the samples containing 80 and 88 % extraction rate and enzymes had the highest overall acceptability. [ABSTRACT FROM AUTHOR]

The process of classification and recognition of the digits is very important and accurate issue, it should depend on a strong, adequate rule, because there are differences in the representation of the digits for various type of font, rather than to get homogeneous classification for group of digits to show the form or the constant shape for the digit from groups of font , where to be one shape represents each group of the shapes and sizes. This paper proposed a new method for recognition images of Arabic digits with various types and size of font which captured by various kind of camera and various resolution depending on the characteristics of each digit which extracted from study of ten types of font with various size for each type. The characteristic of all shapes and sizes extracted for each digit. Then made a constant model for each digit to be compare with the digit image in any size or font type to recognize the digit in the image. A database of ten templates (one for each digit) built, and these templates are basic and general to recognize the Arabic digits with various font and size. The new method applied for recognition of Arabic digits in the images of license plate of the passenger cars. the recognition percentage was 98%.

In present investigation a twin-fluid external mixing atomizer was designed and developed for fuel atomization which is used in liquid fuel burner. The droplet sizes (SMD) in the spray which was produced through the atomizer was measured experimentally. The experiments have been performed for different liquid fuel types, as well as for air to liquid mass flow rates (ALR), to study the effects of these parameters on droplet size (SMD).The liquid fuels used during the tests are biodiesel and its blends (biodiesel-diesel Bx and biodiesel-kerosene Bkx) with three values of ALR (0.6, 0.8 and 1.0).The droplets sizes were investigated for the region near-nozzle by using imaging setup and using dispersion technique. The images viewing regions 366.6 mm2, to determine the droplet size (SMD). Matlab cod software has been used for a number of image processing techniques to identify and improve the detection of small droplets.The results showed that the increasing of biodiesel ratio in blending with diesel and kerosene increases the (SMD), and the increasing of ALR reduces the (SMD) for all experiments fuels. Also the results showed that the agreement is good of this method of SMD measurement and calculations with published studies.

In this paper, a new approach is introduced to detect the edges of any kind of grayscale image by using the k-means clustering algorithm, where three novel features are proposed by taking the advantage of the similarity of the image pixel with its eight surrounding neighbors through feeding these features as attributes to the clustering system. This method of edge detection does not use either any smoothing filter or threshold values. The experimental results show that an acceptable detection of the edges is done.

The recognition of the vehicle license plate systems is considered to be one of the important computer intelligent systems. In this research, a simple algorithm is proposed to analyze and recognize the new style of Iraqi vehicle license plates. The proposed algorithm is based on some steps performed respectively, the first step is the color recognition of the right-hand rectangle bar of the license plate to decide the class of the vehicle using the properties of the HSV color model, the second step is to analyze the Arabic alphanumeric region of the license plate in order to recognize the Arabic (Hindi Numeral System) numbers by testing geometric areas, and recognizing Arabic Letter by indicating and measuring the extrema points of the letter image under process, the third step is to analyze the state name to decide which state the vehicle registered in. The proposed system is tested on samples of license plate captured images using a digital camera with a fixed distance from the vehicle (5 meters), the results of the analysis were accepted by about 75% and failed by 25%.