ISSN: 2074-9074 (Print)
ISSN: 2074-9082 (Online)
DOI: https://doi.org/10.5815/ijigsp
Website: https://www.mecs-press.org/ijigsp
Published By: MECS Press
Frequency: 6 issues per year
Number(s) Available: 139
IJIGSP is committed to bridge the theory and practice of images, graphics, and signal processing. From innovative ideas to specific algorithms and full system implementations, IJIGSP publishes original, peer-reviewed, and high quality articles in the areas of images, graphics, and signal processing. IJIGSP is a well-indexed scholarly journal and is indispensable reading and references for people working at the cutting edge of images, graphics, and signal processing applications.
IJIGSP has been abstracted or indexed by several world class databases: Scopus, Google Scholar, Microsoft Academic Search, CrossRef, Baidu Wenku, IndexCopernicus, IET Inspec, EBSCO, JournalSeek, ULRICH's Periodicals Directory, WorldCat, Scirus, Academic Journals Database, Stanford University Libraries, Cornell University Library, UniSA Library, CNKI Scholar, ProQuest, J-Gate, ZDB, BASE, OhioLINK, iThenticate, Open Access Articles, Open Science Directory, National Science Library of Chinese Academy of Sciences, The HKU Scholars Hub, etc..
IJIGSP Vol. 17, No. 5, Oct. 2025
REGULAR PAPERS
A chronic neurological disorder called epilepsy is characterized by frequent, unplanned seizures. A seizure is an unexpected and uncontrolled electrical disturbance in the brain that can cause a variety of physical and behavioral symptoms. Prognosis of epilepsy can be done based on pre-ictal (prior to seizure) signal variations in Electroencephalogram (EEG) rhythm. EEG rhythm like alpha, beta, theta and delta are substantial for epilepsy analysis. This study aimed to investigate the impact of various features from EEG rhythm and the feature reduction in classification of pre-ictal and inter-ictal (between two seizures) signal. Dataset of CHB-MIT comprises of 23 patients with 23 channels are used to extract Time, Frequency and Time-frequency features from EEG rhythms. Analysis shows that, compared to other bands, beta band features show major variation in pre-ictal and inter-ictal phases, which makes training of a Support Vector Machine (SVM) classifier easy for prediction of seizures. Further reduction in feature size using statistical analysis helped to achieve 75% reduction in computation. Results show average sensitivity of 93% and false positive rate of 0.14 per hour. The proposed method classified pre-ictal signal with maximum accuracy of 95%, sensitivity of 100%, specificity of 93% and false positive rate of 0.07per hour with reduced complexity compare to other state of art methods.
[...] Read more.Quantum computing is a rapidly developing field with faster computational capabilities than classical computing. The popularity of quantum computing has reached the field of image processing, particularly with a breakthrough method known as Quantum Hadamard Edge Detection. This approach represents a significant advancement in edge detection techniques using quantum computing. Quantum Hadamard Edge Detection is a method that can detect image edges more quickly than classical methods with exponential acceleration. This paper explains the Quantum Hadamard Edge Detection method in detail, including how it is implemented, a time complexity explanation, some experiments, and future research directions. Our experiments utilize a quantum computer simulator and employ four measurement metrics: Structural Similarity Index, Figure of Merit, Entropy, and a Proposed Metric with radius-based features, to detect simple binary images, MNIST images, and the Berkeley Segmentation datasets. We recognize the potential of quantum computing and believe that image processing with quantum representation will make processing more efficient and significantly valuable in the future.
[...] Read more.Soil image classification plays a crucial role in agricultural and environmental practices. Traditional methods of soil classification often involve manual labor, which can be time-consuming and prone to human error. Recent advances in computer vision and machine learning have opened new horizons for automating this classification process. This research paper presents a comprehensive study and evaluates the performance of four convolutional neural network (CNN) architectures a custom CNN, ResNet50, InceptionV3, and MobileNetV2 on a custom soil image dataset comprising 1800 labelled images across four soil classes such as Black, Laterite, Red and White. The dataset created using smartphone camera to captured images under varying natural conditions. The objective of this work is to explore the effectiveness and accuracy of different machine learning algorithms used in categorizing soil types based on visual data. Each model’s performance is evaluated in terms of classification accuracy, precision, recall, and F1-score. Results indicate that ResNet50 achieves the highest accuracy 97.3%, followed closely by MobileNetV2 94.7%. The custom CNN, while computationally efficient, achieved 88.2%. We conclude that transfer learning with deep CNNs is highly effective for soil classification, and MobileNetV2 is a strong recommended for mobile applications. The comparative analysis demonstrates their effectiveness in distinguishing between different soil types, textures, and compositions. It also highlights how important it is to select the appropriate CNN architectures for certain tasks related to soil classification. This work belongs to the increasing collection of information at the interface between soil science and computer vision. It offers a strategy to apply sophisticated deep learning-based algorithms to assess soil type more reliably and effectively, serving as a springboard for future research in the field of soil image analysis and classification.
[...] Read more.Infrastructure as a service is used for resource management. Resources that will be available on demand are effectively managed using the resource management module. Predicting CPU and memory usage assists with resource management when cloud resources are provided. This study uses a hybrid DS-RAE model to forecast CPU and memory utilization in the future. Predictions are made using the range of values found, which is helpful for resource management. The memory and CPU use patterns in the cloud traces are identified by the Double Channel Residual Self-Attention Temporal Convolution Network (DSTNW) model as having linear components. The Recursive Autoencoder (RAE) model for tracing and enlarging nonlinear components and power consumption was developed using the DSTNW model. Gathers the raw data taken from the system's operational state, such as bandwidth, disk I/O time, disk space, CPU, and memory utilization. Discover patterns and oscillations in the workload trace by preprocessing the data to increase the prediction efficacy of this model. During data pre-processing, missing value edge computing and z-score normalization are used to select the important properties from raw data samples, eliminate irrelevant elements, and normalize them. After that, preprocessing utilizes a dynamization of the sliding window to improve the proposed model's accuracy on non-random workloads. Next, utilize a hybrid DS-RAE to attain accurate workload forecasting. Comparing the suggested methodology with existing models, experimental results show that it offers a better trade-off between training time and accuracy. The suggested method provides higher performance, with an execution time of 32 seconds and an accuracy rate of 97%. According to the simulation results, the DS-RAE workload prediction method performs better than other algorithms.
[...] Read more.Acne is a persistent skin disorder that typically affects children in the age range of 12 to 25. Both inflammatory and non-inflammatory skin diseases can coexist with various types of acne, such as papules, pustules, nodules, cysts, blackheads, and whiteheads. In recent times, the study of acne has been carried out conventionally, with a manual approach for determining the ROI. As a result, the patient's face will be physically counted and marked with the acne that was found in the ROI. This manual method could result in incorrect identification and diagnosis of acne. Moreover, it is still difficult to determine the type of acne related to another. The necessity for patients to visit a dermatologist is growing despite the difficulties in identifying acne manually. For a patient, waiting for the dermatologist to become available is challenging. Thus, an automated application for recognizing acne types is needed, as it may help these individuals. In order to address these problems, a dataset containing images of skin diseases is created. Lanczos resampling, which is frequently used to shift or enhance a digital signal's sampling rate by a fraction of the sampling interval, is employed in the preprocessing of the skin disease data. Subsequently, the pre-processed images are segmented using the Modified Link Net-B7 in order to eliminate noise and correctly categorize images of acne with the segmented skin images. After the model has been trained and validated, the Acne type prediction is forecast using the HR-Net algorithm. The performance metrics for this developed model are FPR, FOR, NPV, kappa, error, accuracy, precision, sensitivity, specificity, f1-score, kappa, training time, testing time, and execution time. Performance metrics values of 95.17%, 94.10%, 92.33%, 96.34%, 93.15%, 85.74%, 4.83%, 4%, 6%, 95%, 7.7%, 1492, 23 and 1515 have been reached for the proposed approach. Therefore, compared to the existing models, Acne type prediction using the different types of Acne disease images based on modified Link Net-B7 and HR-Net algorithm performs better.
[...] Read more.The new form of coronavirus started in Wuhan, China, in 2019 and is known as COVID-19. It created severe health issues and also deaths in most of the countries. The test kits and certain imaging techniques, namely computed tomography and X-ray, are utilized to analyze the severity of diseases. Earlier, researchers introduced several machine-learning techniques for medical diagnosis. However, due to complexity concerns and a high error rate, such strategies cannot produce superior results. Recently, several deep learning mechanisms have been utilized in medical diagnosis. In this work, a new triple-task learning architecture is introduced for the identification and categorization of COVID-19 disease by referring to CT images. First, the input images are pre-processed utilizing Gabor filtering and image resizing. After pre-processing, the images are fed to the triple-task learning network. Here, in the proposed network, three modules are included, namely Residual Swin Transformer based U-Net, Deep convolution and Extended BiLSTM. In this, the Residual Swin Transformer-based U-Net performs the segmentation task. After that, the most significant features are extracted using Deep convolution. The extracted features are then used in the classification step when the various classes of COVID-19 are classified. Finally, the classification parameters are fine-tuned utilizing the Adaptive Fire Hawks algorithm. Then, the proposed technique is experimentally verified utilizing a Python tool, and the performance is analyzed by evaluating the performance metrics. Also, the proposed approach is compared to existing techniques, and the comparison results show that the proposed technique achieves better performance, having an accuracy of 99.46%.
[...] Read more.The challenge of graph vertex coloring is a well-established problem in combinatorial optimization, finding practical applications in scheduling, resource allocation, and compiler register allocation. It revolves around assigning colors to graph vertices while ensuring adjacent vertices have distinct colors, to minimize the total number of colors. In our research, we introduce an innovative methodology that leverages machine learning to address this problem. Our approach involves comprehensive preprocessing of a collection of graph instances, enabling our machine learning model to discern complex patterns and relationships within the data. We extract various features from the graph structures, including node degrees, neighboring node colors, and graph density. These features serve as inputs for training our machine learning model, which can encompass neural networks or decision trees. Through this training, our model becomes proficient at predicting optimal vertex colorings for previously unseen graphs. To evaluate our approach, the authors conducted extensive experiments on diverse benchmark graphs commonly used in vertex coloring research. Our results demonstrate that our machine learning-based approach achieves comparable or superior performance to state-of-the-art vertex coloring algorithms, with remarkable scalability for large-scale graphs. Further, in this research, the authors explored the use of Support Vector Machines (SVM) to predict optimal algorithmic parameters, showing potential for advancing the field. Our systematic, logical approach, combined with meticulous preprocessing and careful optimizer selection, strengthens the credibility of our method, paving the way for exciting advancements in graph vertex coloring.
[...] Read more.The study is devoted to the analysis of public sentiment towards Ukrainian political figures based on comments on social media, in particular, YouTube and Twitter. The work aims to identify differences in the perception of political leaders and to understand how the platform affects the tone of statements. The main research question is to determine how public opinion about politicians in Ukraine differs between YouTube and Twitter during the full-scale war. To do this, a corpus of comments and tweets from 2022 to 2023 was collected, which went through pre-processing stages (including cleaning up slang and spelling mistakes). The article presents the results of a comprehensive analysis of public opinion on five public figures of Ukraine (S. Prytula, P. Poroshenko, V. Zelensky, S. Sternenko, A. Yermak) based on data from the social networks YouTube and Twitter. For data collection, the YouTube Data API and the Apify platform were used, a corpus of Ukrainian-language comments and tweets was collected and processed, which went through the stages of purification, normalisation and lemmatisation, taking into account slang, surzhyk and spelling mistakes. The sentiment analysis model, built on the basis of multilingual-e5-base embeddings and the XGBClassifier algorithm, showed an accuracy of 89.4%, macro-F1 of 88.7%, and a weighted F1 of 89.1%. Sentiment distribution analysis revealed that, on average, 42% of messages were positive, 36% were negative, and 22% were neutral. Twitter had a higher share of negative statements (up to 40%), while YouTube had a predominance of positive sentiment (up to 47%). The results indicate differences in the perception of public figures on different platforms and confirm the effectiveness of the developed approach for the Ukrainian-speaking segment of social networks. The results indicate significant differences in sentiment distribution: comments on YouTube are more likely to be marked by emotional intensity and harshness. At the same time, Twitter exhibits a more concise but no less polarised discourse. One of the reasons for this difference may be the difference in the format of the platforms, their audience, and the speed of content distribution. Further research should take into account the impact of user demographic biases, as well as the activity of bots or coordinated campaigns that can change the perception of public opinion. The practical significance of the study lies in the fact that its results can be used by politicians, journalists, and public figures to better understand the mood of society, predict reactions to political events, and build more effective communication. At the same time, it is worth noting that there are limitations: automated sentiment analysis has difficulty detecting sarcasm, irony, or context-sensitive meanings, which can affect the Accuracy of the results. In addition, the study takes into account the ethical aspects of data collection and analysis: only publicly available comments were used, without interference in the private sphere of users. There are possible risks of abuse of such technologies, and the need for responsible application of the findings is emphasised.
[...] Read more.Image Processing is the art of examining, identifying and judging the significances of the Images. Image enhancement refers to attenuation, or sharpening, of image features such as edgels, boundaries, or contrast to make the processed image more useful for analysis. Image enhancement procedures utilize the computers to provide good and improved images for study by the human interpreters. In this paper we proposed a novel method that uses the Genetic Algorithm with Multi-objective criteria to find more enhance version of images. The proposed method has been verified with benchmark images in Image Enhancement. The simple Genetic Algorithm may not explore much enough to find out more enhanced image. In the proposed method three objectives are taken in to consideration. They are intensity, entropy and number of edgels. Proposed algorithm achieved automatic image enhancement criteria by incorporating the objectives (intensity, entropy, edges). We review some of the existing Image Enhancement technique. We also compared the results of our algorithms with another Genetic Algorithm based techniques. We expect that further improvements can be achieved by incorporating linear relationship between some other techniques.
[...] Read more.Mushrooms are the most familiar delicious food which is cholesterol free as well as rich in vitamins and minerals. Though nearly 45,000 species of mushrooms have been known throughout the world, most of them are poisonous and few are lethally poisonous. Identifying edible or poisonous mushroom through the naked eye is quite difficult. Even there is no easy rule for edibility identification using machine learning methods that work for all types of data. Our aim is to find a robust method for identifying mushrooms edibility with better performance than existing works. In this paper, three ensemble methods are used to detect the edibility of mushrooms: Bagging, Boosting, and random forest. By using the most significant features, five feature sets are made for making five base models of each ensemble method. The accuracy is measured for ensemble methods using five both fixed feature set-based models and randomly selected feature set based models, for two types of test sets. The result shows that better performance is obtained for methods made of fixed feature sets-based models than randomly selected feature set-based models. The highest accuracy is obtained for the proposed model-based random forest for both test sets.
[...] Read more.This paper presents a design and development of an Artificial Intelligence (AI) based mobile application to detect the type of skin disease. Skin diseases are a serious hazard to everyone throughout the world. However, it is difficult to make accurate skin diseases diagnosis. In this work, Deep learning algorithms Convolution Neural Networks (CNN) is proposed to classify skin diseases on the HAM10000 dataset. An extensive review of research articles on object identification methods and a comparison of their relative qualities were given to find a method that would work well for detecting skin diseases. The CNN-based technique was recognized as the best method for identifying skin diseases. A mobile application, on the other hand, is built for quick and accurate action. By looking at an image of the afflicted area at the beginning of a skin illness, it assists patients and dermatologists in determining the kind of disease present. Its resilience in detecting the impacted region considerably faster with nearly 2x fewer computations than the standard MobileNet model results in low computing efforts. This study revealed that MobileNet with transfer learning yielding an accuracy of about 85% is the most suitable model for automatic skin disease identification. According to these findings, the suggested approach can assist general practitioners in quickly and accurately diagnosing skin diseases using the smart phone.
[...] Read more.In the field of medical image analysis, supervised deep learning strategies have achieved significant development, while these methods rely on large labeled datasets. Self-Supervised learning (SSL) provides a new strategy to pre-train a neural network with unlabeled data. This is a new unsupervised learning paradigm that has achieved significant breakthroughs in recent years. So, more and more researchers are trying to utilize SSL methods for medical image analysis, to meet the challenge of assembling large medical datasets. To our knowledge, so far there still a shortage of reviews of self-supervised learning methods in the field of medical image analysis, our work of this article aims to fill this gap and comprehensively review the application of self-supervised learning in the medical field. This article provides the latest and most detailed overview of self-supervised learning in the medical field and promotes the development of unsupervised learning in the field of medical imaging. These methods are divided into three categories: context-based, generation-based, and contrast-based, and then show the pros and cons of each category and evaluates their performance in downstream tasks. Finally, we conclude with the limitations of the current methods and discussed the future direction.
[...] Read more.Image analysis belongs to the area of computer vision and pattern recognition. These areas are also a part of digital image processing, where researchers have a great attention in the area of content retrieval information from various types of images having complex background, low contrast background or multi-spectral background etc. These contents may be found in any form like texture data, shape, and objects. Text Region Extraction as a content from an mage is a class of problems in Digital Image Processing Applications that aims to provides necessary information which are widely used in many fields medical imaging, pattern recognition, Robotics, Artificial intelligent Transport systems etc. To extract the text data information has becomes a challenging task. Since, Text extraction are very useful for identifying and analysis the whole information about image, Therefore, In this paper, we propose a unified framework by combining morphological operations and Genetic Algorithms for extracting and analyzing the text data region which may be embedded in an image by means of variety of texts: font, size, skew angle, distortion by slant and tilt, shape of the object which texts are on, etc. We have established our proposed methods on gray level image sets and make qualitative and quantitative comparisons with other existing methods and concluded that proposed method is better than others.
[...] Read more.Denoising is a vital aspect of image preprocessing, often explored to eliminate noise in an image to restore its proper characteristic formation and clarity. Unfortunately, noise often degrades the quality of valuable images, making them meaningless for practical applications. Several methods have been deployed to address this problem, but the quality of the recovered images still requires enhancement for efficient applications in practice. In this paper, a wavelet-based universal thresholding technique that possesses the capacity to optimally denoise highly degraded noisy images with both uniform and non-uniform variations in illumination and contrast is proposed. The proposed method, herein referred to as the modified wavelet-based universal thresholding (MWUT), compared to three state-of-the-art denoising techniques, was employed to denoise five noisy images. In order to appraise the qualities of the images obtained, seven performance indicators comprising the Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Structural Content (SC), Peak Signal to Noise Ratio (PSNR), Structural Similarity Index Method (SSIM), Signal-to-Reconstruction-Error Ratio (SRER), Blind Spatial Quality Evaluator (NIQE), and Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE) were employed. The first five indicators – RMSE, MAE, SC, PSNR, SSIM, and SRER- are reference indicators, while the remaining two – NIQE and BRISQUE- are referenceless. For the superior performance of the proposed wavelet threshold algorithm, the SC, PSNR, SSIM, and SRER must be higher, while lower values of NIQE, BRISQUE, RMSE, and MAE are preferred. A higher and better value of PSNR, SSIM, and SRER in the final results shows the superior performance of our proposed MWUT denoising technique over the preliminaries. Lower NIQE, BRISQUE, RMSE, and MAE values also indicate higher and better image quality results using the proposed modified wavelet-based universal thresholding technique over the existing schemes. The modified wavelet-based universal thresholding technique would find practical applications in digital image processing and enhancement.
[...] Read more.This Image deblurring aims to eliminate or decrease the degradations that has been occurred while the image has been obtained. In this paper, we proposed a unified framework for restoration process by enhancement and more quantified deblurred images with the help of Genetic Algorithm. The developed method uses an iterative procedure using evolutionary criteria and produce better images with most restored frequency-content. We have compared the proposed methods with Lucy-Richardson Restoration method, method proposed by W. Dong [34] and Inverse Filter Restoration Method; and demonstrated that the proposed method is more accurate by achieving high quality visualized restored images in terms of various statistical quality measures.
[...] Read more.During past few years, brain tumor segmentation in magnetic resonance imaging (MRI) has become an emergent research area in the ?eld of medical imaging system. Brain tumor detection helps in finding the exact size and location of tumor. An efficient algorithm is proposed in this paper for tumor detection based on segmentation and morphological operators. Firstly quality of scanned image is enhanced and then morphological operators are applied to detect the tumor in the scanned image.
[...] Read more.This paper performs three different contrast testing methods, namely contrast stretching, histogram equalization, and CLAHE using a median filter. Poor quality images will be corrected and performed with a median filter removal filter. STARE dataset images that use images with different contrast values for each image. For this reason, evaluating the results of the three parameters tested are; MSE, PSNR, and SSIM. With the gray level scale image and contrast stretching which stretches the pixel value by stretching the stretchlim technique with the MSE result are 9.15, PSNR is 42.14 dB, and SSIM is 0.88. And the HE method and median filter with the results of the average value of MSE is 18.67, PSNR is 41.33 dB, and SSIM is 0.77. Whereas for CLAHE and median filters the average yield of MSE is 28.42, PSNR is 35.30 dB, and SSIM is 0.86. From the test results, it can be seen that the proposed method has MSE and PSNR values as well as SSIM values.
[...] Read more.This article proposes a receiving device in which arbitrary input signals are subject to pre-detector processing for the subsequent implementation of the idea of compressing broadband modulated pulses with a matched filter to increase the signal-to-noise ratio and improve resolution. For this purpose, a model of a dispersive delay line is developed based on series-connected high-frequency time delay lines with taps in the form of bandpass filters, and analysis of this model is performed as a part of the radio receiving device with chirp signal compression. The article presents the mathematical description of the processes of formation and compression of chirp signals based on their matched filtering using the developed model and proposes the block diagram of a radio receiving device using the principle of compression of received signals. The proposed model can be implemented in devices for receiving unknown signals, in particular in passive radar. It also can be used for studying signal compression processes based on linear frequency modulation in traditional radar systems.
[...] Read more.Mushrooms are the most familiar delicious food which is cholesterol free as well as rich in vitamins and minerals. Though nearly 45,000 species of mushrooms have been known throughout the world, most of them are poisonous and few are lethally poisonous. Identifying edible or poisonous mushroom through the naked eye is quite difficult. Even there is no easy rule for edibility identification using machine learning methods that work for all types of data. Our aim is to find a robust method for identifying mushrooms edibility with better performance than existing works. In this paper, three ensemble methods are used to detect the edibility of mushrooms: Bagging, Boosting, and random forest. By using the most significant features, five feature sets are made for making five base models of each ensemble method. The accuracy is measured for ensemble methods using five both fixed feature set-based models and randomly selected feature set based models, for two types of test sets. The result shows that better performance is obtained for methods made of fixed feature sets-based models than randomly selected feature set-based models. The highest accuracy is obtained for the proposed model-based random forest for both test sets.
[...] Read more.Image Processing is the art of examining, identifying and judging the significances of the Images. Image enhancement refers to attenuation, or sharpening, of image features such as edgels, boundaries, or contrast to make the processed image more useful for analysis. Image enhancement procedures utilize the computers to provide good and improved images for study by the human interpreters. In this paper we proposed a novel method that uses the Genetic Algorithm with Multi-objective criteria to find more enhance version of images. The proposed method has been verified with benchmark images in Image Enhancement. The simple Genetic Algorithm may not explore much enough to find out more enhanced image. In the proposed method three objectives are taken in to consideration. They are intensity, entropy and number of edgels. Proposed algorithm achieved automatic image enhancement criteria by incorporating the objectives (intensity, entropy, edges). We review some of the existing Image Enhancement technique. We also compared the results of our algorithms with another Genetic Algorithm based techniques. We expect that further improvements can be achieved by incorporating linear relationship between some other techniques.
[...] Read more.Denoising is a vital aspect of image preprocessing, often explored to eliminate noise in an image to restore its proper characteristic formation and clarity. Unfortunately, noise often degrades the quality of valuable images, making them meaningless for practical applications. Several methods have been deployed to address this problem, but the quality of the recovered images still requires enhancement for efficient applications in practice. In this paper, a wavelet-based universal thresholding technique that possesses the capacity to optimally denoise highly degraded noisy images with both uniform and non-uniform variations in illumination and contrast is proposed. The proposed method, herein referred to as the modified wavelet-based universal thresholding (MWUT), compared to three state-of-the-art denoising techniques, was employed to denoise five noisy images. In order to appraise the qualities of the images obtained, seven performance indicators comprising the Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Structural Content (SC), Peak Signal to Noise Ratio (PSNR), Structural Similarity Index Method (SSIM), Signal-to-Reconstruction-Error Ratio (SRER), Blind Spatial Quality Evaluator (NIQE), and Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE) were employed. The first five indicators – RMSE, MAE, SC, PSNR, SSIM, and SRER- are reference indicators, while the remaining two – NIQE and BRISQUE- are referenceless. For the superior performance of the proposed wavelet threshold algorithm, the SC, PSNR, SSIM, and SRER must be higher, while lower values of NIQE, BRISQUE, RMSE, and MAE are preferred. A higher and better value of PSNR, SSIM, and SRER in the final results shows the superior performance of our proposed MWUT denoising technique over the preliminaries. Lower NIQE, BRISQUE, RMSE, and MAE values also indicate higher and better image quality results using the proposed modified wavelet-based universal thresholding technique over the existing schemes. The modified wavelet-based universal thresholding technique would find practical applications in digital image processing and enhancement.
[...] Read more.In the field of medical image analysis, supervised deep learning strategies have achieved significant development, while these methods rely on large labeled datasets. Self-Supervised learning (SSL) provides a new strategy to pre-train a neural network with unlabeled data. This is a new unsupervised learning paradigm that has achieved significant breakthroughs in recent years. So, more and more researchers are trying to utilize SSL methods for medical image analysis, to meet the challenge of assembling large medical datasets. To our knowledge, so far there still a shortage of reviews of self-supervised learning methods in the field of medical image analysis, our work of this article aims to fill this gap and comprehensively review the application of self-supervised learning in the medical field. This article provides the latest and most detailed overview of self-supervised learning in the medical field and promotes the development of unsupervised learning in the field of medical imaging. These methods are divided into three categories: context-based, generation-based, and contrast-based, and then show the pros and cons of each category and evaluates their performance in downstream tasks. Finally, we conclude with the limitations of the current methods and discussed the future direction.
[...] Read more.Ultrasound based breast screening is gaining attention recently especially for dense breast. The technological advancement, cancer awareness, and cost-safety-availability benefits lead rapid rise of breast ultrasound market. The irregular shape, intensity variation, and additional blood vessels of malignant cancer are distinguishable in ultrasound images from the benign phase. However, classification of breast cancer using ultrasound images is a difficult process owing to speckle noise and complex textures of breast. In this paper, a breast cancer classification method is presented using VGG16 model based transfer learning approach. We have used median filter to despeckle the images. The layers for convolution process of the pretrained VGG16 model along with the maxpooling layers have been used as feature extractor and a proposed fully connected two layers deep neural network has been designed as classifier. Adam optimizer is used with learning rate of 0.001 and binary cross-entropy is chosen as the loss function for model optimization. Dropout of hidden layers is used to avoid overfitting. Breast Ultrasound images from two databases (total 897 images) have been combined to train, validate and test the performance and generalization strength of the classifier. Experimental results showed the training accuracy as 98.2% and testing accuracy as 91% for blind testing data with a reduced of computational complexity. Gradient class activation mapping (Grad-CAM) technique has been used to visualize and check the targeted regions localization effort at the final convolutional layer and found as noteworthy. The outcomes of this work might be useful for the clinical applications of breast cancer diagnosis.
[...] Read more.Image analysis belongs to the area of computer vision and pattern recognition. These areas are also a part of digital image processing, where researchers have a great attention in the area of content retrieval information from various types of images having complex background, low contrast background or multi-spectral background etc. These contents may be found in any form like texture data, shape, and objects. Text Region Extraction as a content from an mage is a class of problems in Digital Image Processing Applications that aims to provides necessary information which are widely used in many fields medical imaging, pattern recognition, Robotics, Artificial intelligent Transport systems etc. To extract the text data information has becomes a challenging task. Since, Text extraction are very useful for identifying and analysis the whole information about image, Therefore, In this paper, we propose a unified framework by combining morphological operations and Genetic Algorithms for extracting and analyzing the text data region which may be embedded in an image by means of variety of texts: font, size, skew angle, distortion by slant and tilt, shape of the object which texts are on, etc. We have established our proposed methods on gray level image sets and make qualitative and quantitative comparisons with other existing methods and concluded that proposed method is better than others.
[...] Read more.Diabetic retinopathy is one of the most serious eye diseases and can lead to permanent blindness if not diagnosed early. The main cause of this is diabetes. Not every diabetic will develop diabetic retinopathy, but the risk of developing diabetes is undeniable. This requires the early diagnosis of Diabetic retinopathy. Segmentation is one of the approaches which is useful for detecting the blood vessels in the retinal image. This paper proposed the three models based on a deep learning approach for recognizing blood vessels from retinal images using region-based segmentation techniques. The proposed model consists of four steps preprocessing, Augmentation, Model training, and Performance measure. The augmented retinal images are fed to the three models for training and finally, get the segmented image. The proposed three models are applied on publically available data set of DRIVE, STARE, and HRF. It is observed that more thin blood vessels are segmented on the retinal image in the HRF dataset using model-3. The performance of proposed three models is compare with other state-of-art-methods of blood vessels segmentation of DRIVE, STARE, and HRF datasets.
[...] Read more.This paper presents a design and development of an Artificial Intelligence (AI) based mobile application to detect the type of skin disease. Skin diseases are a serious hazard to everyone throughout the world. However, it is difficult to make accurate skin diseases diagnosis. In this work, Deep learning algorithms Convolution Neural Networks (CNN) is proposed to classify skin diseases on the HAM10000 dataset. An extensive review of research articles on object identification methods and a comparison of their relative qualities were given to find a method that would work well for detecting skin diseases. The CNN-based technique was recognized as the best method for identifying skin diseases. A mobile application, on the other hand, is built for quick and accurate action. By looking at an image of the afflicted area at the beginning of a skin illness, it assists patients and dermatologists in determining the kind of disease present. Its resilience in detecting the impacted region considerably faster with nearly 2x fewer computations than the standard MobileNet model results in low computing efforts. This study revealed that MobileNet with transfer learning yielding an accuracy of about 85% is the most suitable model for automatic skin disease identification. According to these findings, the suggested approach can assist general practitioners in quickly and accurately diagnosing skin diseases using the smart phone.
[...] Read more.Image reconstruction is the process of generating an image of an object from the signals captured by the scanning machine. Medical imaging is an interdisciplinary field combining physics, biology, mathematics and computational sciences. This paper provides a complete overview of image reconstruction process in MRI (Magnetic Resonance Imaging). It reviews the computational aspect of medical image reconstruction. MRI is one of the commonly used medical imaging techniques. The data collected by MRI scanner for image reconstruction is called the k-space data. For reconstructing an image from k-space data, there are various algorithms such as Homodyne algorithm, Zero Filling method, Dictionary Learning, and Projections onto Convex Set method. All the characteristics of k-space data and MRI data collection technique are reviewed in detail. The algorithms used for image reconstruction discussed in detail along with their pros and cons. Various modern magnetic resonance imaging techniques like functional MRI, diffusion MRI have also been introduced. The concepts of classical techniques like Expectation Maximization, Sensitive Encoding, Level Set Method, and the recent techniques such as Alternating Minimization, Signal Modeling, and Sphere Shaped Support Vector Machine are also reviewed. It is observed that most of these techniques enhance the gradient encoding and reduce the scanning time. Classical algorithms provide undesirable blurring effect when the degree of phase variation is high in partial k-space. Modern reconstructions algorithms such as Dictionary learning works well even with high phase variation as these are iterative procedures.
[...] Read more.Nowadays, the primary concern of any society is providing safety to an individual. It is very hard to recognize the human behaviour and identify whether it is suspicious or normal. Deep learning approaches paved the way for the development of various machine learning and artificial intelligence. The proposed system detects real-time human activity using a convolutional neural network. The objective of the study is to develop a real-time application for Activity recognition using with and without transfer learning methods. The proposed system considers criminal, suspicious and normal categories of activities. Differentiate suspicious behaviour videos are collected from different peoples(men/women). This proposed system is used to detect suspicious activities of a person. The novel 2D-CNN, pre-trained VGG-16 and ResNet50 is trained on video frames of human activities such as normal and suspicious behaviour. Similarly, the transfer learning in VGG16 and ResNet50 is trained using human suspicious activity datasets. The results show that the novel 2D-CNN, VGG16, and ResNet50 without transfer learning achieve accuracy of 98.96%, 97.84%, and 99.03%, respectively. In Kaggle/real-time video, the proposed system employing 2D-CNN outperforms the pre-trained model VGG16. The trained model is used to classify the activity in the real-time captured video. The performance obtained on ResNet50 with transfer learning accuracy of 99.18% is higher than VGG16 transfer learning accuracy of 98.36%.
[...] Read more.