International Journal of Image, Graphics and Signal Processing (IJIGSP)

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: 138

(IJIGSP) in Google Scholar Citations / h5-index

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..

Latest Issue
Most Viewed
Most Downloaded

IJIGSP Vol. 17, No. 4, Aug. 2025

REGULAR PAPERS

Enhanced Fault Identification in Solar Panels through Binary Cascaded Convolutional Classifiers with Thermal-Visual Image Augmentation

By Sujata P. Pathak Sonali A. Patil

DOI: https://doi.org/10.5815/ijigsp.2025.04.01, Pub. Date: 8 Aug. 2025

Solar power stands as a pivotal renewable energy source for the twenty-first century. However, the optimal functioning of solar panels is often hindered by various faults, necessitating accurate and early defect detection to maximize energy production. Existing solar panel fault identification models encounter challenges such as low precision, difficulty in distinguishing fault types, and poor generalization due to limited and unbalanced data samples. This paper introduces a novel and effective approach, leveraging a Binary Cascaded Convolutional Classifier augmented with visual and thermal image combinations to address these limitations. The proposed model adeptly classifies five distinct types of solar panel faults, including single cell hotspots, diode hotspots, dust/ shadow hotspots, multicell hotspots, and Potential-Induced Degradation (PID) hotspots. Through image augmentation techniques like rotation, shifting, sheering, resizing, jittering, and blurring applied to visual and thermal images, inter-class feature variance is increased. Binary Cascaded Convolutional Neural Network (BCCNN) classifiers are trained using an enriched dataset, each specifically designed to differentiate between dust/ shadow hotspots and other fault categories. The adoption of a binary method significantly enhances precision, allowing for focused fault identification and classification. The proposed model surpasses existing literature in terms of precision (99.8%), accuracy (98.5%) and recall (98.4%), underscoring its effectiveness across all five fault classes. In summary, this research marks a substantial advancement in the realm of solar panel fault identification, presenting a more precise and effective fault detection methodology that has the potential to significantly enhance the maintenance and longevity of solar energy systems.

[...] Read more.
Computed Tomography Image Segmentation Technology Based on ResNet Network Integrated into the Probabilistic Model

By Zhengbing Hu Kostiantyn Zvieriev Oksana Shkurat Andrii Dychka

DOI: https://doi.org/10.5815/ijigsp.2025.04.02, Pub. Date: 8 Aug. 2025

Medical image segmentation is a significant and complex challenge in medical imaging. In recent years, deep learning models have been applied to image segmentation and have shown exceptional performance. However, medical image segmentation has a scarcity of expert-labeled data compared to other deep learning research fields. Therefore, augmenting medical expert-labeled data are primarily the easiest and fastest way to improve the deep learning model’s performance. In this paper, computed tomography image segmentation technology based on the ResNet network integrated into the probabilistic model has been proposed. The proposed segmentation technology is based on the deep learning model of the ResNet50 architecture to extract features from images and initially detect objects of interest and on the probabilistic model with weighted parameters that employs conditional random fields, the GrabCut algorithm, and the argmax function to perform the final detection of objects of interest.
To train, test, and evaluate the effectiveness of the proposed method, appropriate chest CT datasets were identified to solve the task of segmenting the lung cavity, the liver and areas affected by COVID-19. The proposed image segmentation technology demonstrates segmentation accuracy results of 73.12% by Dice Score for the COVID-19 disease dataset, 97.71% for the lung cavity dataset, and 98.36% for the liver dataset, which perform better than state-of-the-art solutions.
The proposed image segmentation technology has been compared with state-of-the-art technologies (SegNet, UNet, and FCN-ResNet50) for CT segmentation to demonstrate the effectiveness of the method. The positive outcomes strongly suggest the significant potential of the proposed image segmentation technology. According to the obtained results, the proposed image segmentation technology can be a useful auxiliary tool for doctors to segment CT images for further analysis and monitoring of statistical and dynamic indicators.

[...] Read more.
An IoMT enabled Deep Insight of MR Images for Brain Tumor Segmentation with Classification Using an Elevated UNet-RESNet Model

By Surendra Kumar Panda Ram Chandra Barik Ganapati Panda Suvamoy Changder

DOI: https://doi.org/10.5815/ijigsp.2025.04.03, Pub. Date: 8 Aug. 2025

Brain tumors are a prominent cause of mortality on a global scale. The American Brain Tumor Association reports 90,000 primary brain tumor diagnoses annually, highlighting the need for improved diagnostic methods. Delaying brain tumor identification can result in significant financial costs and considerable suffering for patients. Timely identification of brain tumors is crucial for preserving both financial resources and human lives. Physicians’s manual identification of brain tumors is quite challenging. Early and precise brain tumor detection is crucial to addressing these concerns. The incorporation of the Internet of Medical Things (IoMT) coupled with deep learning (DL) is essential for advancing contemporary healthcare solutions. The proposed work presents the IoMT-UNet-ResNet model, an advanced DL method designed specifically for accurately identifying and classifying brain tumors in MR image data. By harnessing the potential of the IoMT, the model effortlessly combines UNet for precise spatial delineation and ResNet-50 for sophisticated feature learning, resulting in outstanding accuracy. This model proves to be an invaluable asset for radiologists, as it simplifies and improves the precision of brain tumor analysis through the use of MRI data. The IoMT enables radiologists to effortlessly access and analyze diagnostic information in real-time, leading to enhanced patient care and results in the field of neuroimaging. The proposed IoMT-UNet-ResNet model outperforms by comparing and validating the existing technique.

[...] Read more.
Enhancing In-loop Filter of HEVC with Integrated Residual Encoder-Decoder Network and Convolutional Neural Network

By Vanishree Moji Bharathi Gururaj Mathivanan Murugavelu

DOI: https://doi.org/10.5815/ijigsp.2025.04.04, Pub. Date: 8 Aug. 2025

High Efficiency Video Coding (HEVC) often known as H.265 is a video compression method that outperforms its predecessor H.264. In HEVC, an in-loop filter is an additional processing step that removes compressing artifacts from decoding video frames while improving visual quality. This research article proposes an improved in-loop filter that incorporates a Residual Encoder-Decoder Network based Deblocking Filter (REDNetDF) and a Convolutional Neural Network based Sample Adaptive Offset (CNN-SAO) filter, which together eliminates the smallest range of artifacts in compression video frames. The quantization frame is subjected to REDNetDF, which removes a minute number of blocking artifacts from the compressed frame. To eliminate the ringing artifacts in the compressed frame, CNN-SAO filter is used. The proposed method is used to evaluate the publicly available UVG dataset. To demonstrate efficiency, the new model is evaluated using a variety of metrics. The outcome of this study provides better results like PSNR of 49.7 dB and the SSIM of 0.97 in comparison with other techniques. Besides, the model's outcome indicates an MSE of 1.8 and saves 24.9% more bits on average to provide the same level of quality as previous techniques. The proposed framework also suppresses time complexities regarding encoding and decoding times with the results of 90.5 and 4.5 seconds on average correspondingly.

[...] Read more.
An Effective Hybrid HBA-MAO for Task Scheduling with a Hybrid Fault-Tolerant Approach in Cloud Environment

By Manoj Kumar Malik Hitesh Joshi Abhishek Swaroop

DOI: https://doi.org/10.5815/ijigsp.2025.04.05, Pub. Date: 8 Aug. 2025

"Cloud computing" refers to internet-based computing on demand and describes an incredibly scalable technology used by working-class and non-working individuals globally. Fault-tolerant task scheduling is an essential tool used by end users and cloud suppliers. Finding the best resource for the specified input task presents a key challenge for fault-tolerant task schedulers. The studies that have already been done have attempted to address each of these complex issues independently. Still, it is tricky to optimize resources and provide fault tolerance at the same time. In this paper, an effective hybrid HBA-MAO and hybrid fault-tolerant mechanism in cloud computing are designed to appropriate task scheduling in VMs without delay and failure. Various tasks submitted by users and virtual machines are taken as input for the proposed approach. Hybrid Honey Badger Optimization Algorithm (HBA) and Mexican Axolotl Optimization (MAO) are used in this proposed for priority based optimal task scheduling. These scheduled tasks are assigned to the VM for execution. A fault-tolerant mechanism is immediately carried out if the tasks are not completed successfully. The hybrid reactive and proactive fault-tolerant mechanism is used in this proposed approach for a high level of fault tolerance. The proposed approach attains better performance, like 70 sec of response time, 13% of resource utilization and 95% success rate. This approach uses resources efficiently by reducing resource consumption, so it is the best choice for fault-tolerant aware task scheduling.

[...] Read more.
Spoof-formerNet: The Face Anti Spoofing Identifier with a Two Stage High Resolution Vision Transformer (HR-ViT) Network

By Mudunuru Suneel Tummala Ranga Babu

DOI: https://doi.org/10.5815/ijigsp.2025.04.06, Pub. Date: 8 Aug. 2025

Face anti-spoofing (FAS) detection is essential for assuring the safety and dependability of facial identification systems. This study introduces the implementation of a new approach called Spoof-formerNet, which utilizes the high-resolution vision transformer (HR-ViT) system for detecting face anti-spoofing. The Vision Transformer (ViT) architecture has revealed remarkable execution in numerous computer vision applications, and we are now applying it to the intricate field of spoof detection. In order to distinguish between real faces and spoofing attempts, the Spoof-formerNet is engineered to detect minute details and subtle elements embedded in facial photos. We have conducted experimental research wherein the model is trained independently on color (RGB) and depth data in parallel using two streams of HR-ViT networks. Before applying to a classification head, the features from the two streams were concatenated. Spoof-formerNet is trained and tested using well-known benchmark datasets such as CelebA-Spoof, CASIA-SURF, WMCA, and MSU-MFSD, which are commonly used in the field of anti-face spoofing. The suggested model excels in performance and is cutting-edge in identifying genuine faces from spoofing assaults. We assess the model's efficacy by providing comprehensive findings, such as Area Under the Curve (AUC), Attack Presentation Classification Error Rate (APCER), Bona Fide Presentation Classification Error Rate (BPCER), Equal Error Rate (EER), and Average Classification Error Rate (ACER). The results of this work show how cascaded high-resolution vision transformer networks can be used to improve the safety of facial recognition approaches in real-world applications, in addition to advancing facial anti-spoofing technology. The Spoof-formerNet method for face anti-spoofing detection shows good results, with an average AUC of 99.22 and average APCER, BPCER, and ACER of 0.95, 0.66, and 0.81 correspondingly.

[...] Read more.
Evaluation of Deep Learning Approaches to Detect Choroidal Neovascularization

By Sahil Chukka Vardhanika Jagtap Naveen Patel Sudiksha Jadhav Mimi Cherian Jinesh Melvin Y. I.

DOI: https://doi.org/10.5815/ijigsp.2025.04.07, Pub. Date: 8 Aug. 2025

In ophthalmology, Choroidal Neovascularization (CNV) is a serious medical disease that, if left untreated, frequently results in significant vision loss. In this investigation, we investigate the evaluation and working of deep learning models, notably basic Convolutional Neural Networks (CNN), ResNet18, ResNet50, VGG16, VGG19, Vision Transformers, EfficientNetV2L, MobileNetV2 and InceptionV3 for identification and classification of CNV in Optical Coherence Tomography (OCT) images. The Kermany dataset, which includes OCT images of both CNV-patients and non-CNV patients (Normal OCT images) are utilized for this paper. The dataset was further used in three different versions based on validation and training split. The images from the dataset are already pre-processed and labelled so no pre-processing operations were performed, how- ever resizing of images have been performed according to the models. The deep learning models are trained and evaluated on standard performance metrics such as precision, recall, accuracy, F1-score, etc. All things considered, our work shows the evaluation of deep learning models to classify OCT images that show the presence of CNV. Based on all three dataset versions, the findings of our study confirm that ResNet18, VGGNet19, and MobileNetV2 beat all other approaches and achieved an average accuracy of 1. Additionally, Vision Transformer and Effi- cientNetV2L demonstrated strong performance, averaging 0.99 and 0.96 accuracy on each of the three dataset versions, respectively. These models have the potential to help ophthalmologists detect CNV early and monitor it, which may lead to prompt treatment and better vision preservation for patients.

[...] Read more.
Application of Tensor Networks Analysis to Optimize Traffic Management in a Critical Information and Telecommunications Network

By Oleksandr Lavrut Tetiana Lavrut Victoria Vysotska Zhengbing Hu Yuriy Ushenko Dmytro Uhryn

DOI: https://doi.org/10.5815/ijigsp.2025.04.08, Pub. Date: 8 Aug. 2025

The article investigates the task of optimising traffic management in critical information and telecommunication networks in order to ensure a guaranteed quality of user service, particularly in emergencies. A method of tensor analysis of networks is proposed, using a formalised description of the system in the form of tensors of message lengths, delays and bandwidth of channels. The network is modelled as a simplified complex, and routing is implemented through a tensor equation of connection between network parameters in different coordinate systems. Experimental calculations using examples with dynamically variable topology have shown:

•Reduction of average multipath message delivery latency by 9–40% depending on traffic intensity,
•Probability of packet delivery at or above 0.999 under high loads (200-300 messages/s),
•Zero jitter due to the even distribution of delays between paths,
•The ability to adaptively fragment messages in nodes to reduce latency,
•Increasing the efficiency of resource use compared to single-track models.
 
The use of a tensor apparatus provides stable and scalable routing in an unstable network topology. The method allows you to take into account the heterogeneity of traffic, adapt to the loss of nodes or channels, and maintain guarantees of quality of service in real time. The proposed approach is of practical importance for information and telecommunication systems used in emergencies, in particular for coordinating the actions of emergency rescue services, emergency medicine, civil protection, military units, control of drones and robotic means in the face of infrastructure loss. Potential stakeholders include state and municipal security services, operators of critical networks (energy, transport, healthcare), developers of automated control systems, and manufacturers of secure communication equipment. The proposed method can be integrated into decentralised networks with limited resources and variable topology, where traditional routing approaches do not guarantee sufficient quality of service.

[...] Read more.
Edibility Detection of Mushroom Using Ensemble Methods

By Nusrat Jahan Pinky S.M. Mohidul Islam Rafia Sharmin Alice

DOI: https://doi.org/10.5815/ijigsp.2019.04.05, Pub. Date: 8 Apr. 2019

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.
A Review of Self-supervised Learning Methods in the Field of Medical Image Analysis

By Jiashu Xu

DOI: https://doi.org/10.5815/ijigsp.2021.04.03, Pub. Date: 8 Aug. 2021

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.
Mobile-Based Skin Disease Diagnosis System Using Convolutional Neural Networks (CNN)

By M.W.P Maduranga Dilshan Nandasena

DOI: https://doi.org/10.5815/ijigsp.2022.03.05, Pub. Date: 8 Jun. 2022

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.
Evolutionary Image Enhancement Using Multi-Objective Genetic Algorithm

By Dhirendra Pal Singh Ashish Khare

DOI: https://doi.org/10.5815/ijigsp.2014.01.09, Pub. Date: 8 Nov. 2013

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.
Image Denoising based on Enhanced Wavelet Global Thresholding Using Intelligent Signal Processing Algorithm

By Joseph Isabona Agbotiname Lucky Imoize Stephen Ojo

DOI: https://doi.org/10.5815/ijigsp.2023.05.01, Pub. Date: 8 Oct. 2023

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.
Text Region Extraction: A Morphological Based Image Analysis Using Genetic Algorithm

By Dhirendra Pal Singh Ashish Khare

DOI: https://doi.org/10.5815/ijigsp.2015.02.06, Pub. Date: 8 Jan. 2015

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.
An Efficient Brain Tumor Detection Algorithm Using Watershed & Thresholding Based Segmentation

By Anam Mustaqeem Engr Ali Javed Tehseen Fatima

DOI: https://doi.org/10.5815/ijigsp.2012.10.05, Pub. Date: 28 Sep. 2012

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.
Radio Receiver with Internal Compression of Input Signals Using a Dispersive Delay Line with Bandpass Filters

By Roman Pantyeyev Felix Yanovsky Andriy Mykolushko Volodymyr Shutko

DOI: https://doi.org/10.5815/ijigsp.2023.06.01, Pub. Date: 8 Dec. 2023

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.
Breast Cancer Classification from Ultrasound Images using VGG16 Model based Transfer Learning

By A. B. M. Aowlad Hossain Jannatul Kamrun Nisha Fatematuj Johora

DOI: https://doi.org/10.5815/ijigsp.2023.01.02, Pub. Date: 8 Feb. 2023

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.
Improving Retinal Image Quality Using the Contrast Stretching, Histogram Equalization, and CLAHE Methods with Median Filters

By Erwin Dwi Ratna Ningsih

DOI: https://doi.org/10.5815/ijigsp.2020.02.04, Pub. Date: 8 Apr. 2020

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.
Edibility Detection of Mushroom Using Ensemble Methods

By Nusrat Jahan Pinky S.M. Mohidul Islam Rafia Sharmin Alice

DOI: https://doi.org/10.5815/ijigsp.2019.04.05, Pub. Date: 8 Apr. 2019

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.
Evolutionary Image Enhancement Using Multi-Objective Genetic Algorithm

By Dhirendra Pal Singh Ashish Khare

DOI: https://doi.org/10.5815/ijigsp.2014.01.09, Pub. Date: 8 Nov. 2013

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.
Image Denoising based on Enhanced Wavelet Global Thresholding Using Intelligent Signal Processing Algorithm

By Joseph Isabona Agbotiname Lucky Imoize Stephen Ojo

DOI: https://doi.org/10.5815/ijigsp.2023.05.01, Pub. Date: 8 Oct. 2023

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.
A Review of Self-supervised Learning Methods in the Field of Medical Image Analysis

By Jiashu Xu

DOI: https://doi.org/10.5815/ijigsp.2021.04.03, Pub. Date: 8 Aug. 2021

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.
Breast Cancer Classification from Ultrasound Images using VGG16 Model based Transfer Learning

By A. B. M. Aowlad Hossain Jannatul Kamrun Nisha Fatematuj Johora

DOI: https://doi.org/10.5815/ijigsp.2023.01.02, Pub. Date: 8 Feb. 2023

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.
Retinal Image Segmentation for Diabetic Retinopathy Detection using U-Net Architecture

By Swapnil V. Deshmukh Apash Roy Pratik Agrawal

DOI: https://doi.org/10.5815/ijigsp.2023.01.07, Pub. Date: 8 Feb. 2023

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.
Text Region Extraction: A Morphological Based Image Analysis Using Genetic Algorithm

By Dhirendra Pal Singh Ashish Khare

DOI: https://doi.org/10.5815/ijigsp.2015.02.06, Pub. Date: 8 Jan. 2015

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.
Mobile-Based Skin Disease Diagnosis System Using Convolutional Neural Networks (CNN)

By M.W.P Maduranga Dilshan Nandasena

DOI: https://doi.org/10.5815/ijigsp.2022.03.05, Pub. Date: 8 Jun. 2022

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.
A Review on Image Reconstruction through MRI k-Space Data

By Tanuj Kumar Jhamb Vinith Rejathalal V.K. Govindan

DOI: https://doi.org/10.5815/ijigsp.2015.07.06, Pub. Date: 8 Jun. 2015

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.
Deep Learning Based Autonomous Real-Time Traffic Sign Recognition System for Advanced Driver Assistance

By Sithmini Gunasekara Dilshan Gunarathna Maheshi B. Dissanayake Supavadee Aramith Wazir Muhammad

DOI: https://doi.org/10.5815/ijigsp.2022.06.06, Pub. Date: 8 Dec. 2022

Deep learning (DL) architectures are becoming increasingly popular in modern traffic systems and self-driven vehicles owing to their high efficiency and accuracy. Emerging technological advancements and the availability of large databases have made a favorable impact on such improvements. In this study, we present a traffic sign recognition system based on novel DL architectures, trained and tested on a locally collected traffic sign database. Our approach includes two stages; traffic sign identification from live video feed, and classification of each sign. The sign identification model was implemented with YOLO architecture and the classification model was implemented with Xception architecture. The input video feed for these models were collected using dashboard camera recordings. The classification model has been trained with the German Traffic Sign Recognition Benchmark dataset as well for comparison. Final accuracy of classification for the local dataset was 96.05% while the standard dataset has given an accuracy of 92.11%. The final model is a combination of the detection and classification algorithms and it is able to successfully detect and classify traffic signs from an input video feed within an average detection time of 4.5fps

[...] Read more.