ABSTRACTBreast cancer is one of the most common types of cancer among women worldwide and mammography is the primary method which plays a major role in early diagnosis of breast cancer. Mammograms can be obtained in two-dimensional (2D) or three-dimensional (3D) forms. 3D images contain more information than their 2D forms, however, they involve more computational and time complexities and are more challenging to produce. This study proposes a simple method to convert mammograms into artificial 3D forms. In this method, first, the gray level values of a 2D image are defined as an artificial third dimension for the same image and then the obtained image is saved in a different viewpoint again in the 2D form to make it include more information than its original form. Both, the original mammograms and their converted forms are classified as mass or normal mammograms using the ResNet. The method is tested on masses and normal mammograms taken from MIAS, INBreast and CBIS-DDSM databases, which are frequently used in the literature. The results show that the classification performed on the images obtained with the original 2D forms provided 82.4% accuracy for MIAS, 86.7% for INbreast and 96.7% for CBIS-DDSM databases. Whereas the transformed forms provided 97.8% accuracy for MIAS, 100% for INbreast and 100% for CBIS-DDSM databases, in terms of mass and normal classification. According to these results, it is seen that the transformed forms of the images provided an average of 10.67% higher accuracy for all three databases compared to their original forms.

ABSTRACTMultiple view object recognition is challenged by the impact of various view-angles on intra-class relationships. Visually impaired individuals can benefit from accurate navigation services with a navigation system that enables them to avoid obstacles to their destination. An indoor object detection framework called RSIGConv, based on an integrated Region proposal and Spatial Information Guided Convolution network, is proposed in this paper for visually impaired people. To obtain mutual complementarity (MC) features, the RGB and HHA feature maps are fused using the Information Translation Module (ITM). The hyper-parameters are optimized using the Bayesian optimization Algorithm (BOA) to reduce train error and the gap between train error and validation error. The proposed object detection framework is evaluated using the publicly available SUN RGB-D dataset and compared with previous prediction models. The simulation outputs demonstrate that the model overtakes existing approaches, achieving an accuracy of 97.77%.

ABSTRACTAutomatic detection and classification of mango leaf diseases is a complex task and manual detection system has issues like absence of experts, high cost, and lot of variations in the symptoms of the leaf disease. Hence we propose an automated solution in which the input images are gathered from standard resources and feature enhanced using contrast enhancement followed by segmentation using optimized Fuzzy C Means (FCM). Parameter optimization is done by Deviation-based Updated Dingo Optimizer (D-UDOX). The weighted feature selection is done by D-UDOX. The weighted features are provided to the classifier of Optimized Recurrent Neural Network (WO-RNN). Also, deep features are collected from a segmented image using ResNet-150. The classification with the extracted deep features is performed by WO-RNN. The parameter modification is done using D-UDOX for RNN and ResNet-150. The result of the recommended model achieves 96% accuracy and 93% F1-score which is relatively better than contemporary works.

ABSTRACTArtificial Intelligence (AI), is a field of science and engineering that deals with intelligent behaviour which has the potential of improved access and the cost of healthcare applications.Polycystic Ovarian Syndrome (PCOS) is characterised by a protracted menstrual cycle and frequent excess androgen levels, which often affect many women of reproductive age. There are now no trustworthy objective tests that might fully confirm the diagnosis and comprehension of PCOS. Effective image processing steps have been utilized in this work for the automation of PCOS diagnosis and the classification algorithms used are DarkNet-19, AlexNet, SqueezeNet, and SVM. As a result of the classifier's accelerated PCOS diagnosis and improved performance analysis, there will be fewer instances of potentially deadly consequences that can arise from a delayed diagnosis. The system produced metrics demonstrating improved performance, such as accuracy to provide a comprehensive ultrasound picture diagnosis using the classifier DarkNet-19 with 99%.

ABSTRACTThe aim of image inpainting is to fill in damaged areas according to certain rules based on information about the adjacent positions of missing areas and the overall structure of the image, a technique that plays a key role in various tasks in computer vision. With the rapid development of deep learning, researchers have combined it with image inpainting and achieved excellent performance. To gain insight into the techniques involved, this paper summarizes the latest research advances in the field of image inpainting. Firstly, existing classical image inpainting methods are reviewed, and traditional image inpainting methods and their advantages and disadvantages are introduced. Secondly, three classical network models are outlined, and the image inpainting methods are classified into single-stage, multi-stage and a priori condition-guided approaches according to different network types and model structures. Representative algorithms among them are selected and their important technical improvement ideas are analyzed and summarized. Then, the common datasets commonly used in image inpainting tasks and the evaluation metrics used to evaluate inpainting results are introduced. The paper presents a comprehensive summary of the various algorithms in terms of network models and inpainting methods, and selects representative algorithms for quantitative and qualitative comparative analysis. Finally, the future development trends and research directions have prospected, and the current problems of image inpainting are summarized.

ABSTRACTDynamic Magnetic Resonance Imaging (dMRI) is a valuable tool for understanding changes in human physiology, but its temporal and spatial resolution can be limited. Compressed sensing (CS) has been used to enhance temporal resolution by acquiring partial k-spaces of each time frame and exploiting sparsity to retain spatial resolution. Invoking CS in dMRI necessitates algorithms that can leverage both spatial sparsity within each time frame and temporal sparsity across time frames. A tensor decomposition-based multi-mode dictionary learning algorithm has been proposed to learn the spatial and temporal features of dMRI data and reconstruct it more efficiently. The extensive quantitative simulations reveal the improvement induced by the proposed method in various settings compared to state-of-the-art methods in dMRI. Further, it considerably advances reconstruction speed from trained dictionaries over the state-of-the-art, permitting faster scans catering to a larger patient group.

ABSTRACTLung cancer starts in the lungs and spreads to other organs in the body. Premature identification can only help the doctor to make an exact diagnosis and it may save the life of patients. Numerous studies have been conducted in this area, but none of them attains the accuracy outcomes. To overcome this drawback, a deep multi-scale three dimensional convolutional neural network optimized with the manta ray foraging optimization algorithm is proposed in this article for lung cancer classification on CT images (LCCT-DMS3DCNN-MRFOA) which effectively classifies the lung cancer as benign or malignant. The simulation is executed in MATLAB. The ELCAP dataset is utilized to confirm the performance of the proposed LCCT-DMS3DCNN-MRFOA approach. The efficiency of the LCCT-DMS3DCNN-MRFOA approach attains 14.21%, 22.96% and 24.94% higher accuracy; 12.59%, 11.71% and 11.55% higher AUC and 59.83%, 53.05% and 61.41% lower computational time compared with existing methods.

ABSTRACTCommunity mask use is an efficacious non-pharmacologic way to minimize viral infection spread. It is a recommendation that individuals wear face masks as protective gear. Under ideal weather conditions, machine and artificial intelligence techniques can typically determine if a person is wearing a mask properly. Identification becomes more difficult under inclement weather such as fog, clouds, haze or rain. In this work, we propose a technique that can detect a human face wearing a mask even in adverse weather. For this, homogeneous foggy images have been considered. The main challenge with this problem is that video quality degrades because of fog. Here, diverse Deep learning models train regular datasets containing digital pictures of persons with facial and non-facial masks. The training and validation parameters ensure 97% accuracy in classifying faces wearing a mask.

ABSTRACTA brain tumour is a deadly syndrome caused due to abnormal and uncontrolled expansion of extra cells that creates several tissues in the brain to affect the nervous system. It rapidly increases the growth of tumour cells and affects the brain by damaging or squeezing healthy tissues. Automatic brain tumour classification was done by conditional aquila horse herd optimization driven deep neuro fuzzy network (CAHO-based DNFN) based on MR image. First, image segmentation is done with a multi-encoder net framework (ME-Net), and features that involve statistical and convolutional neural network (CNN) features are extracted. Then, the ME-Net training is performed using AHO. Utilizing deep neuro fuzzy network (DNFN), which is trained by fusing CAViaR with AO and HOA, tumour classification is carried out utilizing augmented data after the process. The proposed scheme showed outstanding results with the measures, namely testing accuracy, specificity, and sensitivity that acquired the values of 0.915, 0.9 and 0.926, respectively.

ABSTRACTSegmentation of brain Magnetic Resonance Images (MRIs) into various brain tissues such as white matter (WM), grey matter (GM), and cerebrospinal fluid (CSF) is very important to detect and diagnose different brain-related disorders at the primitive level. Accurate segmentation of brain MRIs is very difficult because of the intricate anatomical structure of the tissues, the existence of Intensity Inhomogeneity (IIH), noise, and Partial Volume Effects (PVE). Clustering-based methods are generally used to segment brain images. This work proposes a Chaotic based Enhanced Firefly Algorithm Integrated with Fuzzy C-Means (CEFAFCM) for the segmentation of brain tissues WM, GM, and CSF from brain MRIs. The proposed method can handle IIH, PVE, and noise. CEFAFCM is a spatially modified FCM algorithm combined with the Firefly Algorithm (FA) along with a chaotic map for the initialization of the population of fireflies. The algorithm is tested with brain MRIs acquired from the BrainWeb database. The experimental results demonstrate that the proposed technique is producing better results in comparison with some existing brain MRI segmentation methods such as FCM, BCFCM, FAFCM, and En-FAFCM.

ABSTRACTReal-time video surveillance is one of the most effective ways to observe crime, mischief, and violence. But, most of the recent surveillance system consumes huge memory space to store the video. This article proposed an advanced dynamic video surveillance strategy to utilize minimum memory space with the finest detection of suspicious moving objects. In the proposed system, a convolution neural network (CNN) classifier and frame resolution switching is used to detect the movement of objects with appropriate frame resolution. A high-definition (HD) frame can be recorded dynamically when any movement of a suspicious object is detected. The system records low-quality frames, which are less important. Finally, the improved gradient-based histogram equalization technique is applied to all frames to obtain enhanced suspicious frames. Several real-time imperial tests are conducted and it is observed that the proposed system detects suspicious objects with 98.25% accuracy. Besides, the system consumes 80% less memory storage.

ABSTRACTThe global pandemic of coronavirus disease 2019 (COVID-19) causes severe respiratory problems in humans. The Chest X-ray (CXR) imaging technique majorly assists in detecting abnormalities in the chest and lung areas caused by COVID-19. Hence, developing an automatic system for CXR-based COVID-19 detection is vital for disease diagnosis. To accomplish this requirement, an enhanced Residual Network (ResNet) model is proposed in this paper for accurate COVID-19 detection. The proposed model combines the Depthwise Separable Convolutional ResNet and Pyramid dilated module(DSC-ResNet-PDM) for deep feature extraction. Employing the DSC layer minimizes the number of parameters to mitigate the overfitting issue. Further, the pyramid dilated module is used for extracting multi-scale features. The extracted features are finally fed into the optimized Medium Gaussian kernel Support Vector Machine classifier (MGKSVM) for COVID-19 detection. The proposed model attained an accuracy of 99.5%, which is comparatively higher than the standard ResNet50 and ResNet101 models.

ABSTRACTHyper spectral imaging (HSI) is an advanced and fascinating remote sensing method in various domains. Every sample in HS remote sensing images possesses high-size features and has a massive amount of spatial and spectral data that enhances the complexity of feature selection and mining. Also, it improves the interpretational complications and thus surpasses the prediction accuracy of the system. To counterpart such issues, this article introduces an innovative system for HSI categorization wielding introduced Fractional Snake Honey Badger Optimization (FSHBO). Here, image segmentation is done through U-Net, which is trained by Snake Honey Badger Optimization (SHBO). The Deep Belief Network (DBN) is employed for HSI classification that outputs the pixel-wise classified result and this DBN is efficiently tuned using the proposed FSHBO. It is recorded that the proposed FSHBO-DBN has outperformed diverse classical models in terms of accuracy of 0.907, sensitivity of 0.914, and specificity of 0.904.

ABSTRACTIn this paper, a clear underwater image is attained by a fusion process using Transfer Learning (TL). Two images are selected from the underwater colour image dataset and those images are allowed to Discrete Wavelet Transform (DWT), Tetrolet transform and Saliency maps. Here, the outputs gained from images by the Tetrolet transform are fused and allowed for inverse Tetrolet transform. Moreover, the DWT process done with two images is fused and the output gained is allowed for inverse DWT. Similarly, the same fusion process is carried out with image outputs from Saliency maps. Finally, three image outputs that are considered as input to TL with newly devised optimization. Here, Convolutional Neural Network (CNN) is used with hyperparameters from trained models, such as SqueezeNet and AlexNet, where weights are updated using Adam Based Bald Eagle Algorithm (ABBEA). This ABBEA is obtained by combining the Bald Eagle Search (BES) algorithm and Adam Algorithm. Further, the ABBEA has Peak Signal-to-Noise Ratio (PSNR) with maximal of 38.95, Mean Squared Error (MSE) with lesser value of 20.14, Structural Similarity Index Measure (SSIM) with maximal value of 0.92, Mutual Information (MI) with maximal value of 0.86, Signal-to-Noise Ratio (SNR) with lesser value of 0.38.

ABSTRACTVideo compression is necessary to recreate a video without sacrificing quality. Nowadays, researchers are focusing on global optimization approaches to determine the optical flow of the neighboring pixels in video processing. In this work, a novel improved diamond search-hybrid teaching-learning based optimization (IDS-HTLBO) methodology has been proposed to compress the videos and increase the video quality. This method uses a diamond search pattern with a secure number of search points for per frame of the video. The hybridization of DS algorithm and TLBO algorithm are applied in this methodology to reduce computational complexity. Moreover, this method reduces the computational unpredictability of block matching. The quality of the image was validated with 3D reconstruction by the structured light approaches. The experimental result shows that the proposed IDS-HTLBO algorithm achieves a maximum average value of 53.17 dB, 0.44 and 11.57 in terms of peak-to-signal-noise ratio, mean squared error, and compression ratio respectively.

ABSTRACTIncreasingly, analytics such as classification and detection suffer from a significant amount of generated visual data. Nonetheless, recent approaches have not given substantial thought to CAD systems within limited capacities at the expense of performance. For that purpose, we proposed an autoencoder-based classification approach for pneumonia recognition, extending the use of the features extracted by autoencoders for compression to enhance efficiency. Thus, we substitute the classification of images with compressed sequences and encoded tensors, representing a more convenient format for managing and storing data. Which significantly minimizes computing costs and enhances transmission bandwidth. We designed CNN model introducing the attention mechanism to the latent space with minimum parameters optimizing the classification complexity. We assess our method's effectiveness on two medical imaging datasets. In addition, we compared latent space classification to multi-resolution image classification performance. Our approach improves state-of-art performance, boosting efficiency; the number of parameters is negligible, reduced by 69%.

ABSTRACTAutomatic pancreas detection and cropping with high precision from medical images is an important yet challenging problem for medical image analysis and Computer-Aided Diagnosis (CAD). Factors relating to the limited availability of image data and segmentation methodology hinder this task. High variability in the location of the pancreas,which occupies a very small area of the pancreatic Computed Tomography (CT) scans,and the anatomy of organs also add to the list of issues. These challenges necessitate an urgent need for the development of localization and auto-cropping methods of the region of interest (ROI). This paper presents the results obtained by the implementation of Region-based Convolutional Neural Network (RCNN)-Crop inspired by the Region Proposal Network (RPN) and Feature Pyramid Network (FPN) to localize the pancreas by building bounding boxes and auto-crop the ROI obtained from various other organs in the pancreatic CT scans and has a Mean Average Precision (mAP) of 28.10% for the dataset provided.

ABSTRACTIn today’s time, the research mainly focuses on designing a Chat-bot which responds to a user’s query in the most efficient manner. However, state-of-the-art works on chat-bot design are unable to emotionally connect with the user and follow-up to a conversation. In this paper, a socially and emotionally active intelligent assistant, AMIBO is proposed. It detects and recognizes the face, perceives emotion via speech and vision capabilities, provides empathetic and intelligent responses. In order to enhance the experience of AMIBO, navigation and information delivery system have been integrated in the bot. The analysis of the feature vector (on 450 subjects) is done for all the initially taken 75 distances and 15 angles reduced to 26 distances and 11 angles feature vector. An encouraging accuracy of 99% was achieved on CK+ dataset and 97% on KDEF dataset.

ABSTRACTThis paper presents a cooperative game theory approach to improve the video steganography framework. Wherein, the video steganography framework comprises the following steps: (1) Cover video devising, (2) Secret image pre-processing, and (3) Embedding process. In the first step, the cover video is segmented using scene change detection method. Once the scenes are segmented the motion vectors are identified by Block Matching Motion Estimation Algorithm (BMMEA). Based on these motion vectors, the Region of Interest (ROI) is selected. The selected ROI is grouped using their momentum. In order to add an additional layer of security, the secret image is scrambled using pixel-wise Arnold Transform in the next step. Finally, based on the ROI groups, the scrambled secret data is embedded into the ROI's locations. An ideal and perfect video steganography system should be able to maintain the quality of the video after embedding the secret data. The quality factors of the video steganography approach include perceptible invisibility, payload capacity, and robustness. However, these quality factors are conflicted with each other. In order to address this issue, having these three quality factors as players a cooperative 3-players game theory approach is proposed. This technique provides an optimal solution for the video steganography framework using strategy adaption. The optimal solution is acquired by applying the Iterative Elimination of Strictly Dominant Strategies (IESDS) method. The achieved optimal solution comes up with the best trade-off between the quality factors. Experimental results have deduced the best optimal solution from the proposed three-player game theoretic approach that helps the video steganography approach to resolve the quality and security issues. It is also observed that the optimized proposed method outperforms the contemporary methods by attaining significant outcomes.

ABSTRACTThe analysis of Parkinson's disease (PD) is an inspiring task that necessitates the analysis of numerous motor and non-motor indications. During analysis, some abnormalities are considered as important symptoms to analyze the disease. Hence, this research introduced the proposed chronological smart sunflower optimization Algorithm (CSSFOA) for classifying the PD from voice data and voice signal samples. For voice signal, the input signals are pre-processed by the Gaussian filter, and then the significant features are extracted from it. The selection of optimal features is done by the chronological smart flower optimization Algorithm (CSFOA). The proposed CSFOA-based feature selection method considered the features by the Bray–Curtis distance. The PD classification is done by the ZF-Net which is trained by proposed CSSFOA to increase the performance of classification. The experimental result reveals that the proposed CSSFOA_ZF-Net algorithm got a better testing accuracy of 0.945, a sensitivity of 0.919, and a specificity of 0.957.