Image Feature Extraction Techniques Research Articles

Detection and isolation of brain tumors in cancer patients using neural network techniques in MRI images

MRI imaging primarily focuses on the soft tissues of the human body, typically performed prior to a patient's transfer to the surgical suite for a medical procedure. However, utilizing MRI images for tumor diagnosis is a time-consuming process. To address these challenges, a new method for automatic brain tumor diagnosis was developed, employing a combination of image segmentation, feature extraction, and classification techniques to isolate the specific region of interest in an MRI image corresponding to a brain tumor. The proposed method in this study comprises five distinct steps. Firstly, image pre-processing is conducted, utilizing various filters to enhance image quality. Subsequently, image thresholding is applied to facilitate segmentation. Following segmentation, feature extraction is performed, analyzing morphological and structural properties of the images. Then, feature selection is carried out using principal component analysis (PCA). Finally, classification is performed using an artificial neural network (ANN). In total, 74 unique features were extracted from each image, resulting in a dataset of 144 observations. Principal component analysis was employed to select the top 8 most effective features. Artificial Neural Networks (ANNs) leverage comprehensive data and selective knowledge. Consequently, the proposed approach was evaluated and compared with alternative methods, resulting in significant improvements in precision, accuracy, and F1 score. The proposed method demonstrated notable increases in accuracy, with improvements of 99.3%, 97.3%, and 98.5% in accuracy, Sensitivity and F1 score. These findings highlight the efficiency of this approach in accurately segmenting and classifying MRI images.

Analysis of thyroid nodule ultrasound images by image feature extraction technique

Analysis of thyroid nodule ultrasound images by image feature extraction technique

GastroVRG: Enhancing early screening in gastrointestinal health via advanced transfer features

The accurate classification of endoscopic images is a challenging yet critical task in medical diagnostics, which directly affects the treatment and management of Gastrointestinal diseases. Misclassification can lead to incorrect treatment plans, adversely affecting patient outcomes. To address this challenge, our research aimed to develop a reliable computational model to improve the accuracy of classifying conditions of esophagitis and polyps. We focused on a subset of the Kvasir v1 secondary dataset, comprising 2000 endoscopic images evenly distributed across two classes: esophagitis and polyp. The goal was to leverage the strengths of both Machine Learning(ML) and Deep Learning(DL) to create a model that not only predicts with high accuracy but also integrates seamlessly into clinical workflows. To this end, we introduced a novel VRG-based ensemble image feature extraction technique, combining the powers of VGG, RF, and GB models to synthesize a robust feature set conducive to high-precision classification. The ensemble approach demonstrated a best-in-class performance with the GB model achieving an outstanding 99.73% accuracy in detecting esophagitis and polyps. The practical implications of these results are substantial, indicating that our method can significantly improve diagnostic accuracy in real-world settings, reduce the rate of misdiagnosis, and contribute to the efficient and effective treatment of patients, ultimately enhancing the quality of healthcare services. With the successful application of our proposed method to a controlled dataset, future work involves deploying the model in clinical environments and expanding its application to a broader spectrum of Gastrointestinal conditions across multi-class datasets.

Intelligent robotic control system based on computer vision technology

Computer vision is a kind of simulation of biological vision using computers and related equipment. It is an important part of the field of artificial intelligence. Its research goal is to make computers have the ability to recognize three-dimensional environmental information through two-dimensional images. Computer vision is based on image processing technology, signal processing technology, probability statistical analysis, computational geometry, neural network, machine learning theory and computer information processing technology, through computer analysis and processing of visual information.The article explores the intersection of computer vision technology and robotic control, highlighting its importance in various fields such as industrial automation, healthcare, and environmental protection. Computer vision technology, which simulates human visual observation, plays a crucial role in enabling robots to perceive and understand their surroundings, leading to advancements in tasks like autonomous navigation, object recognition, and waste management. By integrating computer vision with robot control, robots gain the ability to interact intelligently with their environment, improving efficiency, quality, and environmental sustainability. The article also discusses methodologies for developing intelligent garbage sorting robots, emphasizing the application of computer vision image recognition, feature extraction, and reinforcement learning techniques. Overall, the integration of computer vision technology with robot control holds promise for enhancing human-computer interaction, intelligent manufacturing, and environmental protection efforts.

Detection of Insects and Pests in Agriculture field using MobileNet

Abstract: The Indian economy heavily relies on agriculture, with high-quality crop production playing a pivotal role. However, frequent pest attacks pose significant threats by reducing crop yields and compromising food safety through nutrient depletion. This adversely impacts the economy, leading to substantial losses for farmers and risking lives. Timely monitoring of crops is imperative to combat pests effectively, necessitating the use of appropriate pesticides. Pest detection technologies can aid in early intervention, preventing crop damage and pesticide overuse. Artificial intelligence (AI) emerges as a crucial tool in addressing agricultural challenges. This research focuses on utilizing the MobileNetV2 algorithm for pest classification, leveraging image reshaping and feature extraction techniques. Results indicate MobileNetV2 outperforms other pre-trained models, achieving a higher accuracy of 0.95. By enhancing pest detection capabilities, AI-based technologies offer promising solutions to bolster agricultural production and mitigate economic losses.

A machine vision approach for detecting changes in drill core textures using optical images

Drill core images offer valuable insights into the texture, structure and mineralogy of ores and their host rocks, which can be used to optimise downstream processes in the mining industry. The impact on downstream processes from particles of similar composition and mineralogy but different textures has been examined by several previous researchers through the application of supervised machine-learning techniques. This study proposes a novel approach for detecting changes in drill core textures through the analysis of optical images. This approach compares three widely used image feature extraction techniques (local binary patterns, grey-level co-occurrence matrix and convolutional neural network), followed by calculation of a uniqueness measure, based on the Hotelling statistic, designed to identify anomalous segments of core. The effectiveness of the uniqueness measure is validated on a test core comprising six sections with different textures. Two drill cores, from the Brukunga test site in South Australia, were selected as case studies. Of the three feature extraction methods, local binary patterns were found to give the strongest signals of change. There exist two main regimes that separate halfway along both drill cores, indicating a change in lithology or the presence of mineralisation.

Radiology Image Data Augmentation and Image Enhancement in Respiratory Disease Infection Detection Using Machine Learning Approach

Medical imaging plays an important role in medical diagnosis and treatment. It is also useful in medical applications. The proposed concept's goal is to understand the importance of data balancing, data augmentation, and segmentation in the clinical field, to improve image data balancing using data augmentation and edge detection techniques, to improve radiology image preprocessing to locate regions of interest (ROI), and to construct custom-built Deep Neural Networks (DNN) in diagnosing respiratory illness using Machine Learning approaches. Images of varying quality from multiple machine types are frequently included in different datasets. This study used four datasets, three of which are online datasets from Kaggle and the fourth is real-time radiology pictures of COVID and Pneumonia-infected persons from neighboring local hospitals. We proposed RESP_DATA_BALANCE for image data balance in dataset construction, and RDD_ROI (Respiratory Disease Detection Region of Interest) algorithm, which combines improved image feature extraction technique using a GLCM and unsupervised K-means clustering for segmentation to identify the region of interest in the detection of respiratory diseases. Our suggested custom-built 28-layer Respiratory Disease Detection Deep Neural Network (RDD_DNN) is used for further training, testing, and validation. Furthermore, experimental results focus on performance characteristics using various data augmentation, edge detection, and preprocessing strategies. The experimental purpose of our research study is to aid in the classification and early diagnosis of respiratory disorders.

Applying Deep Learning Algorithms for Automatic Recognition and Transcription of Texts in Oracle Bones and Golden Texts

Abstract This paper explores applying deep learning techniques for automatically recognizing and transcribing oracle bone and gold texts. We significantly enhance model recognition efficiency by leveraging the power of Generative Adversarial Networks (GANs) for image data enhancement and the Pix2Pix model for text repair. Our approach integrates the ResNet50 model for robust feature extraction with unsupervised domain adaptation, utilizing multiple pseudo labels to achieve efficient text recognition and transcription. We improve the model’s repair capabilities by generating hard-to-distinguish sample data through GANs and employing a U-Net-based text repair model enhanced with dense connectivity and spectral normalization. Further, combining ResNet50 for feature extraction and advanced domain adaptation techniques strengthens the model’s generalization. Our results on the Oracle dataset show an increase in recognition accuracy from 82% to 94.5%, highlighting the effectiveness of our image enhancement strategies. The ResNet50 extractor outperforms others across various Intersection over Union (IoU) metrics, establishing its feature extraction superiority. In real-world scenarios, testing with a combined Oracle and Jinwen dataset yields a recognition accuracy above 80%, demonstrating our model’s ability to effectively fulfill the recognition task. This research underscores the potential of deep learning algorithms in automating the recognition and transcription of ancient texts, offering a novel solution that significantly boosts recognition accuracy through a synergistic blend of image enhancement, feature extraction, and domain adaptation techniques.

Characterization of aqueous alteration and formation of salty exposures at Ius Chasma, Mars

Intriguing outcrops in Ius Chasma provide a window into past aqueous processes in Valles Marineris, Mars. Hydrous sulfate minerals are abundant throughout this region, but one area in Ius Chasma includes phyllosilicates, opal, and additional materials with unusual spectral features. This study at Geryon Montes, an east-west horst that divides Ius Chasma into a northern and southern canyon, exploits recent advances in image calibration and feature extraction techniques for analysis of hyperspectral images acquired by the Compact Reconnaissance Imaging Spectrometer for Mars (CRISM). Specifically, a unique spectral “doublet” feature with absorptions at 2.21–2.23 and 2.26–2.28 μm is isolated at the border of phyllosilicate-bearing and sulfate-bearing regions in Ius Chasma and surveyed to characterize outcrops that may represent a changing climate on Mars. We document and map three distinct forms of this “doublet” material in relation to phyllosilicates and opal. Analyses of compositional maps derived from CRISM overlain on High Resolution Stereo Camera (HRSC) and High Resolution Imaging Science Experiment (HiRISE) imagery has revealed the presence of these hydrated outcrops along the wall rocks below a breach in the Geryon Montes, bordering a canyon containing abundant hydrated sulfates. Our investigation supports formation of these unique alteration phases through acid alteration of ancient smectites in the wall rock as the sulfate brine overflowed the south canyon of Ius Chasma at the breach in Geryon Montes and penetrated the deeper northern canyon.

Folk Games Image Captioning using Object Attention

The result of a deep learning-based image captioning system with encoder-decoder framework relies heavily on the image feature extraction technique and the caption-based model. The accuracy of the model is heavily influenced by the proposed attention mechanism. The inability to distinguish between the output of the attention model and the input expectation of the decoder can cause the decoder to give incorrect results. In this paper, we proposed an object-attention mechanism using object detection. Object detection outputs a bounding box and an object category label, which is then used as an image input into VGG16 for feature extraction and into a caption-based LSTM model. The experimental results showed that the system with object attention performed better than the system without object attention. BLEU-1, BLEU-2, BLEU-3, BLEU-4, and CIDER scores for the image captioning system with object attention improved 12.48%, 17.39%, 24.06%, 36.37%, and 43.50% respectively compared to the system without object attention.

Cocoa beans classification using enhanced image feature extraction techniques and a regularized Artificial Neural Network model

Cut-Test technique employs visual inspection of interior coloration, compartmentalization, and defects of beans for effective classification of cocoa beans. However, due to its subjective nature and natural variations in visual perception, it is intrinsically limited, resulting in disparities in verdicts, imprecision, discordance, and time-consuming and labor-intensive classification procedures. Machine Learning (ML) techniques have been proposed to address these challenges with significant results, but there is still a need for improvement. In this paper, we propose a color and texture extraction technique for image representation, as well as a generalized, less complex Neural Network model, to help improve the performance of machine classification of Cut-Test cocoa beans. A total of 1400 beans were classified into 14 grades. Experimental results on the equal cocoa cut-test dataset, which is the standard publicly available cut-test dataset, show that the novel extraction method combined with the developed Artificial Neural Networks provides a more homogeneous classification rate for all grades, obtaining 85.36%, 85%, 83%, and 83% for accuracy, precision, recall, and F1 measure, respectively. The proposed model outperforms other ML models, such as Support Vector Machines, Decision Trees, Random Forests, and Naïve Bayes, on the same dataset. Additionally, the proposed ANN model demonstrates relatively better generalization when compared with earlier work by Santos on the same dataset. The proposed techniques in this work are robust on the cut-test dataset and can serve as an accurate Computer-Aided Diagnostic tool for cocoa bean classification.

A Methodical and Performance-based Investigation of Alzheimer Disease Detection on Magnetic Resonance and Multimodal Images.

In recent years, Alzheimer's Disease (AD) has received more attention in the field of medical imaging, which leads to cognitive disorders. Physicians mainly rely on MRI imaging to examine memory impairment, thinking skills, judge functional abilities, and detect behavioral abnormalities for diagnosing Alzheimer's disease. Early diagnosis of AD has become a challenging and strenuous task with conventional methods. The diagnostic procedure becomes complicated due to the structure and heterogeneous dimensions of the brain. This paper visualizes and analyzes the publications on AD and furnishes a detailed review based on the stages involved in the early detection of the disease. This paper also focuses on assorted stages of disease detection such as image preprocessing, segmentation, feature extraction, classification, and optimization techniques that have been used in the diagnosis of AD during the past five years. It also spotlights the deep learning models used in assorted stages of detection. This paper also highlights the benefits of each method for assorted modalities of images. AD has been analyzed with various computational methods on a few datasets, which leads to high computation time and loss of important features. Hybrid methods can perform better in every diagnosis stage of AD than others. Finally, the assorted datasets used for the diagnosis and investigation of Alzheimer's disease were analyzed and explored using a computerized system for future scope. From the review papers, we can conclude that DNN has greater accuracy in MR images and CNN +AEC has the best accuracy in the multimodal images.

A post-correlation graphical way for continuous GNSS spoofing detection

Global navigation satellite system (GNSS) receivers are under the threat of spoofing attacks. The signal quality monitoring (SQM) technique is effective in monitoring the distorted auto-correlation function (ACF). However, it has limited detection effectiveness in detecting spoofing signals that are greatly overpowered and with significant code phase shifts. This paper introduces a new metric called ACF similarity to characterize the ACF distortion and power abnormality in the tracking loop based on image feature extraction techniques. The spoofing detection algorithm and the optimal threshold utilizing the generalized likelihood ratio test (GLRT) are further developed. The performance of the proposed detector has been verified by utilizing the Texas Spoofing Test Battery (TEXBAT) dataset and Monte Carlo simulation tests. Results show that with 1% false alarm rate, the proposed detector achieves a detection probability of 87% in the TEXBAT datasets and provides better detection sensitivity than the conventional SQM metrics.

A pathomic approach for tumor-infiltrating lymphocytes classification on breast cancer digital pathology images

Background and objectivesThe detection of tumor-infiltrating lymphocytes (TILs) could aid in the development of objective measures of the infiltration grade and can support decision-making in breast cancer (BC). However, manual quantification of TILs in BC histopathological whole slide images (WSI) is currently based on a visual assessment, thus resulting not standardized, not reproducible, and time-consuming for pathologists. In this work, a novel pathomic approach, aimed to apply high-throughput image feature extraction techniques to analyze the microscopic patterns in WSI, is proposed. In fact, pathomic features provide additional information concerning the underlying biological processes compared to the WSI visual interpretation, thus providing more easily interpretable and explainable results than the most frequently investigated Deep Learning based methods in the literature. MethodsA dataset containing 1037 regions of interest with tissue compartments and TILs annotated on 195 TNBC and HER2+ BC hematoxylin and eosin (H&E)-stained WSI was used. After segmenting nuclei within tumor-associated stroma using a watershed-based approach, 71 pathomic features were extracted from each nucleus and reduced using a Spearman's correlation filter followed by a nonparametric Wilcoxon rank-sum test and least absolute shrinkage and selection operator. The relevant features were used to classify each candidate nucleus as either TILs or non-TILs using 5 multivariable machine learning classification models trained using 5-fold cross-validation (1) without resampling, (2) with the synthetic minority over-sampling technique and (3) with downsampling. The prediction performance of the models was assessed using ROC curves. Results21 features were selected, with most of them related to the well-known TILs properties of having regular shape, clearer margins, high peak intensity, more homogeneous enhancement and different textural pattern than other cells. The best performance was obtained by Random-Forest with ROC AUC of 0.86, regardless of resampling technique. ConclusionsThe presented approach holds promise for the classification of TILs in BC H&E-stained WSI and could provide support to pathologists for a reliable, rapid and interpretable clinical assessment of TILs in BC.

A Novel Architecture for Feature Extraction and Convolution for Image Segmentation of Pathology Detection from Chest X-Ray Images

Neural networks are widely used for the automation of analysis and classification tasks in the field of medical image processing. They have successfully achieved state of the art performance in medical image segmentation and feature extraction techniques. This automatic classification in the medical field is very helpful in developing tools for early detection of dreadful pathologies, like tuberculosis and pneumonia, in areas where access to doctors or radiologists is scarce. In this work, we propose a novel approach for the classification of lung pathologies like tuberculosis and pneumonia by masking them in boundary boxes using convolutional neural networks. Our solution provides a flexible way, by using saved trained models that could be directly employed by the Radiologists. In this paper, we describe the architecture required to achieve such a scalable model which could be used by doctors and radiologists without too much training in the technologies of the times. The proposed convolutional architecture consists of connected components which are parallel residual blocks and sampling layers. The images do not lose their original quality, giving the best error free predictions. We visualize this model to be deployed in labs, providing access to medical imaging expertise to some of the most remote places in the world.

OC-065 PEEKABOO WITH MESHES AND MACHINES: DEEP LEARNING TO IDENTIFY TACKS AND MESHES ON CT SCANS

Abstract Aim To identify the presence of tacks and meshes in CT scans of patients who have previously undergone hernia repairs Materials & Methods We annotated data from >100 anonymised Hernia CT scans of patients who had undergone previous ventral hernia repairs and used machine learning(ML)/ deep learning(DL) techniques to identify the presence of meshes and tacks.Annotation of CT scans was performed using computer vision tools. A combination of image processing, feature extraction and artificial intelligence(AI) techniques were used to create models that could identify tacks and meshes on CT scans. Results We were able to identify the presence of meshes and tacks with >55% accuracy. The AI model under construction is continuing to improve performance. Conclusions Identification of the mesh is a challenge for surgeons and radiologists alike. The presence of machine learning techniques has revolutionised radiology and made the identification of obscure structures possible. Meshes present a unique challenge as they constitute a foreign tissue which integrates into native tissue. We believe that identification of hernia meshes and tacks can help surgeons identify the right planes for planning re-surgeries while operating in patients with previous hernia repairs or while tackling recurrences.

Real-time snowy weather detection based on machine vision and vehicle kinematics: A non-parametric data fusion analysis protocol

Introduction: This study introduces a new analysis protocol for detecting real-time snowy weather conditions on freeways by utilizing trajectory-level data extracted from the Second Strategic Highway Research Program (SHRP2) Naturalistic Driving Study (NDS) dataset. The data include parameters reduced from a real-time image feature extraction technique, time series data collected from external sensors, and CANbus data collected by the NDS ego-vehicles. To provide flexibility in winter maintenance, two segmentation types of one-minute and one-mile segments were used to sample snowy trips and their matched clear weather trips. Method: In this study, four non-parametric models were developed using six data assemblies to detect snowy weather on freeways. The data assemblies are arranged based on three data sources, including image database extracted from an in-vehicle video camera, sensors, and CANbus data, to examine the effectiveness of snow detection models for different data types considering real-time availability of data. Results: Overall, the developed models successfully detected snowy weather on freeways with an accuracy ranging between 76% to 89%. Results indicated that high accuracy of estimating snowy weather can be accomplished using the data fusion between external sensors data and texture parameters of images, without accessing to CANbus data. Practical Applications: Practical applications can be driven with respect to the time or distance coordinates, using different data fusion assemblies, and data availability. The study proves the importance of employing vehicles as weather sensors in the Connected Vehicles (CV) applications and Variable Speed Limit (VSL) to improve traffic safety on freeways.

Computational Technique Based on Machine Learning and Image Processing for Medical Image Analysis of Breast Cancer Diagnosis

Breast cancer is the most lethal type of cancer for all women worldwide. At the moment, there are no effective techniques for preventing or curing breast cancer, as the source of the disease is unclear. Early diagnosis is a highly successful means of detecting and managing breast cancer, and early identification may result in a greater likelihood of complete recovery. Mammography is the most effective method of detecting breast cancer early. Additionally, this instrument enables the detection of additional illnesses and may provide information about the nature of cancer, such as benign, malignant, or normal. This article discusses an evolutionary approach for classifying and detecting breast cancer that is based on machine learning and image processing. This model combines image preprocessing, feature extraction, feature selection, and machine learning techniques to aid in the classification and identification of skin diseases. To enhance the image’s quality, a geometric mean filter is used. AlexNet is used for extracting features. Feature selection is performed using the relief algorithm. For disease categorization and detection, the model makes use of the machine learning techniques such as least square support vector machine, KNN, random forest, and Naïve Bayes. The experimental investigation makes use of MIAS data collection. This proposed technology is advantageous for accurately identifying breast cancer disease using image analysis.

CLASSIFICATION OF INFORMATIVE FRAMES IN COLONOSCOPY VIDEO BASED ON IMAGE ENHANCEMENT AND PHOG FEATURE EXTRACTION

Colonoscopy allows doctors to check the abnormalities in the intestinal tract without any surgical operations. The major problem in the Computer-Aided Diagnosis (CAD) of colonoscopy images is the low illumination condition of the images. This study aims to provide an image enhancement method and feature extraction and classification techniques for detecting polyps in colonoscopy images. We propose a novel image enhancement method with a Pyramid Histogram of Oriented Gradients (PHOG) feature extractor to detect polyps in the colonoscopy images. The approach is evaluated across different classifiers, such as Multi-Layer Perceptron (MLP), Adaboost, Support Vector Machine (SVM), and Random Forest. The proposed method has been trained using the publicly available databases CVC ClinicDB and tested in ETIS Larib and CVC ColonDB. The proposed approach outperformed the existing state-of-the-art methods on both databases. The reliability of the classifiers’ performance was examined by comparing their F1 score, precision, F2 score, recall, and accuracy. PHOG with Random Forest classifier outperformed the existing methods in terms of recall of 97.95%, precision 98.46%, F1 score 98.20%, F2 score of 98.00%, and accuracy of 98.21% in the CVC-ColonDB. In the ETIS-LARIB dataset it attained a recall value of 96.83%, precision 98.65%, F1 score 97.73%, F2 score 98.59%, and accuracy of 97.75%. We observed that the proposed image enhancement method with PHOG feature extraction and the Random Forest classifier will help doctors to evaluate and analyze anomalies from colonoscopy data and make decisions quickly.

An Image Feature extraction technique Alzheimer’s disease using inductive learning

An Image Feature extraction technique Alzheimer’s disease using inductive learning