Image Segmentation Process Research Articles

Sports video retrieval and classification using focus u-net based squeeze excitation and residual mapping deep learning model

Sports videos are widely used by athletes and coaches for training and match analysis purposes outside the mainstream audience. Sports videos should be effectively classified into different genres to easily retrieve and index them from large video datasets. Manual labelling classification methods may cause errors and have low accuracy. Classification based on video content analysis is challenging for computer vision-based techniques. This work introduces an improved focus-net deep learning (DL) model called the Convolutional squeeze U-Net based encoder-decoder for sports video retrieval and classification. First, the keyframes are extracted from the input sports video using a clustering and optical flow analysis method. In the next stage, the frames are pre-processed using a smoothed shock filtering technique to remove the noise. The process of image segmentation is carried out using a Convolutional squeeze U-Net based encoder-decoder model. Finally, the sports video can be classified using the softmax classifier. A CNN (convolutional neural network) is utilized at the encoder section for extracting the features and fed to the decoder for video classification. The experiments are performed in the UCF101 dataset, and the proposed model achieved an overall accuracy of 99.68%. Hence, it is proven that the proposed focus-net model can be efficiently utilized in sports video classification.

Classification of Fruits High in Vitamin C Using Self-Organizing Map and the K-Means Clustering Algorithm

Vitamin C-rich fruits not only taste fresh and delicious but also have the potential to increase the body's resistance to various diseases and maintain a proper nutritional balance. Information about fruits high in vitamin C is very important in order to increase public knowledge about which fruits contain high levels of vitamin C. However, to classify fruits high in vitamin C based on their image, a model is needed that is able to analyze the characteristics present in the image of the fruit. The purpose of this study is to build a classification model for high-vitamin C fruits with a combination of the Self-Organizing Map (SOM) artificial neural network algorithm and K-Means Clustering. Prior to classification, an image segmentation process is carried out using the K-Means Clustering algorithm, which will separate the image into parts that have similar visual characteristics. After the segmented image, the features of the object are extracted based on shape and texture. After the features of the image have been obtained, proceed with classifying images using the SOM algorithm by mapping multidimensional data into a lower-dimensional spatial representation to obtain the appropriate group or class. The accuracy test results for the built model produce an accuracy value of 93.33% and are included in the good category

Design of a Novel Skin Lesion Predictor Model Using Hybrid Particle Swarm Optimization and Convolutional Neural Networks

The prediction of skin cancer at the earlier stage is extremely essential for melanoma. There is a need for intellectual computer analysis for skin lesions. The segmentation of lesion boundaries is vital to accurately identify the lesions from the dermoscopic images where the diagnosis is complex for various skin lesion types. Thus, some pre-processing steps are required to attain higher sensitive lesion boundary segmentation and classification. Initially, pre-processing is done with median filter to offer reputation of boundary preservation and does not in-cooperate newer pixel values to the processed image. Next is the process of image segmentation for Region of Interest (ROI) and non-Region of Interest ([Formula: see text] using the Jaccard Distance segmentation process. The novelty of the work relies on the inclusion of compression techniques to make the access easier without any loss. The extracted regions are encoded with Freeman Chain Coding and compressed with Lempel–Ziv–Welch (LZW) and Zero Tree Wavelet (EZW) for ROI and non-Region of Interest regions. Finally, image classification is done with Hybrid Particle Swarm Optimization and Convolutional Neural Networks ([Formula: see text]PSO-CNN). The simulation is done with TensorFlow & Python environment and the proposed model outperforms the existing standard approaches. Some metrics like objective function, confusion matrix, accuracy, precision, [Formula: see text]-measure, and recall are evaluated. The model attains 77.5% accuracy, 86.36% precision, 77.5% recall and 77.92% [Formula: see text]-measure for proposed [Formula: see text]PSO-CNN which is higher than the standard CNN model.

Image segmentation and advanced processing of 2D diffraction data

Image segmentation and advanced processing of 2D diffraction data

Inspection and classification of wheat quality using image processing

Wheat plays an important role in our daily life and industrial production. Several computer vision approaches have been proposed for classifying wheat quality, but there were some methods focusing on the problem of cohesive wheats while image processing. In this paper, we designed a single kernel guide groove to separate the cohesive wheats, which could simplify the algorithm of image processing and improve the accuracy rate of classification. For the method followed while recording the data, the image information must be converted into digital information, and the results are provided using appropriate image processing algorithms. Image preprocessing steps such as binarization, image enhancement, image segmentation, and morphological processing were used to reduce noise. For image segmentation, we proposed the following new segmentation methods: (1) extracting wheat region by converting image to H channel and (2) watershed algorithm based on Euclidean distance transformation. For the classification model, 22 features of 7 different qualities of wheat were inputted in the Back Propagation (BP) neural network and Support Vector Machine (SVM) model, and the overall correct classification rates were determined to be 91% and 97% for SVM and BP neural network, respectively. The BP neural network was more suitable for wheat appearance quality detection.

RLSegNet: An Medical Image Segmentation Network Based on Reinforcement Learning.

In the area of medical image segmentation, the spatial information can be further used to enhance the image segmentation performance. And the 3D convolution is mainly used to better utilize the spatial information. However, how to better utilize the spatial information in the 2D convolution is still a challenging task. In this paper, we propose an image segmentation network based on reinforcement learning (RLSegNet), which can translate the image segmentation process into a serial of decision-making problem. The proposed RLSegNet is a U-shaped network, which is composed of three components: the feature extraction network, the Mask Prediction Network (MPNet), and the up-sampling network with the cascade attention module. The deep semantic feature in the image is first extracted by adopting the feature extraction network. Then, the Mask Prediction Network (MPNet) is proposed to generate the prediction mask for the current frame based on the prior knowledge (segmentation result). And the proposed cascade attention module is mainly used to generate the weighted feature mask so that the up-sampling network pays more attention to the interesting region. Specifically, the state, action and reward used in the reinforcement learning are redesigned in the proposed RLSegNet to translate the segmentation process as the decision-making process, which performs as the reinforcement learning to realize the brain tumor segmentation. Extensive experiments are conducted on the BRATS 2015 dataset to evaluate the proposed RLSegNet. The experimental results demonstrate that the proposed method can achieve a better segmentation performance, in comparison with other state-of-the-art methods.

Plant Disease Image Segmentation applying the K-Means Algorithm, Firefly, and Particle Swarm Optimisation

Abstract: The process of dividing an image to several pieces with comparable features is known as segmentation of images. A difficult phase in the image segmentation process is to extract the information from the image. Clustering is used to segment photos of a similar type or to assess the relevance of data. In essence, clustering is an unsupervised learning process. The data elements that make up one cluster share the same kinds of characteristics. In other words, each cluster has a minimum difference between its points and a maximum difference from the data points of other clusters. The suggested approach clusters image pixels by combining Particle Swarm Optimization with K-Means. Since combined techniques produce the best results, Kmeans should be thanked. K-means combined with Particle Swarm Optimization performs better than firefly combined with Kmeans. The firefly algorithm is used to tackle optimization issues and has a variety of uses. The Firefly method has been utilized in numerous research and optimization fields. Firefly algorithm and Firefly have been effectively utilized to solve a variety of issues. The firefly algorithm needs to be altered or combined with other algorithms in order to be used to a wide range of problems. Due to their metaheuristic nature, contemporary algorithms are crucial for solving NP-Hard problems

Automatic Detection and Identification of Defects by Deep Learning Algorithms from Pulsed Thermography Data.

Infrared thermography (IRT), is one of the most interesting techniques to identify different kinds of defects, such as delamination and damage existing for quality management of material. Objective detection and segmentation algorithms in deep learning have been widely applied in image processing, although very rarely in the IRT field. In this paper, spatial deep-learning image processing methods for defect detection and identification were discussed and investigated. The aim in this work is to integrate such deep-learning (DL) models to enable interpretations of thermal images automatically for quality management (QM). That requires achieving a high enough accuracy for each deep-learning method so that they can be used to assist human inspectors based on the training. There are several alternatives of deep Convolutional Neural Networks for detecting the images that were employed in this work. These included: 1. The instance segmentation methods Mask-RCNN (Mask Region-based Convolutional Neural Networks) and Center-Mask; 2. The independent semantic segmentation methods: U-net and Resnet-U-net; 3. The objective localization methods: You Only Look Once (YOLO-v3) and Faster Region-based Convolutional Neural Networks (Fast-er-RCNN). In addition, a regular infrared image segmentation processing combination method (Absolute thermal contrast (ATC) and global threshold) was introduced for comparison. A series of academic samples composed of different materials and containing artificial defects of different shapes and nature (flat-bottom holes, Teflon inserts) were evaluated, and all results were studied to evaluate the efficacy and performance of the proposed algorithms.

Gray Level Co-Occurrence Matrices and Support Vector Machine for Improved Lung Cancer Detection

A detection system based on digital image processing and machine learning classification was developed to detect normal and cancerous lung conditions. 340 data from LIDC –IDRI were processed through several stages. The first stage is pre-processing using three filter variations and contrast stretching, which reduce noise and increase image contrast. The image segmentation process uses Otsu Thresholding to clarify the ROI of the image. The texture feature extraction with GLCM was applied using 21 feature variations. Data extraction is used as a label value learned by the classification system in the form of SVM. The results of the training data classification are processed with a confusion matrix which shows that the high pass filter has higher accuracy than the other two variations. The proposed method was assessed in terms of accuracy, precision and recall. The model provided an accuracy of 99.67 % training data and 97.50 % testing data.

Modeling Digital Image Segmentation with Canny Method

In general, the segmentation process is divided into three parts. classification, by edge, and by area. The digital image segmentation process divides an object whose surface or background maintains the RGB value of all pixels of a digital image so that the object can be processed for other purposes. This system aims to execute drawing objects using intelligent methods. In the Canny method, the process begins with taking digital images and continues with the grayscale process. In addition, technique selection starts with performing a complex operator or Laplacian edge detection and finally unlocks it. Successful segmentation results using edge detection with intelligent operators to separate objects. This system uses the Matlab 2017 application.

Application of an improved watershed algorithm based on distance map reconstruction in bean image segmentation

As an important step in image processing, image segmentation can be used to determine the accuracy of object counts, and area and contour data. In addition, image segmentation is indispensable in seed testing research. Due to the uneven grey level of the original image, traditional watershed algorithms generate many incorrect edges, resulting in oversegmentation and undersegmentation, which affects the accuracy of obtaining seed phenotype information. The DMR-watershed algorithm, an improved watershed algorithm based on distance map reconstruction, is proposed in this paper. According to the grey distribution characteristics of the image, the grey reduction amplitude h was selected to generate the mask image with the same grey distribution trend as that of the original image. The original greyscale map was reconstructed with corresponding thresholds selected according to the false minima of different regions that are to be segmented, which generates an accurate distance map that eliminates the wrong edges. An adzuki bean (Vigna angularis L.) image was selected as the experimental material and the residual rate of the segmentation counting results of each algorithm was investigated in two cases of two-particle adhesion and multiparticle adhesion. The results of the proposed algorithm were compared with those of the traditional watershed algorithm, edge detection algorithm and concave point analysis algorithm which are commonly used for seed segmentation. In the case of two-particle adhesion, the residual rates of the watershed algorithm and edge detection algorithm were 0.233 and 0.275, respectively, while the residual rate of the concave point analysis algorithm was 0 which proved to be suitable for two-particle adhesion. In the case of multiparticle adhesion, the concave point analysis algorithm was not applicable because it would destroy the seed image. The residual rates of the watershed algorithm and edge detection algorithm were 0.063 and 0.188, respectively, while the residual rate of the proposed algorithm in the two-particle adhesion cases was 0 and the counting accuracy reached 100%, which proved the effectiveness of the proposed algorithm. The algorithm in this paper significantly improves the accuracy of image segmentation of adherent seeds, and provides a new reference for image segmentation processing in seed testing.

Thresholding and Filtering Based Brain Tumor Segmentation on MRI Images

Abstract: The brain is the interior most part of the central nervous system and is an intracranial solid neoplasm. Tumour’s are created by an abnormal and uncontrollable cell division in the brain. In this work, axial view of the brain image (2D) from MRI scan has been used because MRI scan is less harmful than CT brain scan. The study of brain tumor is important as it is occurring in many people. In this paper, an image segmentation process was proposed for the identification or detection of tumor from the brain. The methodology consists of the following steps: pre-processing by using grey-level, sharpening and median filters; segmentation of the image was performed by thresholding and also by applying the watershed segmentation. Finally the tumor region was obtained with its area [1].

Machine Learning Methods in Skin Disease Recognition: A Systematic Review

Skin lesions affect millions of people worldwide. They can be easily recognized based on their typically abnormal texture and color but are difficult to diagnose due to similar symptoms among certain types of lesions. The motivation for this study is to collate and analyze machine learning (ML) applications in skin lesion research, with the goal of encouraging the development of automated systems for skin disease diagnosis. To assist dermatologists in their clinical diagnosis, several skin image datasets have been developed and published online. Such efforts have motivated researchers and medical staff to develop automatic skin diagnosis systems using image segmentation and classification processes. This paper summarizes the fundamental steps in skin lesion diagnosis based on papers mainly published since 2013. The applications of ML methods (including traditional ML and deep learning (DL)) in skin disease recognition are reviewed based on their contributions, methods, and achieved results. Such technical analysis is beneficial to the continuing development of reliable and effective computer-aided skin disease diagnosis systems. We believe that more research efforts will lead to the current automatic skin diagnosis studies being used in real clinical settings in the near future.

Efficient Approach to Color Image Segmentation Based on Multilevel Thresholding Using EMO Algorithm by Considering Spatial Contextual Information.

The process of image segmentation is partitioning an image into its constituent parts and is a significant approach for extracting interesting features from images. Over a couple of decades, many efficient image segmentation approaches have been formulated for various applications. Still, it is a challenging and complex issue, especially for color image segmentation. To moderate this difficulty, a novel multilevel thresholding approach is proposed in this paper based on the electromagnetism optimization (EMO) technique with an energy curve, named multilevel thresholding based on EMO and energy curve (MTEMOE). To compute the optimized threshold values, Otsu's variance and Kapur's entropy are deployed as fitness functions; both values should be maximized to locate optimal threshold values. In both Kapur's and Otsu's methods, the pixels of an image are classified into different classes based on the threshold level selected on the histogram. Optimal threshold levels give higher efficiency of segmentation; the EMO technique is used to find optimal thresholds in this research. The methods based on an image's histograms do not possess the spatial contextual information for finding the optimal threshold levels. To abolish this deficiency an energy curve is used instead of the histogram and this curve can establish the spatial relationship of pixels with their neighbor pixels. To study the experimental results of the proposed scheme, several color benchmark images are considered at various threshold levels and compared with other meta-heuristic algorithms: multi-verse optimization, whale optimization algorithm, and so on. The investigational results are illustrated in terms of mean square error, peak signal-to-noise ratio, the mean value of fitness reach, feature similarity, structural similarity, variation of information, and probability rand index. The results reveal that the proposed MTEMOE approach overtops other state-of-the-art algorithms to solve engineering problems in various fields.

Design Challenges in Effective Algorithm Development of Sign Language Recognition System

Sign language is the most putative language among hearing impaired people. They use non-verbal form of communication that involves hand gestures, head or body movement or facial expressions. Of these hand gestures is more widely used. Automatic Sign Language Recognition (ASLR) System can be used to convert these non-verbal signs into text or sound so that normal people can identify them without learning the sign language. ASLR employs Image Processing and Artificial Intelligence (AI) algorithms for effective conversion from sign to sound or text. This review unveils various image processing and AI steps involved in the conversion process, bringing out important topologies in the Image acquisition, segmentation, feature extraction, classification and detection process and a comparative analysis among various topologies. Attempts have been made to shed light into adoption of alternate design strategies in segmentation and feature extraction that enhance the performance in a complex environment.

Early Identification and Localization Algorithm for Weak Seedlings Based on Phenotype Detection and Machine Learning

It is important to propose the correct decision for culling and replenishing seedlings in factory seedling nurseries to improve the quality of seedlings and save resources. To solve the problems of inefficiency and subjectivity of the existing traditional manual culling and replenishment of seeds, this paper proposes an automatic method to discriminate the early growth condition of seedlings. Taking watermelon plug seedlings as an example, Azure Kinect was used to collect data of its top view three times a day, at 9:00, 14:00, and 19:00. The data were collected from the time of germination to the time of main leaf growth, and the seedlings were manually determined to be strong or weak on the last day of collection. Pre-processing, image segmentation, and point cloud processing methods were performed on the collected data to obtain the plant height and leaf area of each seedling. The plant height and leaf area on the sixth day were predicted using an LSTM recurrent neural network for the first three days. The R squared for plant height and leaf area prediction were 0.932 and 0.901, respectively. The dichotomous classification of normal and abnormal seedlings was performed using six machine learning classification methods, such as random forest, SVM, and XGBoost, for day six data. The experimental results proved that random forest had the highest classification accuracy of 84%. Finally, the appropriate culling and replenishment decisions are given based on the classification results. This method can provide some technical support and a theoretical basis for factory seedling nurseries and transplanting robots.

A Deep-Learning-Based Method for Correction of Bone-Induced CT Beam-Hardening Artifacts

The x-ray attenuation coefficients generally decrease as the x-ray energy increases, which leads to beam hardening artifacts in CT. Due to the difference of dependence of the attenuation coefficients on energy for soft tissue and bone in human body, a simple water precorrection procedure was unable to correct the bone-induced artifacts. Conventional empirical beam hardening correction (EBHC) method reply on empirical image segmentation and data combination processes and may not be able to fully correct the artifacts. We developed a physics-driven deep learning-based method, which followed the workflow of the EBHC method, but replaced the empirical components of the EBHC method with neural networks. Numerical experiments were performed to validate the proposed method and benchmark its performance with the EBHC method and the end-to-end training strategies based on two popular neural networks, i.e., U-net and RED-CNN. Results demonstrate that the proposed method achieved the best performance in both qualitative and quantitative aspects.

Traditional and deep learning-oriented medical and biological image analysis.

We investigated various methods for image segmentation and image processing for the segmentation of MRI of human medical data, as well as bioinformatics for the segmentation of brain cell details, in this work. The goal is to demonstrate and bring various mathematical analyses for medical and biological image analysis. We proposed new software and methods for improving the segmentation of biological and medical data. This way, we can find new ways to improve the diagnostic process in medical data and improve results in cell and iron diagnostics. We present the GrabCut algorithm as well as new, improved software for this part, a fuzzy approach and fuzzy processing of tissues, and finally machine‑learning techniques with neural networks. We implemented the new software in the C++ programming language for the Grab cut algorithm. Consequently, we present a fuzzy approach to the diagnosis of image data in Matlab. Finally, a deep learning-based approach is used, with a U-Net-based segmentation architecture proposed to measure the various brain cell parameters. We will be able to proceed with data that we were unable to proceed when using other methods. As a result, we improved biological and medical data segmentation to obtain better boundaries and sharper edges on the objects. There is still space to extend these methods to other medical and biological applications (Tab. 1, Fig. 34, Ref. 46). Keywords: segmentation; image processing; fuzzy segmentation, GrabCut, deep learning.

Comparative and Evaluation of Anomaly Recognition by Employing Statistic Techniques on Humanoid Robot

This paper presents the study to differentiate between normal and anomaly conditions detected by humanoid robots using comparative statistics. The study has been conducted in robotic software as a platform to examine the scenario and evaluate between the anomalies and normal behaviour in different conditions. This study employed a machine vision technique to run an image segmentation process and carry out semi-supervised object training within a controlled environment. The robot is trained by differentiating the measurement size of the target object, its location, and the object’s visibility within three different frames. The effect is measured by extracting the positive predictive value (PPV) value, mean and standard deviation value from the captured image using statistical techniques in machine vision. The results showed that the mean value decreased by around 50% from the normal scenario when an anomaly occurred. Aside from that, the standard deviation values were more than twofold compared to the common scenario, especially after the object’s size grew. In contrast, the deviation value is remarkably small when the target is situated in the middle of adjacent frames, compared to the value when the entire shape is positioned in the frame. Simultaneously, the mean values from the processed image produced a minor difference.

Automated Deep Learning Based Melanoma Detection and Classification Using Biomedical Dermoscopic Images

Melanoma remains a serious illness which is a common form of skin cancer. Since the earlier detection of melanoma reduces the mortality rate, it is essential to design reliable and automated disease diagnosis model using dermoscopic images. The recent advances in deep learning (DL) models find useful to examine the medical image and make proper decisions. In this study, an automated deep learning based melanoma detection and classification (ADL-MDC) model is presented. The goal of the ADL-MDC technique is to examine the dermoscopic images to determine the existence of melanoma. The ADL-MDC technique performs contrast enhancement and data augmentation at the initial stage. Besides, the k-means clustering technique is applied for the image segmentation process. In addition, Adagrad optimizer based Capsule Network (CapsNet) model is derived for effective feature extraction process. Lastly, crow search optimization (CSO) algorithm with sparse autoencoder (SAE) model is utilized for the melanoma classification process. The exploitation of the Adagrad and CSO algorithm helps to properly accomplish improved performance. A wide range of simulation analyses is carried out on benchmark datasets and the results are inspected under several aspects. The simulation results reported the enhanced performance of the ADL-MDC technique over the recent approaches.