GLCM Feature Extraction Research Articles

Model Design of The Image Recognition of Lung CT Scan for COVID-19 Detection Using Artificial Neural Network

COVID-19 has become a pandemic and is a big problem that needs to be checked out immediately. CT scan images can explain the lung conditions of COVID-19 patients and have the potential to be a clinical diagnostic tool. In this research, we classify COVID-19 by recognizing images on a computer tomography scan (CT scan) of the lungs using digital image processing and GLCM feature extraction techniques to obtain grayscale level values in CT images, followed by the creation of an artificial neural network model. So that the model can classify CT scan images, the results in this research obtained the most optimal model for COVID-19 classification performance with 90% accuracy, 88% precision, 91% recall, and 90% F1 score. This research can be a useful tool for clinical practitioners and radiologists to assist them in the diagnosis, quantification, and follow-up of COVID-19 cases.

Digital Image Processing using Texture Features Extraction of Local Seeds in Nekbaun Village with Color Moment, Gray Level Co Occurance Matrix, and k-Nearest Neighbor

The problem in determining the selection of corn seeds for replanting, especially maize in East Nusa Tenggara is still an important issue. Things that affect the quality of corn seeds are damaged seeds, dull seeds, dirty seeds, and broken seeds due to the drying and shelling process, which during the process of shelling corn with a machine, many damaged and broken seeds are found. So far, quality evaluation in the process of classification of the quality of corn seeds is still done manually through visible observations. Manual systems take a long time and produce products of inconsistent quality due to visual limitations, fatigue, and differences in the perceptions of each observer. The selection of local maize seeds in Timor Island, East Nusa Tenggara Province, especially in Nekbaun Village, West Amarasi District with feature extraction with a color moment shows that the mean, standard deviation and skewness features have an average validation of 88% and use the GLCM method which shows the neighbor relationship. Between the two pixels that form a co-occurrence matrix of the image data, namely GLCM, it shows that the features of homogeneity, correlation, contrast and energy have an average validation of 70.93%. The k-Nearest Neighbor (k-NN) algorithm is used in research to classify the image object to be studied. The results of this study were successfully carried out using k-Nearest Neighbor (k-NN) with the euclidean distance and k = 1 with the highest extraction yield of 88% and the results of GLCM feature extraction for homogeneity of 75.5%, correlation of 78.67%, contrast of 65.75 % and energy of 63.83% with an average accuracy of 70.93%.

Brain Tumor Segmentation and Classification from MRI Images using Improved FLICM Segmentation and SCA Weight Optimized Wavelet-ELM Model

Image segmentation is an essential technique of brain tumor MRI image processing for automated diagnosis of an image by partitioning it into distinct regions referred to as a set of pixels. The classification of the tumor affected and non-tumor becomes an arduous task for radiologists. This paper presents a novel image enhancement based on the SCA (Sine Cosine Algorithm) optimization technique for the improvement of image quality. The improved FLICM (Fuzzy Local Information C Means) segmentation technique is proposed to detect the affected regions of brain tumor from the MRI brain tumor images and reduction of noise from the MRI images by introducing a fuzzy factor to the objective function. The SCA weight-optimized Wavelet-Extreme Learning Machine (SCA-WELM) model is also proposed for the classification of benign tumors and malignant tumors from MRI brain images. In the first instance, the enhanced images are undergone improved FLICM Segmentation. In the second phase, the segmented images are utilized for feature extraction. The GLCM feature extraction technique is considered for feature extraction. The extracted features are aligned as input to the SCA-WELM model for the classification of benign and malignant tumors. The following dataset (Dataset-255) is considered for evaluating the proposed classification approach. An accuracy of 99.12% is achieved by the improved FLICM segmentation technique. The classification performance of the SCA-WELM is measured by sensitivity, specificity, accuracy, and computational time and achieved 0.98, 0.99, 99.21%, and 97.2576 seconds respectively. The comparison results of SVM (Support Vector Machine), ELM, SCA-ELM, and proposed SCA-WELM models are presented to show the robustness of the proposed SCA-WELM classification model.

Selection of Superior Rice Seed Features Using Deep Learning Method

Indonesia is a tropical country, known as an agricultural country, where 88.57% of the population works in the agricultural sector. Indonesia is rich in agricultural products such as rice, soybeans, corn, peanuts, cassava and sweet potatoes. Rice (Oryza sativia L) is one of the most dominant food commodities for the people of Indonesia. The carbohydrate content per 100 g of rice reaches 79.34 grams. The main benefit of rice is as a source of carbohydrates and a source of energy for the body. Seed is one of the factors that act as a carrier of technology in advanced agriculture, therefore the seeds used must be of good quality. Farmers tend to equate rice seeds from their previous harvests, the rice seed classification process is carried out manually through visual observation and soaking rice seeds in a container filled with water, submerged and floating rice seeds are selected for use, and those that float are discarded. But in reality it still produces less than optimal yields, for example rice that is less dense and broken. This research was conducted using the k Nearest Neighbor method which can classify by utilizing GLCM feature extraction which is an image texture analysis technique to produce features or information from image objects by calculating the contrast, energy, homogeneity and correlation values, then the best hyperplane will be displayed for distinguish between the two classes, namely superior and non-superior classes using the SVM model. This study aims to optimize yields with better quality. The results of this study were successfully carried out using k-Nearest Neighbor (k-NN) with Euclidean distance and k=5 got the highest accuracy of 92.85%. Indonesia is a tropical country, known as an agricultural country, where 88.57% of the population works in the agricultural sector. Indonesia is rich in agricultural products such as rice, soybeans, corn, peanuts, cassava and sweet potatoes. Rice (Oryza sativia L) is one of the most dominant food commodities for the people of Indonesia. The carbohydrate content per 100 g of rice reaches 79.34 grams. The main benefit of rice is as a source of carbohydrates and a source of energy for the body. Seed is one of the factors that act as a carrier of technology in advanced agriculture, therefore the seeds used must be of good quality. Farmers tend to equate rice seeds from their previous harvests, the rice seed classification process is carried out manually through visual observation and soaking rice seeds in a container filled with water, submerged and floating rice seeds are selected for use, and those that float are discarded. But in reality it still produces less than optimal yields, for example rice that is less dense and broken. This research was conducted using the k Nearest Neighbor method which can classify by utilizing GLCM feature extraction which is an image texture analysis technique to produce features or information from image objects by calculating the contrast, energy, homogeneity and correlation values, then the best hyperplane will be displayed for distinguish between the two classes, namely superior and non-superior classes using the SVM model. This study aims to optimize yields with better quality. The results of this study were successfully carried out using k-Nearest Neighbor (k-NN) with Euclidean distance and k=5 got the highest accuracy of 92.85%.

Analysis of Performance of Two Wavelet Families Using GLCM Feature Extraction for Mammogram Classification of Breast Cancer

Background: Mammogram images are low dose x-ray images which detect the breast cancer before the women can actually experience it. Objective: To determine the accurate methodology for feature extraction using different wavelet families and different classification algorithms. Methods: Two wavelet families are used namely Daubechies (db8) and Biorthogonal (bior3.7). The Gray-Level Co-occurrence Matrix is used for extracting 9 features at each sub-band. 27 features are extracted at three sub-bands of Discrete Wavelet Transform. The features are extracted at three levels of decomposition and after that the classification algorithm named as Naive Bayes, Multilayer Perceptron, Fuzzy-NN and Genetic Programming are applied to extracted features. The feature selection algorithms are applied named as Wavelet and Principle Component Analysis for selecting the features and then classification accuracy is determined and compared between these. Results: Mammographic Image Analysis Society, database including 322 mammogram images from 161 patients is used. The classification algorithm without feature selection named as Fuzzy-NN gives better results at the third level of decomposition having classification accuracy for db8 wavelet family up to 99.68% and for bior3.7 wavelet family up to 99.98%. Wavelet with Multilayer Perceptron using feature selection algorithm gives the classification accuracy for db8 wavelet family up to 96.27% and for bior3.7 up to 93.47%. Conclusion: Fuzzy-NN algorithm gives highest accuracy of 99.98% for bior3.7 wavelet family. It indicates that with feature selection and without feature selection, the wavelet families differ as db8 is better consideration for with feature selection and bior3.7 wavelet family for without feature selection.

Comparison of the histogram of oriented gradient, GLCM, and shape feature extraction methods for breast cancer classification using SVM

Breast cancer originates from the ducts or lobules of the breast and is the second leading cause of death after cervical cancer. Therefore, early breast cancer screening is required, one of which is mammography. Mammography images can be automatically identified using Computer-Aided Diagnosis by leveraging machine learning classifications. This study analyzes the Support Vector Machine (SVM) in classifying breast cancer. It compares the performance of three features extraction methods used in SVM, namely Histogram of Oriented Gradient (HOG), GLCM, and shape feature extraction. The dataset consists of 320 mammogram image data from MIAS containing 203 normal images and 117 abnormal images. Each extraction method used three kernels, namely Linear, Gaussian, and Polynomial. The shape feature extraction-SVM using Linear kernel shows the best performance with an accuracy of 98.44 %, sensitivity of 100 %, and specificity of 97.50 %.

Face Recognition using Self Organizing Map Based on Multi-Level Thresholding and Features Extraction

Facial recognition has played a very important role in security systems in recent decades. Various studies have been conducted to find a good method for this recognition to be effective. The facial recognition process in this study uses the self-organizing maps (SOM) method which is based on Multi-Level Thresholding segmentation and extraction of image features. The obtained face image will be segmented using Multi-Level Thresholding and the face will be generated without involving the background. The image that has been segmented will be calculated the values of texture feature extraction using GLCM and color feature extraction using HSV. The resulting image will be carried out by a training and testing process for facial recognition using the self-organizing map (SOM) method. The test results in the proposed study showed good results with an introduction rate of 78.44%. This percentage is higher than face recognition without a segmentation process with a recognition rate of 65.78%. This shows that the proposed method has better performance for the face recognition process without involving the segmentation process.

Utilization of SVM Method and Extraction of GLCM Features in Classifying Fish Images with Formalin

Purpose: Fish is a type of animal protein that can be consumed by humans to supplement protein in the body. Due to the fact that there is an abundance of fish in Indonesia, traders often experience losses because of rotting fish. A small proportion of traders tricked the buyers by mixing fish with formaldehyde to preserve fish in order to prevent fish spoilage until it can be consumed. Thus, every fish buyer must be aware of fraud by traders. Methods: To be able to find out that the fish has been mixed with formalin, the solution offered is computerized by utilizing the GLCM feature extraction as information extraction on the fish image and the SVM method as a classification method. Result : The results showed an average accuracy of 0.784, precision of 0.799, recall of 0.784, and f-measure of 0.781. Novelty : The effect of the SVM classification method on the performance measurement of the model is not too big compared to previous studies, but it is better. Â

Two-tier Grading System for NPDR Severities of Diabetic Retinopathy in Retinal Fundus Images

Background: Diabetic Retinopathy is the leading cause of vision impairment and its early stage diagnosis relies on regular monitoring and timely treatment for anomalies exhibiting subtle distinction among different severity grades. The existing Diabetic Retinopathy (DR) detection approaches are subjective, laborious and time consuming which can only be carried out by skilled professionals. All the patents related to DR detection and diagnoses applicable for our research problem were revised by the authors. The major limitation in classification of severities lies in poor discrimination between actual lesions, background noise and other anatomical structures. Methods: A robust and computationally efficient Two-Tier DR (2TDR) grading system is proposed in this paper to categorize various DR severities (mild, moderate and severe) present in retinal fundus images. In the proposed 2TDR grading system, input fundus image is subjected to background segmentation and the foreground fundus image is used for anomaly identification followed by GLCM feature extraction forming an image feature set. The novelty of our model lies in the exhaustive statistical analysis of extracted feature set to obtain optimal reduced image feature set employed further for classification. Results: Classification outcomes are obtained for both extracted as well as reduced feature set to validate the significance of statistical analysis in severity classification and grading. For single tier classification stage, the proposed system achieves an overall accuracy of 100% by k- Nearest Neighbour (kNN) and Artificial Neural Network (ANN) classifier. In second tier classification stage, an overall accuracy of 95.3% with kNN and 98.0% with ANN is achieved for all stages utilizing optimal reduced feature set. Conclusion:: 2TDR system demonstrates overall improvement in classification performance by 2% and 6% for kNN and ANN respectively after feature set reduction, and also outperforms the accuracy obtained by other state of the art methods when applied to the MESSIDOR dataset. This application oriented work aids in accurate DR classification for effective diagnosis and timely treatment of severe retinal ailment.

Feature Selection Using Artificial Bee Colony for Fruit Classification

Extraction of features plays a very significant part in the creation of images. Different image pre-processing methods such as banalization, thresholding, resizing, normalization are added to the captured picture before receiving functionality. After that, techniques of extraction of features are applied to obtain features that will be useful in the classification and recognition of images. This paper aims to propose a fruit classification system based on an Intelligence algorithm, the proposed framework derives extracted features using merge harries corner detection with GLCM feature extraction. After that, the important features are selected using one of the methods of artificial intelligence, where the bee colony algorithm was used. After obtaining the selected features, two powerful classifiers are merged, which are the decision tree and naïve Bayes to classify the input fruit image. This work uses the Fruit 360 dataset. Where 70 percent of the data set was used during the training phase and 30 percent used during the test phase. It was observed that the proposed approach yielded good results and the accuracy was 96 %.

Rice Leaf Disease Image Classifications Using KNN Based On GLCM Feature Extraction

The disease that often occurs in rice leaves which causes crop failure. At present the attack of pests or leaf diseases in countries where the majority of rice as the main food of the community, especially in Indonesia is increasing. Early detection mechanism to reduce the risk of crop failure is very necessary. Data mining classification methods for the past few years have been very popular to be used in detecting the classification of rice leaf disease. Our paper uses 120 images of rice leaf disease from the UCI repository. The purpose of this study was to determine how to classify images of rice leaf disease consisting of three diseases namely Bacterial leaf blight, Brown spot, and Leaf smut. The study proposes the GLCM method as feature extraction for text analysis, with five feature values consisting of contrast, energy, entropy, homogeneity, and correlation. KNN (K-Nearest Neighbor) algorithm is used for the classification of rice leaf disease, by finding the maximum k value from the experiment k value 1 to 20. The results of our experiments show that the value of k = 11 has the highest accuracy value compared to other k values of 65.83% and kappa 0.485.

Thermal imaging method in the evaluation of psoriasis in upper limb region

Psoriasis is a dermatological disorder that most often causes scaling, itching and lesions on various regions of the skin. This study aims to focus on just the upper limb region affected by psoriasis and perform image acquisition using thermographic imaging. Each and every bodily disorder has a unique heat signature and respective temperature differences. Similarly, Psoriasis also has a typical heat signature that can be clearly observed on performing automated segmentation of the thermal images. The aim of this study includes automated segmentation and GLCM feature extraction in order to understand the nature of the disorder from the thermal images, and to characterize it in a more precise manner. The segmentation algorithm used for the purpose of this study is the Fuzzy C-Means algorithm. Segmentation is performed in order to clearly characterize the region of interest (ROI). The skin temperature differences in the ROI between normal and psoriasis affected hand are important to evaluate the latter. The segmented images’ features have to be extracted in order to clearly visualize the unique aspects of Psoriasis which may not be understandable upon just clinical trials. The GLCM features are extracted using the respective algorithms. The mean average temperature difference between the normal and psoriasis was found to be 2.91°C. The percentage difference between the normal and psoriasis in measurement of average temperature was found to be 9.57%. Thermographic imaging is a non-contact method of image acquisition and is being extensively used in present day for medical study. This study will help understand Psoriasis in a more elaborate and clarified manner and aims to be used as diagnostic tool in the future.

Accurate Breast Cancer Prediction using Machine Learning Techniques

Applications of machine learning (ML) have been increasing widely in various fields like recommendation, fault identification and disease prediction. In ML, different algorithms were available and utilized in disease prediction such as heart disease prediction, cancer prediction and other forms disease prediction. In our proposed work, breast cancer prediction using ML has been implemented. Initially breast cancer images have been taken as input, preprocessing steps will be done to remove noisy and irrelevant data from image. Then 2D median filter is a nonlinear operation often used in image processing to reduce "salt and pepper" noise. To increase contrast of image contrast-limited adaptive histogram equalization is used. Segmentation has been implemented and GLCM feature extraction is deployed based on this information classification is implemented. For accurate classification Artificial neural network (ANN) is used to predict whether the patient is affected by breast cancer or not. Compared to other existing method our method predicts results in accurate way.

Improved Accuracy of Suspicious Activity Detection in Surveillance Video

Suspicious activity detection from surveillance video is the main objective of the work presented in this paper. The method developed consist of various stages of suspicious frame detection, and verifying the frame for suspicious activity related analysis of human movements within obtained set of suspicious frames. The method consist of GLCM feature extraction which constitutes the features such as energy, prominence, contrast, entropy, homogeneity type of features and matching using Euclidian distance along with descriptor features obtained by using Harris corner features and cosine similarity index estimation. The successful suspicious activity detection rate is analyzed which shows better performance and time saving method while analyzing large surveillance video dataset.

Texture Feature Extraction and Classification of Brain Neoplasm in MR Images using Machine Learning Techniques

Identification of pathology in brain such as tumor lesions is a tedious task. MRI is most of the time chosen medical imaging procedure that often pacts with lenient tissues such as brain tissues, tendons and ligaments. This study aims at texture feature extraction and segregation of brain tumor cases into benign and malignant conditions. The stages involved are segmentation, feature extraction and classification. K-means clustering method is preferred for segmentation and selecting the required region of interest. The textural information is captured from region of interest using GLCM, HOG and LBP patterns. ANN, SVM and k-NN classifiers are used to analyze performance accuracy in classifying the tumor data into benign and malignant conditions in brain MR images. ANN with LM training algorithm provides high accuracy with best performance compared to other two classifiers in identifying benign and malignant conditions of tumors by using a combination of GLCM, LBP and HOG feature extraction process successfully. The recommended method is compared with few current approaches in terms of feature extraction and classification.

Analysis of Detection of Drow and Entire Co-Occurrence Matrix GLCM Method on The Classification of Image

Grey level co-occurrence matrix or GLCM is a method for obtaining features of a textural image. On the previous study of GLCM, using only 4-degree degrees 0, 45, 90 and 135 in calculating the result of features. Periodicity, directionalityand randomness are the three most important factors in characterizing textures. Therefore, textural directionality is a basic feature of the image and plays an important role in image descriptions, which can be used to describe image textures. So this research will analyse the effect of modification of directionality or direction of adegree of texture distribution on GLCM by using 8 degree direction, which is degree 0, 45, 90, 135, 180, 225, 270, and 315 to know theeffect that impact on theimage by using support vector machine as aclassifier. The results showed that the SVM classifier was not able to work well on GLCM feature extraction, but the performance of the modification resulted in a consistent increase in accuracy by performing 10 tests.

The application of statistic image analysis for classification of breast cancer based on mammograms

Cancer is a disease characterized by the ability of abnormal cells to grow uncontrollably. In the medical field, detection of breast cancer is done using a mammogram. Examination of the mammogram image is still done manually by the doctor / radiologist, so it is necessary to use technology as supporting information. In this research, mammogram image classification based on gray-level co-occurrence (GLCM) matrix and gray-tone difference matrix (GTDM) has been done with backpropagation method. The stages of the mammogram image classification process include the process of image acquisition, pre-processing, feature extraction with GLCM and GTDM and classification using backpropagation. The preprocessing process carried out is gray-scalling, contrast enhancement, image segmentation with Otsu thresholding, edge detection process, and image thickening process with widening morphology method. The highest performance results for accuracy are 85% and precision is 85.7%. This result was obtained when using the GLCM and GTDM feature extraction methods.

A Clinical Support System for Brain Tumor Classification Using Soft Computing Techniques.

A brain tumor is an accumulation of abnormal cells in human brain. As tumor increases in size, it induces brain damage. Hence it is essential to diagnose the type of brain tumor. The effective modality used for brain tumor diagnose is MRI because of its remarkable image resolution, the speed of acquisition, and high safety profile for patients. The analysis of brain MRI is an important part of patient care and decision. Hence in the proposed Clinical Support System, the brain MRI image is preprocessed using Genetic Optimized Median Filter followed by brain tumor region segmentation using Hierarchical Fuzzy Clustering Algorithm. The features of the tumor region are extracted through GLCM feature extraction method. Lion Optimized Boosting Support Vector machine model is used for further classification of tumor by Brain Tumor Image Segmentation (BraTS) dataset. Hence the proposed clinical support system provides an integrated model for Detection and classification of brain tumor which assists the doctors in appropriate evaluation of tumor.

In-line grading system for mango fruits using GLCM feature extraction and soft-computing techniques

In the fruit production industries and supermarkets, mature (ripe) fruits are demanded for consumption by the consumers and also for production in fruit processing industries. Therefore, there is an urgent need for an in-line grading system in such industry to aid the grading of mango fruit; in order to enhance the use of ripe and mature mangoes for production. Also, such in-line grading systems will speed up the production in these industries since machines are faster which gives a better and standard result as compared with human operators. In this work, we have implemented an in-line grading system using GLCM feature extraction and soft computing techniques. Two models have been implemented to classify the mango fruits into mature (ripe) and immature (unripe) fruits. These models are the feed-forward network trained with back-propagation neural network and the radial basis function network. These models are compared with each other and also with the result of other proposed systems using the same database to ascertain the best result required in such industry.

In-line grading system for mango fruits using GLCM feature extraction and soft-computing techniques

In-line grading system for mango fruits using GLCM feature extraction and soft-computing techniques