Filters








4,719 Hits in 6.2 sec

Boosting Texture-Based Classification by Describing Statistical Information of Gray-Levels Differences

Óscar García-Olalla, Laura Fernández-Robles, Enrique Alegre, Manuel Castejón-Limas, Eduardo Fidalgo
2019 Sensors  
Our proposal uses the statistical information of the texture provided by the image gray-levels differences to increase the discriminative capability of Local Binary Patterns (LBP)-based and other texture  ...  This paper presents a new texture descriptor booster, Complete Local Oriented Statistical Information Booster (CLOSIB), based on statistical information of the image.  ...  Conclusions We proposed a new texture descriptor booster, called CLOSIB, which is based on the statistical information provided by the gray-level differences of the image.  ... 
doi:10.3390/s19051048 fatcat:drjtfrtjdjfy5hpd7dswgnholm

Cascading feature filtering and boosting algorithm for plant type classification based on image features

Adel Bakhshipour
2021 IEEE Access  
GRAY LEVEL RUN LENGTH MATRIX (GLRLM) TEXTURE FEATURES In order to acquire more insight into the plant leaf texture information, the GLRLM based texture features were also extracted and analyzed in this  ...  GLRLM based texture features including Short Run Emphasis (SRE), Long Run Emphasis (LRE), Gray-Level Non-Uniformity (GLN), Run Length Non-Uniformity (RLN), Run Percentage (RP), Low Gray-Level Run Emphasis  ... 
doi:10.1109/access.2021.3086269 fatcat:rqh6i233qvdm3cd5jmqe4dnsou

Magnetic resonance imaging study of gray matter in schizophrenia based on XGBoost

2018 Journal of Integrative Neuroscience  
Grey-level co-occurrence matrix texture features from the previously processed gray matter images of structural magnetic resonance imaging are then extracted and normalized.  ...  This suggests that the textural features of gray matter changes may be of diagnostic value in schizophrenia.  ...  Acknowledgments This work is supported by the Natural Science Foundation of China Conflict of Interest All authors declare no conflict of interest.  ... 
doi:10.31083/j.jin.2018.04.0410 fatcat:xbk3c7s2yzgv5hhkpnwjbdpstm

Explainable Ensemble Machine Learning for Breast Cancer Diagnosis based on Ultrasound Image Texture Features [article]

Alireza Rezazadeh, Yasamin Jafarian, Ali Kord
2022 arXiv   pre-print
Each decision tree learns to classify the input ultrasound image by learning a set of robust decision thresholds for texture features of the image.  ...  In this paper, we address this issue by proposing an explainable machine learning pipeline for breast cancer diagnosis based on ultrasound images.  ...  First-Order Statistics Texture Features First-order texture features are computed based on first-order statistics of the one-dimensional gray level histogram of the image.  ... 
arXiv:2201.07227v1 fatcat:2epaobcuvvdengsnbxys2vjjp4

Explainable Ensemble Machine Learning for Breast Cancer Diagnosis Based on Ultrasound Image Texture Features

Alireza Rezazadeh, Yasamin Jafarian, Ali Kord
2022 Forecasting  
Each decision tree learns to classify the input ultrasound image by learning a set of robust decision thresholds for texture features of the image.  ...  In this paper, we address this issue by proposing an explainable machine learning pipeline for breast cancer diagnosis based on ultrasound images.  ...  First-Order Statistics' Texture Features First-order texture features are computed based on first-order statistics of the onedimensional gray level histogram of the image.  ... 
doi:10.3390/forecast4010015 fatcat:2lskzez7znbvdinjktr7hov4qe

Machine Learning Based Statistical Analysis of Emotion Recognition using Facial Expression

Aqib Ali, Jamal Abdul Nasir, Muhammad Munawar Ahmed, Samreen Naeem, Sania Anam, Farrukh Jamal, Christophe Chesneau, Muhammad Zubair, Muhammad Saqib Anees
2020 RADS Journal of Biological Research & Applied Science  
In the second step, 3 types of statistical features named texture, histogram, and binary feature are extracted from each ROIs.  ...  In the first step, all images are converted into a gray level format and 4 Regions of Interest (ROIs) are created on each image, so the total image dataset gets divided in 2400 (600 x 4) sub-images.  ...  Here, N is a Total Pixel and the Gray Level of K(h) has a Total Pixel.  ... 
doi:10.37962/jbas.v11i1.262 fatcat:on4auklrqjeglo3toqhuzy4hzu

Comparative Analysis on Scene Image Classification using Selected Hybrid Features

Madhu BalaMyneni, M. Seetha
2013 International Journal of Computer Applications  
The features are extracted in three ways; conventional feature extraction methods like gray level co-occurrence matrices features & statistical moment's features; hybrid feature extraction is the combination  ...  A comparative analysis on image classification is accomplished on scene image feature set by using various existing classifiers.  ...  CONVENTIONAL FEATURE EXTRACTION METHODS The texture features are extracted by using Gray Level Co-Occurrence Matrix (GLCM) Features and Histogram based statistical moments.  ... 
doi:10.5120/10442-5130 fatcat:nflethpna5c2vg7dg7bjubouwy

A Novel Bio-Inspired Texture Descriptor based on Biodiversity and Taxonomic Measures [article]

Steve Tsham Mpinda Ataky, Alessandro Lameiras Koerich
2021 arXiv   pre-print
Texture can be defined as the change of image intensity that forms repetitive patterns, resulting from physical properties of the object's roughness or differences in a reflection on the surface.  ...  The proposed approach considers each image channel as a species ecosystem and computes species diversity and richness measures as well as taxonomic measures to describe the texture.  ...  gradient boosting ensembles of decision trees (HistoB), light gradient boosting decision trees (LightB), and super learner (SuperL) [54], which involves the selection of different base classifiers and  ... 
arXiv:2102.06997v3 fatcat:clm6ywpnnjfhfcr26oebnzmvcm

The Diagnostic Value of Radiomics-Based Machine Learning in Predicting the Grade of Meningiomas Using Conventional Magnetic Resonance Imaging: A Preliminary Study

Chaoyue Chen, Xinyi Guo, Jian Wang, Wen Guo, Xuelei Ma, Jianguo Xu
2019 Frontiers in Oncology  
Objective: The purpose of the current study is to investigate whether texture analysis-based machine learning algorithms could help devise a non-invasive imaging biomarker for accurate classification of  ...  A total number of 40 texture parameters were extracted from pretreatment postcontrast T1-weighted (T1C) images based on six matrixes.  ...  Forty quantified texture features were extracted, including features from histogram-based matrix and shape-based matrix from the first order and features from gray-level co-occurrence matrix (GLCM), gray-level  ... 
doi:10.3389/fonc.2019.01338 pmid:31867272 pmcid:PMC6908490 fatcat:n4yadxhi4jd2tkxrl75qe7rnaq

A Statistical Approach of Texton Based Texture Classification Using LPboosting Classifier

C. Vivek, S. Audithan
2014 Research Journal of Applied Sciences Engineering and Technology  
The entropy lineage parameters of redundant and interpolate at a certain point which congregating adjacent regions based on geometric properties then the classification is apprehended by comparing the  ...  We show that the resulted texture features while incurring the maximum of the discriminative information.  ...  Feature extraction method consists of gray level co-occurrence matrix and GMRF features. The classification is done by using Support Vector Machine (SVM).  ... 
doi:10.19026/rjaset.7.771 fatcat:7mcachjurjacfmetvni4nfhyua

Intravascular Ultrasound Images Vessel Characterization Using AdaBoost [chapter]

Oriol Pujol, Misael Rosales, Petia Radeva, Eduard Nofrerias-Fernández
2003 Lecture Notes in Computer Science  
Nowadays, the most common methods to separate the tissue from the lumen are based on gray levels providing non-satisfactory segmentations.  ...  This paper presents a method for accurate location of the vessel borders based on boosting of classifiers and feature selection.  ...  Acknowledgements This work was partially supported by the project TIC2000-1635-C04-04 of CI-CYT, Ministerio de Ciencia y Tecnologa of Spain.  ... 
doi:10.1007/3-540-44883-7_25 fatcat:6hhtv2x4wrfvtmq3berstm3ppu

Fish Image Classification by XgBoost Based on Gist and GLCM Features

Prashengit Dhar, Cox's Bazar City College, Bangladesh, Sunanda Guha
2021 International Journal of Information Technology and Computer Science  
This paper presents a fish image classification method with the robust Gist feature and Gray Level Co-occurrence Matrix (GLCM) feature.  ...  Classification is made on ten types of raw images of fish from two datasets -QUT and F4K dataset. The feature set is trained with different machine learning models.  ...  Gist feature extraction method GLCM-Gray Level Co-occurrence Matrix Statistical texture features are determined by observing the statistical distribution of image pixels combination in a particular position  ... 
doi:10.5815/ijitcs.2021.04.02 fatcat:iwurtsvidfdfrecouoaz46qrde

Magnetic resonance imaging (MRI)-based radiomics for prostate cancer radiotherapy

Fei Yang, John C. Ford, Nesrin Dogan, Kyle R. Padgett, Adrian L. Breto, Matthew C. Abramowitz, Alan Dal Pra, Alan Pollack, Radka Stoyanova
2018 Translational Andrology and Urology  
information.  ...  targets for radiation boost.  ...  Higher order statistical features consist of various textural parameters derived based on different encoding schemes including gray-level co-occurrence matrices (GLCOM), gray-level neighborhood difference  ... 
doi:10.21037/tau.2018.06.05 pmid:30050803 pmcid:PMC6043736 fatcat:22h5rn2rings7jmnh2v3fdiekm

Evaluation of Adaptive Boosting and Neural Network in Earthquake Damage Levels Detection

Mona PeykHerfeh, Asadollah Shahbahrami
2014 International Journal of Computer Applications  
When an earthquake happens, the image-based techniques are influential tools for detection and classification of damaged buildings.  ...  For classification, adaptive boosting and neural networks are utilized and compared with each other.  ...  First Statistical Features: In texture analysis, features such as mean, median, entropy, variance of gray value are utilized as 1st statistical textural feature.  ... 
doi:10.5120/17507-8058 fatcat:7h3tf36j65eyncijvqnx4hg7vm

MRI Texture Analysis for Differentiation Between Healthy and Golden Retriever Muscular Dystrophy Dogs at Different Phases of Disease Evolution [chapter]

Dorota Duda, Marek Kretowski, Noura Azzabou, Jacques D. de Certaines
2015 Lecture Notes in Computer Science  
This work was performed under the auspices of the European COST Action BM1304, MYO-MRI. It was also supported by grant S/WI/2/2013 from the Bialystok University of Technology, Bialystok, Poland.  ...  Texture features, based on the gray-level histogram and run length matrices, were calculated from T2-weighted images.  ...  The aim of this study is to assess the potential of various MRI texture analysis techniques (statistical, model-based, and filter-based) for characterization of different types of muscles in canine pelvic  ... 
doi:10.1007/978-3-319-24369-6_21 fatcat:inryywtxkfaphd6zakiwcsx7xy
« Previous Showing results 1 — 15 out of 4,719 results