A benchmarking: Feature extraction and classification of agricultural textures using LBP, GLCM, RBO, Neural Networks, k-NN, and random forest

Sercan Aygun, Ece Olcay Gunes

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

7 Citations (Scopus)

Abstract

Agricultural textures are in the interest of classification in image processing. Natural images have unique textural shapes inside which cause a tough problem for classification. This paper tests different feature extraction and classification approaches to serve a benchmarking on several agricultural databases like seeds and leaves. Features are obtained using Local Binary Pattern (LBP), Gray Level Co-Occurrence Matrix (GLCM), and Relational Bit Operator (RBO) independently. Classification is done by Neural Networks, k-nearest neighbor method, and random forest independently, too. LBP counts several binary patterns that occur in the image. GLCM is a kind of statistical approach that uses homogeneity, contrast, energy, and correlation information from pixels. RBO counts the binary relations of neighboring pixels in a box filter to get textural features for image processing. The leading test results are obtained from the LBP method for features and random forest data structure for classification. For example, agricultural seed type classification is obtained with LBP features and random forest classification with an accuracy of 99.5% and leaf classification with 93.5% accuracy. Following sections in the paper start with an introduction and continue with literature review, methods and materials, test results and conclusion.

Original languageEnglish
Title of host publication2017 6th International Conference on Agro-Geoinformatics, Agro-Geoinformatics 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781538638842
DOIs
Publication statusPublished - 19 Sept 2017
Event6th International Conference on Agro-Geoinformatics, Agro-Geoinformatics 2017 - Fairfax, United States
Duration: 7 Aug 201710 Aug 2017

Publication series

Name2017 6th International Conference on Agro-Geoinformatics, Agro-Geoinformatics 2017

Conference

Conference6th International Conference on Agro-Geoinformatics, Agro-Geoinformatics 2017
Country/TerritoryUnited States
CityFairfax
Period7/08/1710/08/17

Bibliographical note

Publisher Copyright:
© 2017 IEEE.

Funding

ACKNOWLEDGMENT This research was funded by T.R. Ministry of Food, Agriculture and Livestock, I.T.U. TARBIL Environmental Agriculture Informatics Applied Research Center. The special thanks also for the YÕldÕz Technical University for their procedural and official allowance for the conference attendance of author Sercan Aygün. To whom the database can be needed to download should contact the authors to reach the cloud link.

FundersFunder number
TARBIL Environmental Agriculture Informatics Applied Research Center
Ministry of Food, Agricultural and Livestock

    Keywords

    • agricultural textures
    • benchmarking
    • classification
    • computer vision
    • feature extraction
    • GLCM
    • k-NN
    • LBP
    • neural networks
    • random forest
    • RBO

    Fingerprint

    Dive into the research topics of 'A benchmarking: Feature extraction and classification of agricultural textures using LBP, GLCM, RBO, Neural Networks, k-NN, and random forest'. Together they form a unique fingerprint.

    Cite this