Classification Based on Texture Analysis for Synthetic Hazy Image from Mount Kelud Haze Image Density

• Published in: ICEEIE 2023 - International Conference on Electrical, Electronics and Information Engineering
• Main Author: Nugroho F.; Basid P.M.S.A.; Arif Y.M.; Diah N.M.; Bahtiar F.S.; Nurhayati H.; Kurniawan F.; Priandani N.D.; Dermawan D.A.
• Format: Conference paper
• Language: English
• Published: Institute of Electrical and Electronics Engineers Inc. 2023
• Online Access: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85181072711&doi=10.1109%2fICEEIE59078.2023.10334845&partnerID=40&md5=3cc4f3498588f6342ea6a9b12bb1d2ee

This paper classifies the simulations of homogeneous synthetic images, heterogeneous synthetic hazy images, and original hazy images taken from CCTV (Close Circuit Television) of Mt. Kelud crater using the GLCM (Gray Level Co-Occurrence Matrix) method. The average feature values obtained using the GLCM (Gray Level Co-Occurrence Matrix) method are used to compare the similarity of gray feature values of the three and then classify thin, medium, and thick images. The results for classifying thin haze, medium haze, and thick haze on the homogeneous synthetic hazy image test data obtained an accuracy value of 50%, a precision value of 46%, and a sensitivity value of 65%. As for the classification of thin, medium, and thick fog on heterogeneous synthetic hazy images, test data obtained an accuracy value of 42%, a precision value of 32%, and a sensitivity value of 48%. © 2023 IEEE.