CBIR for an Automated Solid Waste Bin Level Detection System Using GLCM

• Published in: Visual Informatics: Sustaining Research and Innovations pp. 280 - 288
• Main Authors: Arebey, Maher, Hannan, M. A., Begum, R. A., Basri, Hassan
• Format: Book Chapter
• Language: English
• Published: Berlin, Heidelberg Springer Berlin Heidelberg 2011
• Series: Lecture Notes in Computer Science
• Subjects: CBIR; GLCM; Solid waste management; Visual Informatics
• ISBN: 3642251900; 9783642251900
• ISSN: 0302-9743; 1611-3349
• DOI: 10.1007/978-3-642-25191-7_27

Nowadays, as the amount of waste increases, the need of automated bin collection and level detection becomes more crucial. The paper present an automated bin level detection using gray level co-occurrence matrices (GLCM) based on content-based image retrieval (CBIR). Bhattacharyya and Euclidean distances were used to evaluate CBIR system. The database consisting of different bin images, the database is divided into five classes such as low, medium, full. Flow and overflow. The GLCM features are extracted from both query image and all the images in the database, the output of the query and database images are compared using the similarity distances Bhattacharyya and Euclidean distances. The result shows that Bhattacharyya performs better than Euclidean in retrieving the top 20 images that are close to the query image. The performance of the automated bin level detection system using GLCM and CBIR system reached 0.716. The combination between the two techniques proved to be efficient and robust.