المستخلص: |
This paper presents an automated bin level detection system using Gabor wavelets and gray level co-occurrence matrices (GLCM) a based on content-based image retrieval (CBIR). Parameters such as Euclidean, Bhattacharyya, Chisq, Cosine, and EMD distances were used to evaluate the CBIR system. The database consists of different bin images and is divided into five classes (low, medium, full, flow and overflow) with two bin sizes (120 L and 240 L). The features are extracted from both query images, and all the images in the database, the output of the query and the database images are compared using similarity distances. The result shows that the EMD similarity distance performs better than other distances in retrieving the top 20 images that are close to the query image. The performance of the automated bin level detection system using Gabor wavelets and GLCM with the CBIR system had high identification accuracy. The combination of the two techniques proved to be efficient and robust. Based on the results, this method has the potential to be used in solid waste bin level identification to provide a robust solution for solid waste bin level detection, monitoring and management.
|