Feature extraction using Hough transform for solid waste bin level detection and classification

M. A. Hannan, W. A. Zaila, M. Arebey, R. A. Begum, H. Basri

Research output: Contribution to journalArticle

4 Citations (Scopus)


This paper deals with the solid waste image detection and classification to detect and classify the solid waste bin level. To do so, Hough transform techniques is used for feature extraction to identify the line detection based on image's gradient field. The feedforward neural network (FFNN) model is used to classify the level content of solid waste based on learning concept. Numbers of training have been performed using FFNN to learn and match the targets of the testing images to compute the sum squared error with the performance goal met. The images for each class are used as input samples for classification. Result from the neural network and the rules decision are used to build the receiver operating characteristic (ROC) graph. Decision graph shows the performance of the system waste system based on area under curve (AUC), WS-class reached 0.9875 for excellent result and WS-grade reached 0.8293 for good result. The system has been successfully designated with the motivation of solid waste bin monitoring system that can applied to a wide variety of local municipal authorities system. © 2014 Springer International Publishing.
Original languageEnglish
Pages (from-to)5381-5391
Number of pages4841
JournalEnvironmental Monitoring and Assessment
Publication statusPublished - 01 Jan 2014
Externally publishedYes

Fingerprint Dive into the research topics of 'Feature extraction using Hough transform for solid waste bin level detection and classification'. Together they form a unique fingerprint.

  • Cite this