An Automated Tiles Defect Detection

Mohan, V.; Kumar, S. Suresh

doi:10.5120/19234-0993

Cited by 1 publication

(1 citation statement)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Research conducted by Mohan and Kumar [15] regarding to automation for the crack of ceramic tiles defect detection uses Probabilistic Neural Network (PNN) method, and feature extraction using wavelet filters with cooccurrence features. Discrete Wavelet Transform represents decomposed signal into different sub band image, for Co-occurrence Matrix the factors of: Energy, Entropy, Contrast, Correlation and Homogeneity of GLCM are used.…”

Section: Literature Reviewmentioning

confidence: 99%

Design of Automation System for Ceramic Surface Quality Control Using Artificial Neural Network at Balai Besar Keramik

Lestari

Rachmat

Ibrahim

et al. 2019

Proceedings of the 2018 International Conference on Industrial Enterprise and System Engineering (IcoIESE 2018)

View full text Add to dashboard Cite

Indonesia ceramic tiles production is currently ranked between the fifth and sixth of the world, it shows that ceramic tiles is one of the largest commodities in Indonesia. So, ceramic quality becomes very important to be considered for it is used as one of the basic building materials. The existing ceramic testing system in Balai Besar Keramik is performed by the operator repeatedly. With the repetitive performances, they cause fatigue to operator that results in decreased work ability, so in the calibration and readings of measuring instruments an error occurs. To improve the accuracy level of quality control system to remain stable, it's necessary to create an intelligent device that can overcome errors that occur in the inspection process using human vision on the surfaces of defect detection of ceramic tiles that have a high level of system stability; therefore, it is required the automation system design of the image processing-based using Artificial Neural Network method with backpropagation algorithm. The process of system design is using automation design with 300 Lx light intensity, 50 cm of camera distance, based on Artificial Neural Network method with confusion matrix result obtaining accuracy rate of 96.9% for offline mode and 92.3% for realtime mode.

show abstract

Section: Literature Reviewmentioning

confidence: 99%