||Bridge painting defects recognition using samplying plans and image processing techniques
||Chang L M, Chen P H, Abdelraziq Y
||Bridge painting inspection is a time-consuming work that relies on plenty of human visual efforts that are subjective, inefficient, and inaccurate. In order to shorten the inspection / evaluation time and increase the accuracy, two unbiased sampling plans and an automated recognition system were developed with the hope of standardizing and automating the inspection process. The system hybridizes image processing techniques and neural networks, which provide expert knowledge through training, to automatically diagnose the defects on an image. The developed recognition system can process vast number of images instantly and intelligently with simulated human expertise. The detection of rust areas is used to exemplify the recognition system.
|Year of publication:
Chang L M, Chen P H, Abdelraziq Y (2000).
Bridge painting defects recognition using samplying plans and image processing techniques. Construction Information Technology 2000. Taking the construction industry into the 21st century.; ISBN 9979-9174-3-1; Reykjavik, Iceland, June 28 - 30, 2000 (ISSN: 2706-6568),