Recognition of Defects in TOFD Image Based on HSV Black Color Histogram

Authors

  • Qi Yao School of Digital Economy, Changzhou College of Information Technology, Changzhou 213164, China
  • Dayang Jiang Information Center, Changzhou College of Information Technology, Changzhou 213164, China

Abstract

In this paper, a TOFD image defect recognition method based on HSV block color histogram is proposed to address the problems of poor image recognition accuracy and long recognition which are the shortcomings of current methods. The aim is to improve the accuracy of defect recognition in images. Depending on the difference in the shape and gray of various types of defects in the actual image, the average ratio of gray defect to background, the defect perimeter area ratio and the defect symmetry are selected as indicators of defects in TOFD images. The hyperspectral sensor is used to denoise the TOFD image with defect indicators to reduce the influence of noise on the accuracy of the defect-recognition result. According to the denoising result, an image defect recognition model is established based on the HSV block color histogram to obtain image defect information.
Experimental results show that the proposed method has higher recognition accuracy, shorter time and clearer defect features when applied to TOFD image defect recognition. The proposed method has certain effectiveness and superiority in image processing.

Keywords: HSV block color histogram, TOFD image, hyperspectral sensor, defect index, denoising

Cite As

Q. Yao, D. Jiang, "Recognition of Defects in TOFD Image Based on HSV Black Color Histogram",
vol. 30 no. 4, pp. 269-277, 2022.




Downloads

Published

2022-07-01

Issue

Vol. 30 No. 4 (2022): International Journal of Engineering Intelligent Systems

Section

General Submission

License

The submission of a paper implies that, if accepted for publication, it will not be published elsewhere in the same form, in any language, without the prior consent of the publisher. Before publication, authors are requested to assign copyright to CRL Publishing Ltd. This allows CRL to sanction photocopying, and to authorize the reprinting of issues or volumes according to demand. Authors' traditional rights will not be jeopardized by assigning Copyright in this way, as they retain the right to reuse the material following publication, and to veto third-party publication.