关键词: 带钢, 表面缺陷, 人工免疫系统, 检测器分块, 三维恢复

Abstract: The traditional algorithms of surface defects detection for steel strips cannot achieve expected results because of the image noises, and inadequate or uneven illumination. To address this issue, a new method based on artificial immune system was proposed. According to the spatial inclusion relationship between detector and antigen, as well as self location information in domain, block-based detector generating algorithm was introduced to obtain the height information of surface defects for steel strips through three-dimensional recovery of their gray-level images, thus the three-dimensional quality of surface defects detection for steel strips was achieved. The experimental results show that the proposed method has an excellent effect compared with the traditional image detection algorithm in the condition of low contrast ratio uneven illumination or noise interference.

Key words: steel strip, surface defect, artificial immune system, block-based detector, three-dimensional recovery