Study of On-line Paper Defect Inspection Method Based on Visual Attention Model

摘要

Due to massive information and a high density of noise included in on-line web inspection detection system, a on-line paper defect Inspection method based on visual attention model is presented in this paper. Firstly, low-level of image feature at different scales are analyzed in the frequency domain. Then some corresponding salient maps are constructed, and combined into a salient image with normalization and linear-fusion in the spatial domain. Secondly, one viewpoints is found and used as the seed point for region growing in the image. After region growing, a paper defect region is extracted from background according to some rules. At last geometrical features and gray features of defect region are extracted, and imported into neural network for classifying paper defects. The experimental results showed that the method had high identification rate, and performed well even in on-line paper images with a high density of noise.