Defect Image Test Technology And Application Of Defects Detection

In the process of industrial products manufacturing, the surface defect detection of the product has been occupying the main position of product quality detection. Because of raw materials, manufacturing equipment and the process technology problem and other causes, surface defects of the product not only affect the appearance of products, but also they are likely to reduce the quality of the products. Feather was the main raw material in the production of shuttlecock, the strength of shuttlecock depends directly on the intensity of quill in the feather, but the scratches affect the quill’s intensity. The quill’s scratches defect will not only make the appearance unbeautiful, but also make the quill easy to broken off, and affect the strength. Therefore, the quill’s scratch defect is the important factor to affect the quality. The paper use image processing technology to realize the automatic detection of the quill’s scratch. It has vital actual meaning and economic efficiency.The scratches on quill mainly present tiny size, the small color contrast between scratch and surrounding tissues, and extremely easily disturbed by the edge noise of quill. After obtaining reliable feather image information in the feather image collection platform, this paper separately adopt wavelet transform and ridgelet transform to detect quill’s scratches, mainly solved the following questions:1. According to the characteristics of quill’s scratches, it is better to detect feather pole scratches under both of positive light and side light. This paper chooses the appropriate camera and the lighting source, and establishes scratch test platform under both of positive light and side light and gain scratches obvious being testing images.2. Anglicizing the characteristics of quill’s scratches, this paper selects the convolution method for image preprocessing to eliminate the edge noise of feather pole and separately adopt wavelet transform and ridgelet transform to detect feather pole scratches, and finally use the OSTU method to segment images that transformed by wavelet transform and ridgelet transform. By this method, we achieved a clear binary image.3. Because of the size characteristic of the quill’s scratches and avoiding the serious wrong judgment, this paper analyzes and researches the quill’s scratches images that obtained under both of positive light and side light, and judges the scratches by comminuting scratches features in different images, on the basis of principle and method of multi-source image information fusion, experiments indicate this method is better than a single image with defect, and further reduce the misjudgment of the scratch defects.4. According to images information after threshold segmentation, the paper get scratches features emerges, summary scratches features, and put forward on the judgment of the feather pole scratches. The paper completes all the arithmetic through using the software of Matlab, the software deals with the images of quill’s scratch defects and gets the result of emulator analysis. The last method has been decided and the good effect has acquired from the research of many kinds of method and the influence of all the data. It has some practical value.