Defect Detection And Classification Of Mango's Surface Based On Computer Vision

Study on the real time fruit quality detection and classification is an attractive and prospective R&D subject for improving marketing competition and post harvesting value-added processing technology of fruit products. As China entering WTO, it becomes more and more urgent. While went without saying, there is great advantage substituting the computer vision for person vision to inspect the fruit quality automatically. The objectives of this research are contributed to develop method and technology for mango's surface defect detection and classification by computer vision.As mango's surface is velvet and it has preferable reflection, with black back-ground, the acquired images were studied. Based on the images from the digital camera, Several methods of lower-layer image processing technique were studied. Projection was adopted to fix on the image processing window. To eliminate all kinds of noise, at the same time, overcome the disadvantage of traditional filtering methods of color image, the vector median filtering was adopted to filter the mango image. The improved histogram pure-line transfer was put into effect in order to increasing image. Gray level histogram segment method was adopted to segment the mango from the background. The method of lower-layer image processing technique could satisfy the demand of defect detection and classification.Take into account of the brightness character in the defect region, the...