| Study on the real time fruit quality detection by computer vision is an attractive and prospective subject for improving marketing competition and post harvesting value-added processing technology of fruit products. However, the farm produce with different varieties and different quality have cause tremendous losses in economy due to lacking the post-harvest inspecting standards and measures in China, and this problem will become more grave with China entering the WTO. It aims at solving the problems, such as fast processing the large amount of image information, improving system performance for real time dynamic image capture and processing capability, increasing precision of detection and on line grading system establishment, etc. The inspection items for fruit external quality involve size, shape, color and surface defects. The results of study are briefly summarized as follows:(1) Some fast image preprocessing methods suitable for on-line pear automatic grading including image smoothing, enhancement, edge detection, segmentation method were determined through investigations and experiments. Template analysis was introduced to edge detection, the image area detected with this method is only equal to half of traditional way, but the processing speed can be doubled.(2) Based on correlative theory a fast and effective shape judgement method and a size calculating method have been developed. The shape was graded by artificial neural network.(3) The color was graded by RGB, HIS. Real-time fruit surface defect inspection and recognition is still a challenging subject due to its complexity. A novel defect segmentation algorithm was developed. A BP neural network is designed for identifying fruit defect area and stem, calyx concave area.(4) Using LabWindows/CVI6.0, The hardware system can perform fruits transportation and dynamic image capture function; the software can be used for on line fruit grading by size, shape, color and surface defects.
|
PDF Full Text Request