Study On The Computer Vision System Of YAPEAR Quality Testing And Grading

YAPEAR, a specialty in heibei province, and is primary export fruit. Quality grading of fruit is an important item in post-harvest handling and marking. In our country the grading is still mainly depends on manual grading, and it has many defects such as: inconsistency, inefficiency and subjection, which result in the pear bad quality. Therefore an automatic grading system is required urgently.The research of fruit grading has been developing greatly influenced by the development of image processing and computer vision technique. YAPEAR grading was studied based on computer vision technique. A hardware and software system for YAPEAR grading was developed. In view of size, shape and coloring, four features ware selected. They represent the appearance feature of YAPEAR adequately. The four features are the max horizontal diameter, the radio of fruit shape, the head of pear and coloring. Through the calculating on multiplayer feedforward neural networks with BP, YAPEAR get three grading, AA, A and substandard fruit, based on this four features.The whole grading system includes: image acquirement, preprocess, character pick-up and grading.A hardware system used to acquire image includes: Person Computer, PCI/PXI-1411 EVIAQ from NI company and a homemade light-box. Panasonic WV-CP240/G camera, annular incandescence lamp 40W and elevator ware set up in light-box. White lacquer was spread in the walls of light-box. In experiment, under the black background, 3 images of each pear ware acquired from different angle (interval 120 degree).After considering the actual status and the process effect, the following methods ware determined at last: transformation, image enhancement, median filter, segmentation, edge detection, etc. To acquire image without pear's stem is a trait. The method: firstly, to acquire the whole image of pear and the image of stem by threshold method. Secondly, do the operation of subtracting between the two images to get the image without pear's stem.The method of character pick-up: The max horizontal diameter of pear, and the radio of fruit shape ware extracted though the method of mini-circum-rectangle. The feature of YAPEAR' head was acquired by the method of template matching. Select the excellent head of pear as a template, compare the others with the template. Take...