Study On Melon External Quality Inspection Based On Computer Vision

Improving agricultural production efficiency and automaticity is a basic way which achieves modern agricultural production, basing on agricultural foundation position in our country. In recent years, the automatic of quality-rating fruits have been of wider application, however the techniques of the automatic quality-rating system still have big problems. The quality-rating system of Melons which are commonly seen on the market or in the fruit trade of import and export always refer to external quality of shape, size, colour and surface defects. This research aims to research melon goity and visual type of identification algorithm using the computer images recognition technology to lay the foundation of automatically detected quality-rating system.Accurate detection and segmentation of the pedicels are important tasks in a melon quality-rating system which is based on image processing. It presents a novel method of detecting the pedicels and erasing them in the melon images. The corners of a melon image are extracted firstly, and most of them distributes in the pedicel. Utilizing this feature, the pedicels exactly and erase them easily can be detected. The proposed method is not sensitive to variations of their shape, length, thickness of pedicels, and thus is adaptable. The experimental results show that, compared with the several existing approaches, the accuracy of the proposed method is improved and the average time cost is reduced.In order to improve the accuracy of muskmelon's defect detection, adopting complex features of texture and color, we construct an automatic defect detection system based on support vector machine (SVM). Four textural parameters and twelve color features of combinations from RGB are tested for their discriminability in stem, calyx, bruise and mildew. Through the experiments, two textural and four color features with good discriminability are selected and treated as the complex features. The results indicate that with the complex features and SVM, the accuracy of classification on the muskmelons is up to 92.2%.The paper achieves above algorithm and a simple melon quality-rating experiment system at MATLAB7.0.