Determination of the varieties and characteristics of wheat seeds grown in Turkey using image processing techniques

摘要

Image processing has been applied to various process of agricultural industry in order to achieve fast and accurate operation. Applying image processing techniques to classify wheat seeds based on their varieties is also objective method in real time applications. Seed analysis and classification can provide additional knowledge in their production, seeds quality control and in impurities identification. Also, it is very important to confirm the variety of the wheat before planting. Because each variety needs its own condition for taking good yield. In this study, a method is proposed to identify the wheat varieties grown in Turkey by using image analysis techniques, with the motivation of developing a fully automatic grain type and variety identification system. The proposed method is based on texture analysis (Gray Level Co-occurence Matrix (GLCM) and Linear Binary Pattern (LBP) methods) and k-Nearest Neighbor type classifier.