Font Size: a A A

Grain Recognition System Based On Image Classification

Posted on:2017-05-31Degree:MasterType:Thesis
Country:ChinaCandidate:D Q QianFull Text:PDF
GTID:2308330482981779Subject:Computer Science and Technology
Abstract/Summary:PDF Full Text Request
With the social progress and the improvement of people’s living level, people pay more and more attention to the improvement of the quality of life. However the Soybean Milk Machine still artificial put in cereal grains and water according to the experience. For lack of experience of the novice, the proportion of grain and water are hard to grasp. Comfortable, convenient and personal living condition is the eternal pursuit of people. People want Soybean Milk Machine to answer the proportion of grain and water to make delicious soybean milk.With the development of computer science, especially the development of computer vision, makes it possible to intelligent hardware based on vision. Grain recognition system based on Image processing can intelligently identify what is put in the soybean milk machine. According to the experience and knowledge of the diet, the machine gives us the optimum ratio of water and grain.According to the shape and color of the grain, this paper presents a grain localization method based on image segmentation, and based on this proposed grain recognition method based on image classification. The system is mainly divided into:grain detection module and grain recognition module. The main work of this paper is as follows:1. Research on the detection method of grain based on image segmentation.2. Research on the extraction method of the local feature, and the extraction of the feature of the color dense SIFT is mainly introduced.3. Study on the module of bag of features, BOF, sparse coding, and spatial pyramid matching. Combining with those to abstraction of image features.4. Study on the classifier of machine learning, and focuses on the application of support vector machine in grain recognition.
Keywords/Search Tags:Grain recognition, Color dense SIFT, Bag of features, Sparse Coding, SVM
PDF Full Text Request
Related items