Embedded bean classifying system based on image recognition technology

Abstract

The invention relates to an automatic classification technology of solid particles based on an image pattern recognition technology, belonging to the field of image processing technology, in particular to an embedded bean classifying system which can be used for progressively analyzing the composition of beans and classifying mixed beans with similar colors and is suitable for various common beans. The whole classifying system can be integrated in a limited small region through the embedded design to meet the strict restriction of bean processing devices such as bean milk machines on volume, thereby possibly realizing highly automatic machining processes of various beans in a same device.

Description

technical field [0001] The invention relates to an embedded bean classification system based on image recognition technology, which can be applied to various occasions of bean classification and processing, and belongs to the technical field of image processing. Background technique [0002] There are many kinds of beans, mainly broad beans, soybeans, mung beans, black beans, red beans, peas and so on. They are rich in nutritional value and medicinal value, rich in protein, fat, carbohydrates, and also contain A, B, D, E multivitamins and minerals such as calcium, phosphorus, and iron. With the improvement of people's living standards and the praise of green products, various bean products, including tofu, soy milk, bean curd, and soy milk, have been widely welcomed by consumers. [0003] Because different beans have different physical properties such as hardness, heat resistance, and scale, when processed into soybean products, some of them are relatively easy to process, ...

AI Technical Summary

Problems solved by technology

[0005] In the prior art, there is no image system dedicated to bean classification. The patent document with application number 200710146050.0 discloses a portable grain analyzer based on digital image processing technology. The document describes a grain analyzer based on PC control. Quality inspection system, the system is used for grain authenticity identification and quality inspection, which focuses on mechanical structure and does not involve specific image recognition algorithms; and the two patent documents with application numbers 200810112084.2 and 200810111705.5 are both used to identify rice , first collect the image, then use the adaptive threshold segmentation method to binarize the image, and finally count the area and scale of the bright and dark feature regions respectively. Although the algorithm is involved, it has no learning function and self-adjusting function, and can only be used for defects. Detection, cannot be used for classification, and industrial PC or notebook is used to complete the control, which is bulky and expensive

Images