Chromatic aberration histogram and DAG-SVMs-based photovoltaic battery piece color classification algorithm

Abstract

The invention discloses a chromatic aberration histogram and DAG-SVMs-based photovoltaic battery piece color classification algorithm. According to the invention, after an acquired original image is preprocessed, a target image is obtained; the target image is subjected to color space conversion, and then the color information of the image of a photovoltaic battery piece is accurately extracted; meanwhile, the calculation amount is simplified and the image dimension quantization is carried out; the feature vector of the image is obtained through the calculation of a color difference histogram,so that an image feature information library is built. In this way, the training and the learning are carried out, and the DAG-SVMs classification is carried out by means of a support vector machineclassifier based on six types of sample classification. As a result, the color classification of photovoltaic battery pieces is realized. The algorithm improves the traditional support vector method which can only solve the dichotomy problem in the prior art, wherein the provided algorithm can solve the DAG-SVMs algorithm of the k classification problem. Therefore, the classification of six typesof colors of photovoltaic battery pieces can be realized. The algorithm is strong in application performance and high in classification accuracy.

Description

technical field [0001] The invention relates to the technical field of photovoltaic cell manufacturing, in particular to a photovoltaic cell color classification algorithm based on color difference histograms and DAG-SVMs. Background technique [0002] In the context of increasingly serious environmental problems and dwindling energy sources, the development of new energy industries is crucial. As the main force of the new energy industry, the photovoltaic cell industry is developing extremely rapidly. As a big country in photovoltaic production and manufacturing, my country has formed a relatively complete photovoltaic industry chain. While new technologies and products are constantly emerging, the quality requirements for photovoltaic cells and photovoltaic modules are also constantly improving. Among them, the difference in the color of the cells due to the production process of the photovoltaic cells is called the color difference of the cells in the industry. At this...

AI Technical Summary

Problems solved by technology

At this stage, the color classification of photovoltaic cells in China mainly relies on human eyes for recognition, and the efficiency and accuracy of classification are low

Images