The invention discloses a machine vision-based method for detecting and sorting polycrystalline silicon solar energy. The method comprises the following steps of: 1) allowing a polycrystalline silicon solar cell to pass through an image acquisition area, and acquiring a corresponding image through a charge coupled device (CCD) camera; 2) performing image preprocessing on the acquired image, wherein the image preprocessing comprises image extraction, gray processing, image noise filtering, image enhancement, edge detection and solar cell positioning; and 3) performing image recognition, comparing the parameters of the polycrystalline silicon solar cell acquired in the step 2) with a template, performing image similarity measurement, performing color classification to sort the colors. The grey level histogram of the polycrystalline silicon solar cell is analyzed and is compared with a standard sample image for calculation to obtain the standard deviation of the histogram distribution, and a classification decision is made through the obtained standard deviation. Through the proving of the experiment proves, the method has the advantages that the detection speed is high and the accuracy is high and the detection requirements can be met.