An image-based sugar crystal classification and identification and crystallization quality control method

Abstract

The invention discloses an image-based sugar crystal classification identification and crystal quality control method, which belongs to the field of image recognition classification technology and industrial control system. Steps: 1) Under the cooperation of the light-giving device, the original sample image of sugar crystals is obtained from the microscopic camera device, the original sample image is preprocessed by image preprocessing technology, and the preprocessed image is segmented to obtain The region of interest of the sugar crystal sample image; 2) for the region of interest, extract the characteristic parameters of each sample image according to the given identification features and use it to train the parallel multi-classifier; 3) set the control period to One control cycle is used as a unit, and the image to be classified is obtained within the cycle, and after preprocessing, the trained parallel multi-classifier is used to classify, and the crystallization state information of the sugar crystal is calculated according to the classification result; 4) The action of the actuator is controlled according to the crystallization state information . The method can realize the automation of the boiling sugar crystallization process as a whole.

Description

technical field [0001] The invention relates to an image recognition and classification technology and an industrial control system, in particular to a multi-classifier for sugar crystal images, a method and device for classifying sugar crystal images by using the multi-classifier, and a control method for controlling the quality of sugar crystals by using the recognition and classification results. Background technique [0002] In industry, the boiled sugar crystallization process requires the operator to constantly observe the condition of the grains in the tank in order to take corresponding actions. At present, most sugar factories use sampling probes to take out massecuite samples and observe them under the lamp or twist them by hand to judge by feeling. They cannot directly observe the changes of grains in the tank, which brings certain difficulties to the accuracy of the operation. In order to solve this problem, people have developed and developed a sugar cooking mic...

AI Technical Summary

Problems solved by technology

[0004] The automatic identification and classification of sugar crystals is an important part of the automation of the sugar cooking process. The results obtained by it are the decision-making basis for the subsequent control system. Without accurate identification and classification results, the automation of the sugar cooking process cannot be realized.

Images