Algorithm for digital recognition of digital instrument based on support vector machine

Algorithm for digital recognition of digital instruments based on support vector machine is proposed. First of all, digital instrument image was collected by the robot, which are preprocessed by de-noise and other operations. Secondly, extreme regions were used for coarse positioning which is the digital ROI region. In the ROI region, bilateral filtering and other preprocessing operations were used once again, and the former extreme region is combined with support vector machine to eliminate the error window, and the accurate positioning of the digital segmentation is achieved. Finally, the digital feature vectors are sent to the support vector machine classifier sequentially and the number of significant digits of the result is determined according to the first nonzero value, and the correct reading of the instrument is output. The experimental results show that the algorithm can realize the digital recognition of digital instrument. The algorithm has high accuracy and strong robustness, which provides technical support for full coverage of digital instrument in substation, and this method, is superior to MSER+SVM method, and the comprehensive accuracy rate reaches 98.34%.