AI intelligent identification method for numbers of water meter

Abstract

The invention relates to an AI intelligent identification method for numbers of a water meter. The AI intelligent identification method adopts Darknet-19 as a basic network, and is realized based on YOLOv2: numbers in each box in a data source-data annotation and format conversion-creation.Names file-creation.data file-modification.Cfg configuration file-training model-testing model-model is presented on a use interface in a continuous Arabic number combination form. According to the image identification and detection method, water meter number identification is achieved based on YOLOv2, and Darknet-19 is adopted as a basic network, so that the effect is improved without deepening or widening the network while the network is simplified, and obvious advantages are achieved in the aspects ofthe recall rate and positioning; and the precision is high, and finally the numbers can be presented on the use interface in a continuous Arabic numeral combination mode, and complete artificial intelligence is achieved, and a user does not need to analyze and guess, so that the AI intelligent identification method is visual and convenient.

Description

technical field [0001] The invention relates to the technical fields of pattern recognition and artificial intelligence, in particular to an intuitive AI intelligent recognition method for water meter numbers. Background technique [0002] The application of deep learning in target detection has developed rapidly. After YOLO (You Only Look Once), an upgraded version of YOLOv2 appeared, using Darknet-19 as the basic network. It does not improve the effect by deepening or widening the network, but instead The network is simplified, and it has obvious advantages in both recall rate and positioning. Our water meter digital recognition is based on YOLOv2. [0003] At present, there are many technologies involving the combination of pattern recognition and artificial intelligence, especially applied to image data detection. The main detection and analysis process of image data detection based on YOLO in the prior art is based on the identification and analysis of pictures, and th...

AI Technical Summary

Problems solved by technology

The main detection and analysis process of image data detection based on YOLO in the prior art is based on the identification and analysis of pictures, and the final analysis result is a picture with an accuracy rate, which requires the user to make a judgment based on the accuracy rate , or what is presented to the user is the most accurate picture analyzed by the system, which requires the user to analyze the picture, not only cannot fully realize the intelligent recognition, but also the process of recognition and detection is cumbersome and complicated, and will gradually be replaced by the new network , cannot meet the needs of network upgrades

Images