BP neural network-based steel seal character recognition method

Abstract

The invention discloses a BP neural network-based steel seal character recognition method, which belongs to the technical field of image recognition. The method comprises the following steps of: photographing a workpiece steel seal through an industrial camera arranged in an industrial field, and acquiring an image; performing threshold segmentation on the image through a machine learning clustering algorithm. A good segmentation effect is achieved; the problem that features and character backgrounds cannot be accurately segmented through traditional single threshold segmentation for steel seal pictures is solved. Meanwhile, a clustering algorithm is applied to character segmentation, automatic segmentation of characters in the image is achieved, normalization processing of the image solves the problem that the size of the image is changed due to the fact that position deviation possibly exists in the moving process of the workpiece, and the accuracy of steel seal recognition is improved; meanwhile, training of the steel seal recognition model is achieved through the neural network, and the model has a good effect in a test set.

Description

technical field [0001] The invention belongs to the technical field of image recognition, and in particular relates to a steel stamp character recognition method based on a BP neural network. Background technique [0002] In recent years, due to the rapid development of computer technology and sensor technology, traditional factories have gradually developed in the direction of intelligence and unmanned. However, during the processing of large castings and aluminum parts, the surface of the workpiece The temperature can reach hundreds of degrees Celsius, so it cannot be automatically identified by traditional RFID (such as two-dimensional codes, sensors, etc.) In some cases, there will be problems such as slow input speed and incorrect input results. Therefore, in order to realize the intelligent upgrading of the factory and solve the problems existing in the automatic identification of factory materials, an image recognition technology is urgently needed to realize the auto...

AI Technical Summary

Problems solved by technology

[0004] In view of the poor image threshold segmentation effect in the image feature extraction in the prior art, there are problems such as noise after image segmentation, the object of the present invention is to provide a kind of steel seal character recognition method based on BP neural network, the inventive method in the image segmentation processing part Starting from the sample size, the clustering algorithm is used to divide the samples into several groups (the number should be determined according to the actual situation), and the ratio of the number of samples in the group to the total number of samples is used to divide them into character areas and background areas to realize image segmentation. Segmentation, realizes the accurate segmentation of images under the conditions of uneven illumination and similar characters and backgrounds for stamp recognition, and applies connected domain size discrimination to image noise points that may exist after image segmentation to identify character areas and noise areas, and then realizes The removal of noise, and then use the clustering algorithm to divide the picture into a single character, after normalization, as the input of the neural network to obtain the corresponding neural network recognition model, compared with the traditional character recognition technology, the image in this method The segmentation algorithm realizes the segmentation of image characters and background regions through the proportion of sample volume instead of traditional single threshold or multi-threshold methods, which overcomes the inability of traditional single-threshold or multi-threshold methods to be accurate under the conditions of uneven illumination and similar characteristics of character regions and background regions. At the same time, the step of removing noise points after image segmentation is added, which enhances the robustness of algorithm recognition. Its actual recognition effect is good and the recognition speed is fast, and it has the conditions for application in industrial field environments.

Images