Image recognition method, related device and equipment

Abstract

The invention discloses an image recognition method. The image recognition method comprises the following steps: carrying out binarization processing on an image to obtain a binary image, wherein theimage comprises a plurality of characters; performing skeleton extraction on the binary image, and extracting skeleton information of the plurality of characters; extracting the stroke information from the skeleton information, wherein the stroke information comprises the number of stroke feature points and position information between the adjacent stroke feature points; and analyzing the stroke information through a time sequence recognition engine based on a deep learning network, and identifying the plurality of characters and the position relation information among the characters. The invention further discloses an image recognition device and equipment, being characterized in that manual feature design is not needed; character separation is not needed; and the technical problem that the recognition accuracy is low due to the fact that in the prior art, for characters with adhesion, a separation algorithm cannot be well processed is solved.

Description

technical field [0001] The present invention relates to the field of computers, in particular to an image capture method, related devices and equipment. Background technique [0002] Optical Character Recognition (OCR) means that an electronic device (such as a scanner or digital camera) checks characters printed on paper, determines its shape by detecting dark and light patterns, and then uses character recognition methods to translate the shape into computer characters. text process. Among them, the misrecognition rate or recognition accuracy rate is an important index to measure the performance of OCR. [0003] At present, OCR mathematical character recognition has a wide range of applications, and it can replace the keyboard to complete high-speed text entry in many occasions. For example, using OCR to identify and input printed manuscripts is one of the methods often used by many office departments; there is also printed recognition that can automatically segment comp...

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the embodiments of the present invention is to provide an image recognition method, an image recognition device, an image recognition device, and a computer-readable storage medium, so as to solve the problem of separation of characters with sticking in the prior art. Algorithms cannot be handled well, leading to technical problems with low recognition accuracy

Images