Character sequence recognition method, device, equipment and medium based on computer vision

Abstract

The present application relates to a computer vision-based character sequence recognition method, device, computer equipment and storage medium. The method comprises: obtaining an image carrying a sequence of characters to be recognized; obtaining an image of a target area where the sequence of characters to be recognized in the image is located based on a pre-built position detection model; performing horizontal correction on the image of the target area to obtain a horizontal image of the target area; Based on the pre-constructed angle judgment model, obtain the standing state of the character sequence of the horizontal target area image; if the character sequence is in an upright state, input the horizontal target area image into the pre-built content recognition model to obtain the The character sequence content corresponding to the character sequence. By adopting the method, the image of the target area can be horizontally corrected, and the adaptive processing of the change of the image shooting angle in the industrial scene is realized, thereby improving the accuracy rate of character sequence recognition.

Description

technical field [0001] The present application relates to the technical field of computer vision, in particular to a computer vision-based character sequence recognition method, device, computer equipment and storage medium. Background technique [0002] With the development of computer vision technology, the recognition of character sequences has become a part of practical applications in life, such as the recognition of character sequences such as product serial numbers, production dates, and stamped inscriptions in industrial scenarios. Generally speaking, the process of recognizing a character sequence is to first detect the position of the character sequence, then cut the character sequence at the detected position, and finally judge and recognize the angle of the cropped character sequence image to obtain the corresponding Text content; or by using the character sequence as a special target detection, through the classifier detection and based on the model of the image...

AI Technical Summary

Problems solved by technology

[0003] However, the current character sequence recognition methods are all based on low-dimensional manual features, and lack the ability to adaptively process changes in image shooting angles in industrial scenes. Therefore, the current character sequence recognition methods have low recognition accuracy for character sequences.

Images