Image data processing method and device

Abstract

The invention discloses an image data processing method and device. The method comprises that a target image is obtained, a monochromatic component image corresponding to the target image is generated; the target image is divided into to-be-identified areas according to angular points and end points of each monochromatic component image; and on the basis of a classifier, a character identificationprobability corresponding to each to-be-identified area is calculated, and a character area is identified from each to-be-identified area according to the character identification probability. Via the method and device, the cost of identifying the character areas can be reduced, and consumption of network flow can be reduced.

Description

technical field [0001] The present invention relates to the field of computer technology, in particular to an image data processing method and device. Background technique [0002] The current scheme for identifying the text area in the picture is usually: a mobile phone takes a picture containing text content, and sends the picture to the cloud server, and the cloud server performs deep learning detection on the picture to identify the text in the picture. text area. Although this method can accurately identify the text area in the picture, the cloud server uses a complex deep learning technology with many layers, which requires high computing power of the device. Therefore, if this deep learning technology is applied On most mobile phones, due to the computing power of most mobile phones, it will not be able to meet the real-time requirements. Therefore, it is necessary to deploy cloud servers to realize this deep learning technology, thereby increasing the cost of implem...

AI Technical Summary

Problems solved by technology

Although this method can accurately identify the text area in the picture, the cloud server uses a complex deep learning technology with many layers, which requires high computing power of the device. Therefore, if this deep learning technology is applied On most mobile phones, due to the computing power of most mobile phones, it will not be able to meet the real-time requirements. Therefore, it is necessary to deploy cloud servers to realize this deep learning technology, thereby increasing the cost of implementation; Send to the cloud server, and the cloud server will return the recognition result to the mobile phone, so if there are many pictures that need to be recognized by the text area, it may greatly increase the consumption of network traffic

Images