Training method and device of target object recognition model and electronic equipment

Abstract

The embodiment of the invention discloses a training method and device of a target object recognition model and electronic equipment. The training method of the target object recognition model comprises the steps of performing preprocessing operation on an image region with a target object to obtain a preprocessed image; inputting the preprocessed image into a target object recognition model for recognition operation to obtain a recognition result of the target object; in response to the fact that the recognition result is a first result, adjusting the preprocessing operation and parameters ofthe target object recognition model; and continuing to perform preprocessing operation and recognition operation on the image area with the target object until the recognition result is a second result. According to the training method of the target object recognition model, by dynamically generating the training image and adjusting the preprocessing operation of generating the training image, the technical problems that the training image set occupies the storage space and cannot be flexibly adjusted in the prior art are solved.

Description

technical field [0001] The present disclosure relates to the field of image processing, in particular to a training method, device and electronic equipment for a target object recognition model. Background technique [0002] Text recognition generally refers to the process of analyzing and recognizing image files of text materials to obtain text and layout information. Generally speaking, character recognition generally includes two processes of detection and recognition, wherein the detection process includes finding the area containing text in the image, and the recognition process includes recognizing the text in the text area. [0003] The traditional recognition process can generally use template matching or feature extraction to compare features, but this method is usually affected by the state of the text, such as the direction of the text, the intensity of light, etc., resulting in limited recognition accuracy and speed. In recent years, there is also a method of us...

AI Technical Summary

Problems solved by technology

[0003] The traditional recognition process can generally use template matching or feature extraction to compare features, but this method is usually affected by the state of the text, such as the direction of the text, the intensity of light, etc., resulting in limited recognition accuracy and speed.

In recent years, there is also a method of using a neural network for recognition, but the neural network needs to be trained, and the training requires a training atlas. The training atlas in the prior art generally includes various text lines, such as generally may include 400,000 Lines of text, the training atlas is very large and takes up a lot of space, and usually the neural network may not be able to recognize a certain type of text line during training, so it is necessary to manually add the corresponding type of text line to strengthen Neural Network Training

Images