Text detection model training method and device, computer equipment and storage medium

Abstract

The invention relates to a text detection model training method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring a sample image with a text annotation box; performing feature extraction on the sample image, inputting the sample feature map into an initial text detection model to obtain a text prediction box of the sample image and a corresponding second coordinate matrix, and determining a loss value of the second coordinate matrix corresponding to the text prediction box according to a preset loss function and the first coordinate matrixof the text annotation box; and training an initial text detection model according to the loss value. A polygonal text annotation box with any angle is arranged in a sample image used during training; therefore, the directivity and the scale change of the text can be learned in the process of training the model, and when the model is used for text positioning detection, the target textbox which is matched with the text direction in the image and has any angle can be output, so that the recognition precision of a subsequent machine is improved.

Description

Technical field [0001] This application relates to the field of image recognition technology, in particular to a training method, device, computer equipment and storage medium of a text detection model. Background technique [0002] With the development of artificial intelligence technology, more and more tedious tasks are replaced by machines. For example, the recognition and input of some text images is not only time-consuming and labor-intensive, but also causes problems due to fatigue and negligence if it is only done manually. Therefore, the positioning and detection of the text in the text image can be automatically completed by the machine. [0003] However, text detection and positioning in natural scenes and documents have problems such as large changes in text scale, multiple directions, variable length and width, and dense text. In addition, the environment for text detection and positioning is more complicated, which makes multi-directional text and bending and tilting...

AI Technical Summary

Problems solved by technology

[0003] However, text detection and positioning in natural scenes and documents has problems such as large changes in text scale, multiple directions, variable length and width, and dense text. In addition, due to the complex environment of text detection and positioning, multi-directional texts and curved and inclined texts in natural scenes are often It leads to machine misrecognition. Therefore, the traditional rectangular regression can no longer meet the actual text detection and positioning needs.

Images