Scene text detection method based on end-to-end full convolutional neural network

Abstract

The present invention discloses a scene text detection method based on an end-to-end full convolutional neural network, which is used for the problem of finding a multi-directional text position in animage of a natural scene. The method specifically comprises the following steps: obtaining a plurality of image data sets for training scene text detection, and defining an algorithm target; carryingout feature learning on the image by using a full convolution feature extraction network; predicting an affine transformation matrix in an instance level for each sample point on the feature map, andcarrying out feature expression on the text according to the predicted affine transformation deformation sampling grid; classifying feature vectors of a candidate text, and carrying out coordinate regression and affine transformation regression to jointly optimize the model; using the learning framework to detect the precise position of the text; and carrying out non-maximum suppression on the bounding box set output by the network to obtain a final text detection result. The method disclosed by the present invention is used for scene text detection of real image data, and has a better effectand robustness for multi-directional, multi-scale, multi-lingual, shape distortion and other complicated situations.

Description

technical field [0001] The invention belongs to the field of computer vision, and in particular relates to a scene text detection method based on an end-to-end full convolutional neural network. Background technique [0002] Scene text detection is defined as the problem of finding multi-directional, multi-scale, multi-lingual text region locations in natural scene images. In recent years, it has been widely used in computer vision tasks such as scene understanding and image retrieval. There are two key points in this task: the first is how to well model multi-directional and severely distorted text objects to generate effective feature expressions; the second is how to use an end-to-end network to directly output detection results. For the first point, the present invention believes that the key to feature expression of scene text is to accurately model its spatial geometric characteristics, and use affine transformation to encode its spatial structure to produce a more ac...

AI Technical Summary

Problems solved by technology

Traditional methods generally use a fixed receptive field to extract the feature expression of the text and ignore the diversification of the target space structure of the te

Images