Sequence domain adaptation method based on adversarial learning in scene text recognition

Abstract

The invention belongs to the technical field of artificial intelligence, and particularly relates to a domain adaptation method based on a machine vision scene text recognition task. The method comprises the following steps: constructing a CNN-LSTM network and an attention network; combining the CNN-LSTM network and the attention network into a scene text recognition network; inputting the scene images from the source domain and the target domain into a scene text recognition network, extracting image features from the input scene images by CNN-LSTM, recoding the image features by an attentionnetwork, extracting corresponding features of each character, and segmenting text information in the images into character level information; and finally, constructing a domain classification networkby applying a transfer learning technology based on adversarial learning, forming an adversarial generation network together with the scene text recognition network, and finally enabling the model toeffectively adapt to a target domain. According to the method, a small number of target domain calibration samples are fully utilized, the problem of sample scarcity frequently occurring in an actualscene text recognition task is solved, and the recognition effect is improved.

Description

technical field [0001] The invention belongs to the technical field of artificial intelligence, and in particular relates to a sequence domain adaptation method based on adversarial learning in scene text recognition. Background technique [0002] With the rapid development of the field of computer vision, the application of scene text recognition covers all aspects of life. However, a key factor for deep learning to ensure the effect is the need to provide a large number of calibration samples, but in practice, only a small number of calibration samples are often provided. A common solution is to use existing samples of related scenes with a large number of samples to participate in training, but due to the differences between scenes, the effect is often unsatisfactory. The existing methods of domain adaptation have a common problem, that is, they are all aimed at classification tasks in computer vision tasks, and reduce the difference between the source domain and the tar...

AI Technical Summary

Problems solved by technology

But powerless for sequence recognition tasks like text recognition

Images