Verification Code Recognition Based on Active and Deep Learning

TL;DR

This paper introduces an active and deep learning approach to improve verification code recognition accuracy with limited training data by generating new data automatically and designing a specialized CNN model.

Contribution

It proposes a novel active and deep learning strategy for data augmentation and a feature learning model tailored for small datasets in verification code recognition.

Findings

Significantly improved recognition accuracy with limited initial data.

Effective automatic data generation without manual intervention.

Enhanced CNN performance in low-data scenarios.

Abstract

A verification code is an automated test method used to distinguish between humans and computers. Humans can easily identify verification codes, whereas machines cannot. With the development of convolutional neural networks, automatically recognizing a verification code is now possible for machines. However, the advantages of convolutional neural networks depend on the data used by the training classifier, particularly the size of the training set. Therefore, identifying a verification code using a convolutional neural network is difficult when training data are insufficient. This study proposes an active and deep learning strategy to obtain new training data on a special verification code set without manual intervention. A feature learning model for a scene with less training data is presented in this work, and the verification code is identified by the designed convolutional neural network. Experiments show that the method can considerably improve the recognition accuracy of a neural network when the amount of initial training data is small.