A Novel LSTM-RNN Decoding Algorithm in CAPTCHA Recognition

Author

Chen Rui ; Yang Jing ; Hu Rong-gui ; Huang Shu-guang

Author_Institution

Dept. of Network, Electron. Eng. Inst., Hefei, China

fYear

2013

fDate

21-23 Sept. 2013

Firstpage

766

Lastpage

771

Abstract

LSTM-RNN has been succeeded in applying in offline handwritten recognition. The paper used two-dimensional LSTM-RNN to recognize text-based CAPTCHA. Aiming at the problem that traditional decoding algorithm cannot obtain satisfactory results. The paper proposed a novel decoding algorithm based on the multi-population genetic algorithm. The experimental results showed that the novel decoding algorithm for the LSTM-RNN can improve the recognition rate of merged-type CAPTCHA.

Keywords

decoding; genetic algorithms; handwriting recognition; security of data; text detection; Completely Automated Public Turning test to tell Computers and Humans Apart; LSTM-RNN decoding algorithm; merged-type CAPTCHA; multipopulation genetic algorithm; network security mechanism; offline handwritten recognition; text-based CAPTCHA recognition; CAPTCHAs; Decoding; Genetic algorithms; Hidden Markov models; Image recognition; Image segmentation; Probability; CAPTCHA recognition; Network Security; Recurrent Neural Network; decoding algorithm;

fLanguage

English

Publisher

ieee

Conference_Titel

Instrumentation, Measurement, Computer, Communication and Control (IMCCC), 2013 Third International Conference on

Conference_Location

Shenyang

Type

conf

DOI

10.1109/IMCCC.2013.171

Filename

6840561