谱聚类递归神经网络集成的全自动公开区分计算机和人的图灵测试识别算法  

Completely automated public turing test to tell computers and humans apart recognition algorithm based on spectral-clustering recurrent neural network ensemble

作　　者：张亮[1] 陈睿[1] 邱小松[1] 

机构地区：[1]电子工程学院网络系,合肥230037

出　　处：《计算机应用》2014年第5期1383-1385,共3页journal of Computer Applications

基　　金：安徽省自然科学基金资助项目(1208085QF107)

摘　　要：针对粘着全自动公开的区分计算机和人的图灵测试(CAPTCHA)的识别问题,提出了一种基于谱聚类递归神经网络(RNN)集成的识别算法。该算法首先使用不一致测度度量两个RNN之间的距离,构建出一张由多个候选RNN形成的图;然后基于谱图聚类理论,将多个RNN划分为不同的簇,并在每个簇上选择最佳RNN参与集成。实验结果表明:相对于单个候选RNN,该算法的识别率提高了约16%;相对于全部候选RNN构成的集成系统,该算法形成的集成规模更小,仅为原来的23%。Concerning the recognition of closely-connected Completely Automated Public Turing Test to Tell Computers and Humans Apart （ CAPTCHA）, a recognition algorithm based on spectral-clustering Recurrent Neural Network （RNN） ensemble was proposed. This algorithm firstly used disagreement measure for distance between two RNNs, thus constructed a graph composed by candidate RNNs. Then, a graph cluster method was used to divide RNNs into clusters. Finally, the best RNN in each cluster was selected. The experimental results reveal that： compared with single candidate RNN, recognition rates of this algorithm is increased by 16%. Compared with the ensemble of all candidate RNNs, ensemble size of this algorithm is much smaller, it is about 23% of the original size.

关 键 词：全自动公开区分计算机和人的图灵测试识别 谱聚类 递归神经网络 网络安全 多分类器集成 

分 类 号：TP393.08[自动化与计算机技术—计算机应用技术]