当前位置: X-MOL 学术Comput. Secur. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Iris Template Protection Using Double Bloom Filter Based Feature Transformation
Computers & Security ( IF 4.8 ) Pub Date : 2020-10-01 , DOI: 10.1016/j.cose.2020.101985
Ajish S , K S AnilKumar

Abstract The primary focus of the bloom filter based iris feature transformations are template protection, data compression, response time of matching and the accuracy of matching. The increase in size of the code word of the bloom filter based feature transformation results in an exponential increase in the size of the transformed iris template and it degrades the data compression ratio, response time of matching and the accuracy of matching. This study presents a double bloom filter based iris feature transformation to reduce the exponential increase in the size of the transformed iris template. The number of bits set to one in the bloom filter based feature transformation is very less and it increases the false acceptance rate. The total bits set to one in the double bloom filter based feature transformation is double that of the bloom filter based transformation and it enhances the accuracy of matching of the transformed iris template. Experimental analysis exhibits that the double bloom filter based feature transformation enhances the data compression ratio, template protection, response time of matching and the accuracy of matching. The double bloom filter transformation reduces the size of the transformed iris template and increases the number of bits set to one there by it enhances the data compression ratio, template protection, response time of matching and the accuracy of matching.

中文翻译:

使用基于双布隆过滤器的特征转换的虹膜模板保护

摘要 基于布隆过滤器的虹膜特征转换主要关注模板保护、数据压缩、匹配响应时间和匹配精度。基于布隆过滤器的特征变换码字大小的增加导致变换后的虹膜模板的大小呈指数增长,降低了数据压缩率、匹配响应时间和匹配精度。本研究提出了一种基于双布隆过滤器的虹膜特征变换,以减少变换后的虹膜模板大小的指数增长。在基于布隆过滤器的特征变换中设置为 1 的位数非常少,这增加了错误接受率。基于双布隆过滤器的特征变换中设置为1的总位数是基于布隆过滤器变换的两倍,提高了变换后的虹膜模板的匹配精度。实验分析表明,基于双布隆过滤器的特征变换提高了数据压缩率、模板保护、匹配响应时间和匹配精度。双布隆过滤器变换减小了变换后的虹膜模板的大小,增加了设置为1的位数,从而提高了数据压缩率、模板保护、匹配响应时间和匹配精度。实验分析表明,基于双布隆过滤器的特征变换提高了数据压缩率、模板保护、匹配响应时间和匹配精度。双布隆过滤器变换减小了变换后的虹膜模板的大小,增加了设置为1的位数,从而提高了数据压缩率、模板保护、匹配响应时间和匹配精度。实验分析表明,基于双布隆过滤器的特征变换提高了数据压缩率、模板保护、匹配响应时间和匹配精度。双布隆过滤器变换减小了变换后的虹膜模板的大小,增加了设置为1的位数,从而提高了数据压缩率、模板保护、匹配响应时间和匹配精度。
更新日期:2020-10-01
down
wechat
bug