作者: Sharatchandra Pankanti , Minerva M. Yeung
DOI: 10.1117/12.344704
关键词: Digital watermarking 、 Feature extraction 、 Fingerprint (computing) 、 Robustness (computer science) 、 Image processing 、 Computer science 、 Watermark 、 Copy protection 、 Fingerprint recognition 、 Artificial intelligence 、 Computer vision
摘要: Current 'invisible' watermarking techniques aim at producing watermarked data that suffer no or little quality degradation and perceptually identical to the original versions. The most common utility of a image is (1) for viewing display, (2) extracting embedded watermark in subsequent copy protection applications. issue often centered on robustness detection extraction. In addition studies, fundamental question will center utilization value images beyond perceptual evaluation. Essentially we have study how watermarks inserted affect processing images, what schemes can develop cater these tasks. This work focuses used automatic personal identification technology based fingerprints. We investigate effects fingerprint recognition retrieval accuracy using proposed invisible fragile technique verification applications specific system. shall also describe scheme, feature extraction used. believe provided value-added protection, as well copyright notification capability, collection processes usage.