Researchers working on binary pattern technique
31 December 2018 12:53 GMT

Researchers have proposed that an "Entropy based Local Binary Pattern (ELBP)" feature extraction technique could be used with multimodal biometrics as a defence mechanism for cloud storage

A paper by Sree Vidyaa and E Chandrab explains that ELBP is a new texture-based feature extraction technique proposed to describe the entropy information into Local Binary Pattern histogram in one-dimensional space.

"ELBP feature extraction technique needs no quantization. Biometric images exhibit higher uniqueness and hence incorporating entropy values into local regions add higher information content to these images, thus leading to better feature extraction. "

The team's experiments are performed on biometric images from Chinese Academy of Science, Institute of Automation (CASIA) Iris, Face and Fingerprint databases and the results show that the proposed ELBP feature extraction achieves substantial improvement, in terms of various classification metrics like accuracy, precision, recall etc. in comparison with the conventional rotation invariant LBP methods.

It adds that the Receiver Operating Characteristics Curve (ROC) also bears testimony to the performance of the authentication system.