MultiModal-database-XJTU: An available database for biometrics recognition with its performance testing
Dongpeng Shang, Xinman Zhang, Jiuqiang Han, Xuebin Xu · 2017 IEEE 3rd Information Technology and Mechatronics Engineering Conference (ITOEC) · 2017
The current need for large multimodal databases to evaluate automatic biometrics recognition systems has motivated the development of the XJTU multimodal database. The main purpose has been to consider a large scale population, with statistical significance, in a real multimodal procedure, and including several sources of variability that can be found in real environments. The acquisition process, contents and availability of the single-session baseline corpus are fully described. Some experiments showing consistency of data through the different acquisition sites and assessing data quality are also presented. MultiModal-Database-XJTU, a new multimodal database, is presented. The database consists of fingerprint images acquired with sensor, frontal face images from a camera, iris images from a Cannon scanner, and voice utterances acquired with a microphone. The MultiModal-Database-XJTU includes real multimodal data from 102 individuals. In this contribution, the acquisition setup and protocol are outlined, and the contents of the database are described. The database will be publicly available for research purposes.