The human iris has proved to be one of the most reliable biometric features for the identification of individuals. Realtime iris recognition requires high quality images that provide enough details about the iris texture and algorithms to analyze and process the images at the highest possible speed.In this work, an extension to the classical circular model for the pupil and iris using flexible contours is provided. Then, a method for assessing the quality of the iris images in real-time based on the segmentation results is introduced. Experimental results are presented, and we conclude that the new methods improve the recognition rate, achieving a 100% correct recognition rate on the CASIA iris database, while being suitable for a real-time iris recognition camera system.

Abstract. The pattern of the human iris contains rich information which provides one of the most accurate methods for recognition of individuals. Identification through iris recognition is achieved by matching a biometric template generated from the texture of the iris against an existing database of templates. This relies on the assumption that the probability of two different iris generating similar templates is very low. This assumption opens a question: how can one be sure that two iris templates are similar because they were generated from the same iris and not because of some other random factor?In this paper we introduce a novel technique for iris matching based on the a contrario framework, where two iris templates are decided to belong to the same iris according to the unlikelyness of the similarity between them. This method provides an intuitive detection thresholding technique, based on the probability of occurence of the distance between two templates. We perform tests on different iris databases captured in heterogeneous environments and we show that the proposed identification method is more robust than the standard method based on the Hamming distance.

This work is a part of a project supported by STIC Am-Sud where the main objective is to design an intelligent vision system to protect children from some critical information accessible from the Internet, from some videos or from some video games that are related to violence, wars, pornography, etc. Considered definitively not appropriate for their age, such multimedia contains can significantly offend young people. More specifically, in this paper, we are interested in discussing a general concept of a supervised biometric system that is controlled by specific tags embedded in video frames through a multimodal compression. Using a spiral insertion scheme, specific frequencies (TAGs) are compressed jointly with video frames in the region of insertion and then extracted for supervision purpose. The multimodal compression is considered here because it allows high-level robustness regarding the bitrates and downsampling.

Snel is a relational database engine featuring Just-In-Time (JIT) compilation of queries and columnar data representation. Snel is designed for fast on-line analytics by leveraging the LLVM compiler infrastructure. It also has custom special methods like resolving histograms as extensions to the SQL language. "Snel" means "SQL Native Execution for LLVM".Unlike traditional database engines, it does not provide a client-server interface. Instead, it exposes its interface as an extension to SQLite, for a simple interactive usage from command line and for embedding in applications. Since Snel tables are read-only, it does not provide features like transactions or updates. This allows queries to be very fast since they don't have the overhead of table locking or ensuring consistency.At its core, Snel is simply a dynamic library that can be used by client applications. It has an SQLite extension for seamless integration with a traditional SQL environment and simple interactive usage from command line.