Frédéric Ros

Hybrid genetic algorithm for dual selection

In this paper, a hybrid genetic approach is proposed to solve the problem of designing a subdatabase of the original one with the highest classification performances, the lowest number of features and the highest number of patterns. The method can simultaneously treat the double problem of editing instance patterns and selecting features as a single optimization problem, and therefore aims at providing a better level of information. The search is optimized by dividing the algorithm into self-controlled phases managed by a combination of pure genetic process and dedicated local approaches. Different heuristics such as an adapted chromosome structure and evolutionary memory are introduced to promote diversity and elitism in the genetic population. They particularly facilitate the resolution of real applications in the chemometric field presenting databases with large feature sizes and medium cardinalities. The study focuses on the double objective of enhancing the reliability of results while reducing the time consumed by combining genetic exploration and a local approach in such a way that excessive computational CPU costs are avoided. The usefulness of the method is demonstrated with artificial and real data and its performance is compared to other approaches.

An Industrial Watermarking Process for Plastic Card Supports

This paper investigates a robust method to watermark and decode images such as identity pictures printed on plastic card supports that have a special interest in industrial areas requiring secure authentication. The watermark is embedded in two different secret middle frequency bands of the DFT (discrete Fourier transform) and its imperceptibility enhanced via a psychological mask incorporated in the spatial domain. Printing and scanning processes are well controlled in smart card area so than image synchronization is reduced to retrieve small translations and rotation in the spatial domain. This process is therefore simple, efficient and fast. The method interest is demonstrated with several watermarked images printed via common industrial printers and decoded by our home-made industrial reader prototype. Pictures were degraded via the print/scan process and by the wear and soil test that simulates the card usage along its lifetime. The correlation is very often above 50% when pictures are decoded with the right keys. It goes down on average to 10% if a wrong key is used as it is the case of an impostor. The process is very reliable: by setting an authenticity threshold to 20%, the probability of false alarm is less than 10-7.

Automatic and real-time inspection system for smart card module inspection

We present an automatic and real-time vision system to inspect the two sides of a smart card module using fuzzy logic. In the smart card industry, the module is the referential element sup- porting the chip. It is designed via successive microelectronic opera- tions to be finally embedded in the plastic card. For the chip side, the system can detect overflow of resin, integrity problems of the surface or of the resin protection, and misalignments. For the con- tact side, the system can detect all the defects affecting the module surface such as scratches, marks, or pollution. The vision system is flexible and real time. It is organized in dedicated layers and offers the necessary elements including controlled illumination systems to manage different films. A priori knowledge is introduced in the sys- tem, and fuzzy classifiers allow fast and reliable decisions. This in- dustrial system has exhibited an efficiency comparable to that of experienced human observers but at much higher speed.

Automatic and Real Time Inspection System for Smart Card Module using Fuzzy Logic

This paper presents an automatic and real time vision system to inspect the contact side of a smart card module using fuzzy logic. In the smart card industry, the module is the referential element supporting the chip. It is designed via successive microelectronic operations to be finally embedded in the plastic card. A priori knowledge is introduced in the system via fuzzy classifiers that allows fast and reliable decisions. The system can detect all the defects affecting the module surface such as scratches and marks. The vision system is flexible and real time. It is organized in dedicated layers and offers the necessary elements including controlled illumination systems to manage films variabilitys. This industrial system has exhibited efficiency comparable to that of experimented human observers but at much higher speed.