Xirong Lin

Liveness detection for iris recognition using multispectral images

Liveness detection is a necessary step towards higher reliability of iris recognition. In this research, we propose a novel iris liveness detection method based on multi-features extracted from multispectral images. First, we analyze the specific multispectral characteristics of conjunctival vessels and iris textures. To ensure the effective utilization of these characteristics, iris images are simultaneously captured at near-infrared (860nm) and blue (480nm) wavelengths. Then we respectively define and measure relative number of conjunctival vessels (RNCV) and entropy ratio of iris textures (ERIT) using 860-nm and 480-nm images. Finally, the feature values of RNCV and ERIT are arranged to form a robust 2-D feature vector. The trained Support Vector Machine (SVM) is used to classify the feature vectors extracted from live and fake irises. Experimental results demonstrate that the proposed method can discriminate between live irises and various types of fake irises with high classification accuracy and low computational cost.

Accurate and fast iris segmentation applied to portable image capture device

As an important step for iris recognition, iris segmentation provides available texture region for subsequent processing. When using portable image capture device, non-ideal iris images are often obtained. Hence, this paper presents a novel algorithm for accurate and fast iris segmentation. By combining level set theory with variational method, probabilistic active contour model (PAC) is established. In addition, region information and probability distribution are used as stop terms. Under this model, initial curve is iteratively driven towards iris boundaries. In the evolving process, eyelids, eyelashes, reflections and shadows are simultaneously detected. Experimental results on iris image database demonstrate that the proposed algorithm outperforms state-of-the-art methods in both accuracy and speed.

Indirect real-time measurement of the penpoint in an interactive projector-camera system

Real-time interactive on documents can enhance effectiveness of learning in modern education. A pen capable of locating on a screen is one significant choice. Some products have been developed and the nib of pen is used as the emitter. However, the pen might fail to be located while our body or hand would block the light wherever the photo detector is. In this paper, we have proposed a scheme to solve the problem. It will detect the nib of pen indirectly. Meanwhile, for the realization of real time, we choose PSD(position sensitive detector) as the detector to track the light of the LEDs. And by using the method of coding, multiple light points detected by one PSD could be achieved.