Introduction

Important applications related to PRIP Lab research include face recognition, fingerprint identification, document image analysis, 3D object recognition, robot navigation, and visualization/exploration of 3D data.

PRIP Lab faculty and students investigate the use of machines to recognize a variety of patterns or objects. Methods are developed to sense objects, to discover which of their features distinguish them from others, and to design algorithms that can be used by a machine to classify or cluster objects. Since many applications use a sensed image to initially represent the object much PRIP Lab research deals with images. A significant portion of our research focuses on the development of algorithms to do feature extraction (such as finding the ends of ridges in a fingerprint) and matching (such as matching ridge endpoints across two fingerprints) and on the organization of data to support efficient matching

Some recent projects include biometric authentication, automatic surveillance and tracking of people in a work area, face modeling, digital watermarking, medical image segmentation, and analyzing structure of online documents. Description of both current and recent research projects can be found under research from www.cse.msu.edu

Face Recognition Videos

3d Face

A 3D model of a face can be acquired using a laser scanner. We use this data to generate 2D images of the face under various poses and lighting conditions to improve recognition. It is also used for 3D matching.

Face Expression

Using the 3D data of the face, expressions can be learned and applied to neutral models in order to better match faces with varying expression.

3D Finger

The latest technology for capturing fingerprints is able to acquire the finger in 3D. Typically, when fingerprints are captured, they become distorted when the finger is pressed against a surface, where other problems with smearing and residue can occur. 3D fingers can be matched with 2D pressed images or with other 3D fingers without such problems.

Fingerprint Alignment

Automatic fingerprint matching is performed by applying image processing algorithms, extracting minutiae, finding the correspondences between a stored finger and the input finger, and finally computing a score based on how well the minutiae match.