Footprint Recognition Using Footprint Energy Image
Abstract:Footprint recognition for user identification is one of the emerging and promising technologies in behavioral biometrics area such as gait and voice because of its advantages like unconstrained and unconscious measurement from the user. Compared with OCR/CCD Scanner-based footprint recognition, pressure sensor-based approach has some advantage that not only the recognition of static footprint shape but also the recognition of dynamic walking behaviors such as COP (Centerof-pressure) Trajectories is easy to be found. As a result, there are some previous researches using the fusion of both static and dynamic information based on a mat-type floor pressure sensor to enhance the user identification rate. In this paper, a novel technique for the fusion of both static and dynamic information is addressed using the concept of temporal template image. Temporal template image can reflect global shape of the overlapped footprint image and their changes in each pixel over a single gait cycle. Compared with the fusion method of footprint shape and COP trajectory information, temporal template image has more strong power in the sense of computational cost, complexity of recognizer, and robustness to sensing error mainly due to the inevitable very low spatial resolution of commercial pressure sensor. Various techniques to make temporal template image, including Footprint Energy Image, Motion Silhouette Contour Templates, and Motion Silhouette Image, are compared each other in this paper. And, the effectiveness of the Footprint Energy Image is verified by the experiments with 26 university students' footprints data. The best recognition rate of footprint recognition for 26 people using Footprint Energy Image is 96.2% in our experiments.
Document Type: Research Article
Publication date: May 1, 2012
More about this publication?
- The growing interest and activity in the field of sensor technologies requires a forum for rapid dissemination of important results: Sensor Letters is that forum. Sensor Letters offers scientists, engineers and medical experts timely, peer-reviewed research on sensor science and technology of the highest quality. Sensor Letters publish original rapid communications, full papers and timely state-of-the-art reviews encompassing the fundamental and applied research on sensor science and technology in all fields of science, engineering, and medicine. Highest priority will be given to short communications reporting important new scientific and technological findings.
- Editorial Board
- Information for Authors
- Subscribe to this Title
- Terms & Conditions
- Ingenta Connect is not responsible for the content or availability of external websites