✦ LIBER ✦

Robust face recognition using 2D and 3D data: Pose and illumination compensation

✍ Scribed by Sotiris Malassiotis; Michael G. Strintzis

Publisher: Elsevier Science
Year: 2005
Tongue: English
Weight: 482 KB
Volume: 38
Category: Article
ISSN: 0031-3203
DOI: 10.1016/j.patcog.2005.02.001

No coin nor oath required. For personal study only.

✦ Synopsis

The paper addresses the problem of face recognition under varying pose and illumination. Robustness to appearance variations is achieved not only by using a combination of a 2D color and a 3D image of the face, but mainly by using face geometry information to cope with pose and illumination variations that inhibit the performance of 2D face recognition. A face normalization approach is proposed, which unlike state-of-the-art techniques is computationally efficient and does not require an extended training set. Experimental results on a large data set show that template-based face recognition performance is significantly benefited from the application of the proposed normalization algorithms prior to classification.

📜 SIMILAR VOLUMES

3D object recognition using Bayesian geo

3D object recognition using Bayesian geometric hashing and pose clustering

✍ Anshul Sehgal; U.B. Desai 📂 Article 📅 2003 🏛 Elsevier Science 🌐 English ⚖ 779 KB

Geometric hashing (GH) and partial pose clustering are well-known algorithms for pattern recognition. However, the performance of both these algorithms degrades rapidly with an increase in scene clutter and the measurement uncertainty in the detected features. The primary contribution of this paper

Robust palmprint verification using 2D a

Robust palmprint verification using 2D and 3D features

✍ David Zhang; Vivek Kanhangad; Nan Luo; Ajay Kumar 📂 Article 📅 2010 🏛 Elsevier Science 🌐 English ⚖ 778 KB

Automatic facial feature extraction and

Automatic facial feature extraction and 3D face modeling using two orthogonal views with application to 3D face recognition

✍ A-Nasser Ansari; Mohamed Abdel-Mottaleb 📂 Article 📅 2005 🏛 Elsevier Science 🌐 English ⚖ 679 KB

A Fast and Robust Algorithm for 2D/3D Pa

A Fast and Robust Algorithm for 2D/3D Panorama Ultrasound Data

✍ Otmar Scherzer; Armin Schoisswohl 📂 Article 📅 2002 🏛 Elsevier Science 🌐 English ⚖ 873 KB

T his paper presents a fast and robust algorithm for generating compound panorama images from partially (spatially) overlapping data sets. This method results in optimizing a nonlinear functional. We propose a multiscale approach for the solution of the optimization problem that is based on a multir

A Constraint-Satisfaction Approach for 3

A Constraint-Satisfaction Approach for 3-D Object Recognition by Integrating 2-D and 3-D Data

✍ Michael Boshra; Hong Zhang 📂 Article 📅 1999 🏛 Elsevier Science 🌐 English ⚖ 415 KB

We present a framework for recognition of 3D objects by integrating 2D and 3D sensory data. The major thrust of this work is to efficiently utilize all relevant data, both 2D and 3D, in the early stages of recognition, in order to reduce the computational requirements of the recognition process. To

Visual learning and recognition of 3D ob

Visual learning and recognition of 3D objects using two-dimensional principal component analysis: A robust and an efficient approach

✍ P. Nagabhushan; D.S. Guru; B.H. Shekar 📂 Article 📅 2006 🏛 Elsevier Science 🌐 English ⚖ 478 KB