Design of rotation, illumination, and texture-invariant composite filters from range images using simulated annealing for face recognition
✍ Scribed by Shizhuo Yin; David Duarte; Purwadi Purwosumarto
- Publisher
- John Wiley and Sons
- Year
- 1999
- Tongue
- English
- Weight
- 312 KB
- Volume
- 23
- Category
- Article
- ISSN
- 0895-2477
No coin nor oath required. For personal study only.
✦ Synopsis
In this paper, the design of composite filters from range images using the simulated annealing technique for robust face recognition is discussed. Due to the use of range images as the training set for the synthesis of composite filters, besides the out-of-plane rotation in¨ariance, the designed composite filters are also inherently insensiti¨e to the ¨ariation in the illumination and texture of the object. In addition, since the correlation operation can be done in the 2-D domain, the required processing time for 3-D range data is also substantially reduced. The experimental results show that the maximum responses of the antitarget are always less than the minimum response of the target, e¨en in the case where multiple faces are in¨ol¨ed, which demonstrates the feasibility of the proposed technique.