A highly robust approach face recognition using hausdorff-trace transformation
ICONIP'10 Proceedings of the 17th international conference on Neural information processing: models and applications - Volume Part II
| Hi-index | 0.00 |
This paper presents a robust method for digital image identification under conditions of variant illumination, compression, flip, scaling, rotation and gray scale conversion. Techniques introduced in this work are composed of two parts. The first one is the signature of image is to be detected by the Trace Transform [6]. Then, in the second part, the notion of Hausdorff distance [8] and Modified Shape Context [10] are employed to measure and to determine the similarity between the models and tested images. Finally, our approach is evaluated with experiments on a set of over 60,000 unique images and one billion images pairs. The experimental result has show that the average of accuracy rate is higher than 83%.