Loading...
Please wait, while we are loading the content...
Similar Documents
Face reconstruction using fixation positions and foveated imaging (2008)
| Content Provider | CiteSeerX |
|---|---|
| Author | Fang, Fang Qing, Zhiguo Ma Laiyun |
| Description | Face representation is important for face recognition system. Though most popular face representations are based on uniform grid sampling, some recent face recog-nition systems adopt weighted sampling on the different re-gions of a face. Psychological analysis of visual attention or human eye fixations on human face images may sug-gest some cues for face representation. Human Visual Sys-tem(HVS) gives different weight to different region of human face via space-variant sampling on fovea and non-uniform distribution of fixations. This paper focuses on the prob-lem of simulation of the foveated imaging phenomenon in HVS, and introduction of foveated imaging method into re-construction of face in region of interest (ROI) using differ-ent fixation sources. We compare the effectiveness of actual fixation on reconstruction of face in ROI with uniform, ran-dom distribution fixation as well as fixation generated by ar-tificial model. The experimental results on 100 face images from FRGC [7] data set show that actual fixation positions and model-generated fixation positions reconstruct the face in ROI with considerably better quality. A further analysis on the statistics of fixation positions also shows that the dis-tribution of the fixation points is consistent with the weights of different regions on face images used in some other face recognition systems. 1. |
| File Format | |
| Language | English |
| Publisher Date | 2008-01-01 |
| Publisher Institution | In Automatic Face Gesture Recognition, 2008. FG ’08. 8th IEEE International Conference on |
| Access Restriction | Open |
| Subject Keyword | Human Visual Sys-tem Recent Face Recog-nition System Psychological Analysis Uniform Grid Sampling Human Face Image Actual Fixation Position Fixation Position Face Recognition System Human Face Different Weight Actual Fixation Ar-tificial Model Weighted Sampling Fixation Point Different Re-gions Model-generated Fixation Position Different Region Face Image Human Eye Fixation Face Reconstruction Visual Attention Non-uniform Distribution Popular Face Representation Ran-dom Distribution Fixation Foveated Imaging Phenomenon Experimental Result Differ-ent Fixation Source Face Representation |
| Content Type | Text |
| Resource Type | Article |
