Abstract
In this paper, we propose a new method of removing glasses from a human frontal facial image. We first detect the regions occluded by the glasses and generate a natural looking facial image without glasses by recursive error compensation using PCA reconstruction. The resulting image has no trace of the glasses frame or of the reflection and shade caused by the glasses. The experimental results show that the proposed method provides an effective solution to the problem of glasses occlusion and we believe that this method can also be used to enhance the performance of face recognition systems.
| Original language | English |
|---|---|
| Pages (from-to) | 805-811 |
| Number of pages | 7 |
| Journal | IEEE Transactions on Pattern Analysis and Machine Intelligence |
| Volume | 27 |
| Issue number | 5 |
| DOIs | |
| Publication status | Published - 2005 May 1 |
Fingerprint
Keywords
- Face recognition
- Face reconstruction
- Face synthesis
- Glasses removal
- Recursive error compensation
ASJC Scopus subject areas
- Control and Systems Engineering
- Electrical and Electronic Engineering
- Artificial Intelligence
- Computer Vision and Pattern Recognition
Cite this
Glasses removal from facial image using recursive error compensation. / Park, Jeong Seon; Oh, You Hwa; Ahn, Sang Chul; Lee, Seong Whan.
In: IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 27, No. 5, 01.05.2005, p. 805-811.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - Glasses removal from facial image using recursive error compensation
AU - Park, Jeong Seon
AU - Oh, You Hwa
AU - Ahn, Sang Chul
AU - Lee, Seong Whan
PY - 2005/5/1
Y1 - 2005/5/1
N2 - In this paper, we propose a new method of removing glasses from a human frontal facial image. We first detect the regions occluded by the glasses and generate a natural looking facial image without glasses by recursive error compensation using PCA reconstruction. The resulting image has no trace of the glasses frame or of the reflection and shade caused by the glasses. The experimental results show that the proposed method provides an effective solution to the problem of glasses occlusion and we believe that this method can also be used to enhance the performance of face recognition systems.
AB - In this paper, we propose a new method of removing glasses from a human frontal facial image. We first detect the regions occluded by the glasses and generate a natural looking facial image without glasses by recursive error compensation using PCA reconstruction. The resulting image has no trace of the glasses frame or of the reflection and shade caused by the glasses. The experimental results show that the proposed method provides an effective solution to the problem of glasses occlusion and we believe that this method can also be used to enhance the performance of face recognition systems.
KW - Face recognition
KW - Face reconstruction
KW - Face synthesis
KW - Glasses removal
KW - Recursive error compensation
UR - http://www.scopus.com/inward/record.url?scp=18144427173&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=18144427173&partnerID=8YFLogxK
U2 - 10.1109/TPAMI.2005.103
DO - 10.1109/TPAMI.2005.103
M3 - Article
C2 - 15875801
AN - SCOPUS:18144427173
VL - 27
SP - 805
EP - 811
JO - IEEE Transactions on Pattern Analysis and Machine Intelligence
JF - IEEE Transactions on Pattern Analysis and Machine Intelligence
SN - 0162-8828
IS - 5
ER -