Limits...
Robust Eye Center Localization through Face Alignment and Invariant Isocentric Patterns.

Pang Z, Wei C, Teng D, Chen D, Tan H - PLoS ONE (2015)

Bottom Line: In addition, we apply our method to non-frontal faces to test its robustness and accuracy, which are essential in gaze estimation but have seldom been mentioned in previous works.Through extensive experimentation, we show that the proposed method can achieve a significant improvement in accuracy and robustness over state-of-the-art techniques, with our method ranking second in terms of accuracy.According to our implementation on a PC with a Xeon 2.5Ghz CPU, the frame rate of the eye tracking process can achieve 38 Hz.

View Article: PubMed Central - PubMed

Affiliation: School of Physics and Engineering, Sun Yat-Sen University, Guangzhou, China.

ABSTRACT
The localization of eye centers is a very useful cue for numerous applications like face recognition, facial expression recognition, and the early screening of neurological pathologies. Several methods relying on available light for accurate eye-center localization have been exploited. However, despite the considerable improvements that eye-center localization systems have undergone in recent years, only few of these developments deal with the challenges posed by the profile (non-frontal face). In this paper, we first use the explicit shape regression method to obtain the rough location of the eye centers. Because this method extracts global information from the human face, it is robust against any changes in the eye region. We exploit this robustness and utilize it as a constraint. To locate the eye centers accurately, we employ isophote curvature features, the accuracy of which has been demonstrated in a previous study. By applying these features, we obtain a series of eye-center locations which are candidates for the actual position of the eye-center. Among these locations, the estimated locations which minimize the reconstruction error between the two methods mentioned above are taken as the closest approximation for the eye centers locations. Therefore, we combine explicit shape regression and isophote curvature feature analysis to achieve robustness and accuracy, respectively. In practical experiments, we use BioID and FERET datasets to test our approach to obtaining an accurate eye-center location while retaining robustness against changes in scale and pose. In addition, we apply our method to non-frontal faces to test its robustness and accuracy, which are essential in gaze estimation but have seldom been mentioned in previous works. Through extensive experimentation, we show that the proposed method can achieve a significant improvement in accuracy and robustness over state-of-the-art techniques, with our method ranking second in terms of accuracy. According to our implementation on a PC with a Xeon 2.5Ghz CPU, the frame rate of the eye tracking process can achieve 38 Hz.

No MeSH data available.


Related in: MedlinePlus

Successful (first row) and failed (second row) eye center localization using the BioID face database.The white dots represent the estimated centers and the first, second, and third rows shows the maximum isocenter (MIC) estimation results, the candidate MICs, and the final estimation (red dot) with the facial alignment constraint (blue dot), respectively. Both the present approach and the MIC method are effective in many situations (first row), however, in more challenging cases (other rows) our method has better accuracy.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4591357&req=5

pone.0139098.g007: Successful (first row) and failed (second row) eye center localization using the BioID face database.The white dots represent the estimated centers and the first, second, and third rows shows the maximum isocenter (MIC) estimation results, the candidate MICs, and the final estimation (red dot) with the facial alignment constraint (blue dot), respectively. Both the present approach and the MIC method are effective in many situations (first row), however, in more challenging cases (other rows) our method has better accuracy.

Mentions: In Fig 7, the first row shows the MIC estimation results, the second row demonstrates the candidate MICs, and the third row indicates the final estimation (red dot) with the face alignment constraint (blue dot). The first column shows that, in many cases, both our approach and the MIC method work well, while the other columns show that, in some extreme cases such as eye closure or strong reflection from glasses, our methods work more accurately.


Robust Eye Center Localization through Face Alignment and Invariant Isocentric Patterns.

Pang Z, Wei C, Teng D, Chen D, Tan H - PLoS ONE (2015)

Successful (first row) and failed (second row) eye center localization using the BioID face database.The white dots represent the estimated centers and the first, second, and third rows shows the maximum isocenter (MIC) estimation results, the candidate MICs, and the final estimation (red dot) with the facial alignment constraint (blue dot), respectively. Both the present approach and the MIC method are effective in many situations (first row), however, in more challenging cases (other rows) our method has better accuracy.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4591357&req=5

pone.0139098.g007: Successful (first row) and failed (second row) eye center localization using the BioID face database.The white dots represent the estimated centers and the first, second, and third rows shows the maximum isocenter (MIC) estimation results, the candidate MICs, and the final estimation (red dot) with the facial alignment constraint (blue dot), respectively. Both the present approach and the MIC method are effective in many situations (first row), however, in more challenging cases (other rows) our method has better accuracy.
Mentions: In Fig 7, the first row shows the MIC estimation results, the second row demonstrates the candidate MICs, and the third row indicates the final estimation (red dot) with the face alignment constraint (blue dot). The first column shows that, in many cases, both our approach and the MIC method work well, while the other columns show that, in some extreme cases such as eye closure or strong reflection from glasses, our methods work more accurately.

Bottom Line: In addition, we apply our method to non-frontal faces to test its robustness and accuracy, which are essential in gaze estimation but have seldom been mentioned in previous works.Through extensive experimentation, we show that the proposed method can achieve a significant improvement in accuracy and robustness over state-of-the-art techniques, with our method ranking second in terms of accuracy.According to our implementation on a PC with a Xeon 2.5Ghz CPU, the frame rate of the eye tracking process can achieve 38 Hz.

View Article: PubMed Central - PubMed

Affiliation: School of Physics and Engineering, Sun Yat-Sen University, Guangzhou, China.

ABSTRACT
The localization of eye centers is a very useful cue for numerous applications like face recognition, facial expression recognition, and the early screening of neurological pathologies. Several methods relying on available light for accurate eye-center localization have been exploited. However, despite the considerable improvements that eye-center localization systems have undergone in recent years, only few of these developments deal with the challenges posed by the profile (non-frontal face). In this paper, we first use the explicit shape regression method to obtain the rough location of the eye centers. Because this method extracts global information from the human face, it is robust against any changes in the eye region. We exploit this robustness and utilize it as a constraint. To locate the eye centers accurately, we employ isophote curvature features, the accuracy of which has been demonstrated in a previous study. By applying these features, we obtain a series of eye-center locations which are candidates for the actual position of the eye-center. Among these locations, the estimated locations which minimize the reconstruction error between the two methods mentioned above are taken as the closest approximation for the eye centers locations. Therefore, we combine explicit shape regression and isophote curvature feature analysis to achieve robustness and accuracy, respectively. In practical experiments, we use BioID and FERET datasets to test our approach to obtaining an accurate eye-center location while retaining robustness against changes in scale and pose. In addition, we apply our method to non-frontal faces to test its robustness and accuracy, which are essential in gaze estimation but have seldom been mentioned in previous works. Through extensive experimentation, we show that the proposed method can achieve a significant improvement in accuracy and robustness over state-of-the-art techniques, with our method ranking second in terms of accuracy. According to our implementation on a PC with a Xeon 2.5Ghz CPU, the frame rate of the eye tracking process can achieve 38 Hz.

No MeSH data available.


Related in: MedlinePlus