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

Examples of eye detection on the FERET database.The facial variations include pose, illumination, and glasses. The three left-most columns show accurate eye-center localization, while the right-most two columns show the inaccurate results.
© Copyright Policy
Related In: Results  -  Collection

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

pone.0139098.g012: Examples of eye detection on the FERET database.The facial variations include pose, illumination, and glasses. The three left-most columns show accurate eye-center localization, while the right-most two columns show the inaccurate results.

Mentions: In Fig 12, several examples show both accurate and inaccurate eye-center localization results. The first three columns show that, although the facial deflection angle is large, our algorithm works very well. In the fourth column, since the glasses generate a strong edge detection response when the face is turned left, these edges may lead to an inaccurate localization. In the fifth column, the facial angle is a little large, and the background causes instability in the eye-center estimation. Although the eye–center localizations are incorrect, the algorithm in this paper shows a very small deviation. This fully reflects the robustness of our method, due to the combination of global and local information.


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

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

Examples of eye detection on the FERET database.The facial variations include pose, illumination, and glasses. The three left-most columns show accurate eye-center localization, while the right-most two columns show the inaccurate results.
© Copyright Policy
Related In: Results  -  Collection

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

pone.0139098.g012: Examples of eye detection on the FERET database.The facial variations include pose, illumination, and glasses. The three left-most columns show accurate eye-center localization, while the right-most two columns show the inaccurate results.
Mentions: In Fig 12, several examples show both accurate and inaccurate eye-center localization results. The first three columns show that, although the facial deflection angle is large, our algorithm works very well. In the fourth column, since the glasses generate a strong edge detection response when the face is turned left, these edges may lead to an inaccurate localization. In the fifth column, the facial angle is a little large, and the background causes instability in the eye-center estimation. Although the eye–center localizations are incorrect, the algorithm in this paper shows a very small deviation. This fully reflects the robustness of our method, due to the combination of global and local information.

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