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

Comparison with [18] on BioID.The results yielded by our method when applied to the BioID and those given in [18] are compared. For (e ≤ 0.05) our method does not demonstrate significantly better performance, for (e ≤ 0.1) however, our method is more effective.
© Copyright Policy
Related In: Results  -  Collection

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

pone.0139098.g009: Comparison with [18] on BioID.The results yielded by our method when applied to the BioID and those given in [18] are compared. For (e ≤ 0.05) our method does not demonstrate significantly better performance, for (e ≤ 0.1) however, our method is more effective.

Mentions: In Fig 8, apart from the least accurate estimations, we also show the optimal estimations and the average difference between these two results, which is required if our results are to be compared with other published works. Compared with the MIC method applied to the BioID database, our method yielded more accurate results, as shown in Fig 8. From the curve in Fig 9, we can determine that our method does not have a significant advantage at (e ≤ 0.05), as the face regression model does not work efficiently at this stage. But, when it comes to (e ≤ 0.1), our method is more effective, since the face regression model can work as a robust constraint to determine the most likely center location. When the normalized error is increased, the advantage of our approach is more significant.


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

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

Comparison with [18] on BioID.The results yielded by our method when applied to the BioID and those given in [18] are compared. For (e ≤ 0.05) our method does not demonstrate significantly better performance, for (e ≤ 0.1) however, our method is more effective.
© Copyright Policy
Related In: Results  -  Collection

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

pone.0139098.g009: Comparison with [18] on BioID.The results yielded by our method when applied to the BioID and those given in [18] are compared. For (e ≤ 0.05) our method does not demonstrate significantly better performance, for (e ≤ 0.1) however, our method is more effective.
Mentions: In Fig 8, apart from the least accurate estimations, we also show the optimal estimations and the average difference between these two results, which is required if our results are to be compared with other published works. Compared with the MIC method applied to the BioID database, our method yielded more accurate results, as shown in Fig 8. From the curve in Fig 9, we can determine that our method does not have a significant advantage at (e ≤ 0.05), as the face regression model does not work efficiently at this stage. But, when it comes to (e ≤ 0.1), our method is more effective, since the face regression model can work as a robust constraint to determine the most likely center location. When the normalized error is increased, the advantage of our approach is more significant.

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