Performance evaluation of a face tracking algorithm based on ASM models using the Kinect Sensor
DOI:
https://doi.org/10.33304/revinv.v10n2-2017007Keywords:
kinect sensor, Active shape models ASM, PCA, OpenCV, Feature points recognitionAbstract
This work shows the performance evaluation of a face tracking features algorithm, applying active shape models (ASM) and using the Kinect sensor as the capture image device. The development was implemented by using OpenCV libraries, in a laptop with processor core i5 at 2.4 GHz, 4 GB of RAM, and Windows 7 operative system. In order to perform the evaluation, the algorithm was run to analyze the response under different facial expression poses. The stabilization times of the points over the image were measured and the localization of the points in the image was manually evaluated. The face was divided in regions: face contours, eyebrows, nose, eyes and mouth. Finally, the results are presented as the average time of the face matching, the average number of frames required to perform matching, and the average error of the positioning in different faces conditions. The results show the strength of this work and the adaptability for future work.Downloads
References
Baltrusaitis, T., Robinson, P., & Morency, L.-P. (2012). 3D constrained local model for rigid and non-rigid facial tracking. In Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on (pp. 2610–2617). IEEE.
Chen, Y., & Davoine, F. (2006). Simultaneous Tracking of Rigid Head Motion and Non-rigid Facial Animation by Analyzing Local Features Statistically. In BMVC (pp. 609–618).
Cheng, S., Zafeiriou, S., Asthana, A., & Pantic, M. (2014). 3D facial geometric features for constrained local mode. In 2014 IEEE International Conference on Image Processing (ICIP) (pp. 1425–1429). IEEE.
Cheng, Y. (1995). Mean shift, mode seeking, and clustering. IEEE Transactions on Pattern Analysis and Machine Intelligence, 17(8), 790–799.
Cootes, T. F., & Taylor, C. J. (1992). Active shape models—“smart snakes.” In BMVC92 (pp. 266–275). Springer.
Cristinacce, D., & Cootes, T. F. (2004). A comparison of shape constrained facial feature detectors. In Automatic Face and Gesture Recognition, 2004. Proceedings. Sixth IEEE International Conference on (pp. 375–380). IEEE.
Cristinacce, D., & Cootes, T. F. (2006). Feature Detection and Tracking with Constrained Local Models. In BMVC (p. 10).
Cristinacce, D., & Cootes, T. F. (2007). Boosted regression active shape models. In BMVC (p. 7).
Delac, K., Grgic, M., & Grgic, S. (2005). Independent comparative study of PCA, ICA, and LDA on the FERET data set. International Journal of Imaging Systems and Technology, 15(5), 252–260.
Dornaika, F., & Davoine, F. (2004). Head and facial animation tracking using appearance-adaptive models and particle filters. In Computer Vision and Pattern Recognition Workshop, 2004. CVPRW’04. Conference on (pp. 153–153). IEEE.
Viola, P., & Jones, M. (2001). Rapid object detection using a boosted cascade of simple features. In Computer Vision and Pattern Recognition, 2001. CVPR 2001. Proceedings of the 2001 IEEE Computer Society Conference on (pp. I–511). IEEE.
Wang, Y., Lucey, S., & Cohn, J. F. (2008). Enforcing convexity for improved alignment with constrained local models. In Computer Vision and Pattern Recognition, 2008. CVPR 2008. IEEE Conference on (pp. 1–8). IEEE.
