Please use this identifier to cite or link to this item: http://ena.lp.edu.ua:8080/handle/ntb/52449
Title: Development and Implementation of Human Face Alignment and Tracking in Video Streams
Authors: Zadorozhnii, Yevhen
Tverdokhlib, Yevhenii
Fedoronchak, Tetiana
Myronova, Natalia
Affiliation: Uzhhorod National University
Zaporizhzhia National Technical University
Bibliographic description (Ukraine): Development and Implementation of Human Face Alignment and Tracking in Video Streams / Yevhen Zadorozhnii, Yevhenii Tverdokhlib, Tetiana Fedoronchak, Natalia Myronova // Data stream mining and processing : proceedings of the IEEE second international conference, 21-25 August 2018, Lviv. — Львів : Lviv Politechnic Publishing House, 2018. — P. 574–579. — (Machine Vision and Pattern Recognition).
Bibliographic description (International): Development and Implementation of Human Face Alignment and Tracking in Video Streams / Yevhen Zadorozhnii, Yevhenii Tverdokhlib, Tetiana Fedoronchak, Natalia Myronova // Data stream mining and processing : proceedings of the IEEE second international conference, 21-25 August 2018, Lviv. — Lviv Politechnic Publishing House, 2018. — P. 574–579. — (Machine Vision and Pattern Recognition).
Is part of: Data stream mining and processing : proceedings of the IEEE second international conference, 2018
Conference/Event: IEEE second international conference "Data stream mining and processing"
Issue Date: 28-Feb-2018
Publisher: Lviv Politechnic Publishing House
Place of the edition/event: Львів
Temporal Coverage: 21-25 August 2018, Lviv
Keywords: regressor
cascade
face
search
marking
landmarks
classification
optimization
opencv
machine learning
machine vision
Number of pages: 6
Page range: 574-579
Start page: 574
End page: 579
Abstract: The paper presents a method that allows detection, alignment and tracking of a human face in a real time in video streams. To detect and to align face on an image a face shape regression approach is used. The developed method uses scanning window, a cascade of ensembles of regression and classification trees, and adaptive boosting. The same trees are used for classification whether the given window contains a face and for regression of a face shape. For face tracking a starting position for face search is taken from the found shape on the previous frame. Conducted analysis of the proposed method implementation gave good performance results but revealed shortcomings and directions for future work. Sensitivity of face detection is 78% and accuracy of face alignment is 95%. The implementation can track faces in real time with a speed of at least 20 frames per second.
URI: http://ena.lp.edu.ua:8080/handle/ntb/52449
ISBN: © Національний університет „Львівська політехніка“, 2018
© Національний університет „Львівська політехніка“, 2018
Copyright owner: © Національний університет “Львівська політехніка”, 2018
URL for reference material: http://viswww.cs.umass.edu/fddb
References (Ukraine): [1] B. Ginneken, “Active Shape Model Segmentation with Optimal Features”, IEEE Transactions on Medical Imaging, vol.21, No.8, pp. 924-933, 2002.
[2] T. F. Cootes, C. J. Taylor, D. H. Cooper, and J. Graham, “Active shape models – their training and application”, Computer Vision and Image Understanding, vol. 61, pp. 38–59, 1995.
[3] T. Cootes, G. Edwards, and C. Taylor, “Active appearance models”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 23, No.6., pp. 681–685, 2001.
[4] T. F. Cootes, G. J. Edwards, and C. J. Taylor, “Active appearance models”, European Conference on Computer Vision, vol. 2, pp. 484–498, 1998.
[5] S. Ren, X. Cao, Y. Wei, J. Sun, and S. Ren, “Face Alignment at 3000 FPS via Regressing Local Binary Features”, Computer Vision and Pattern Recognition, pp. 1685–1692, 2014.
[6] L. Breiman, “Random forests”, Machine Learning, vol. 45, No. 1, pp. 5–32, October 2001.
[7] Y. Freund, R. Schapire, and N. Abe, “A short introduction to boosting”, Journal of Japanese Society for Artificial Intelligence”, vol. 14, No. 5, pp. 771-780, September 1999.
[8] M. Valstar, B. Martinez, and X. Binefa, “Facial Point Detection using Boosted Regression and Graph Models”, Computer Vision and Pattern Recognition, pp. 2729-2736, 2010.
[9] S. Zhu, C. Li, C. Change Loy, and X. Tang, “Face Alignment by Coarse-to-Fine Shape Searching”, Computer Vision and Pattern Recognition, pp. 4998-5006, 2015.
[10] J. Li and Y. Zhang, “Learning surf cascade for fast and accurate object detection”, Computer Vision and Pattern Recognition, pp. 3468–3475, June 2013.
[11] R. Schapire and Y. Singer, “Improved Boosting Algorithm Using Confidence-rated Predictions,” Machine Learning, vol. 37, No. 3, pp. 297-336, 1999.
[12] B. M. Smith and L. Zhang, “Joint face alignment with nonparametric shape models”, 12th European Conference on Computer Vision, 14 p., 2012.
[13] FDDB: Face Detection Data Set and Benchmark. URL: http://viswww.cs.umass.edu/fddb. Last checked on 10th March, 2018.
References (International): [1] B. Ginneken, "Active Shape Model Segmentation with Optimal Features", IEEE Transactions on Medical Imaging, vol.21, No.8, pp. 924-933, 2002.
[2] T. F. Cootes, C. J. Taylor, D. H. Cooper, and J. Graham, "Active shape models – their training and application", Computer Vision and Image Understanding, vol. 61, pp. 38–59, 1995.
[3] T. Cootes, G. Edwards, and C. Taylor, "Active appearance models", IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 23, No.6., pp. 681–685, 2001.
[4] T. F. Cootes, G. J. Edwards, and C. J. Taylor, "Active appearance models", European Conference on Computer Vision, vol. 2, pp. 484–498, 1998.
[5] S. Ren, X. Cao, Y. Wei, J. Sun, and S. Ren, "Face Alignment at 3000 FPS via Regressing Local Binary Features", Computer Vision and Pattern Recognition, pp. 1685–1692, 2014.
[6] L. Breiman, "Random forests", Machine Learning, vol. 45, No. 1, pp. 5–32, October 2001.
[7] Y. Freund, R. Schapire, and N. Abe, "A short introduction to boosting", Journal of Japanese Society for Artificial Intelligence", vol. 14, No. 5, pp. 771-780, September 1999.
[8] M. Valstar, B. Martinez, and X. Binefa, "Facial Point Detection using Boosted Regression and Graph Models", Computer Vision and Pattern Recognition, pp. 2729-2736, 2010.
[9] S. Zhu, C. Li, C. Change Loy, and X. Tang, "Face Alignment by Coarse-to-Fine Shape Searching", Computer Vision and Pattern Recognition, pp. 4998-5006, 2015.
[10] J. Li and Y. Zhang, "Learning surf cascade for fast and accurate object detection", Computer Vision and Pattern Recognition, pp. 3468–3475, June 2013.
[11] R. Schapire and Y. Singer, "Improved Boosting Algorithm Using Confidence-rated Predictions," Machine Learning, vol. 37, No. 3, pp. 297-336, 1999.
[12] B. M. Smith and L. Zhang, "Joint face alignment with nonparametric shape models", 12th European Conference on Computer Vision, 14 p., 2012.
[13] FDDB: Face Detection Data Set and Benchmark. URL: http://viswww.cs.umass.edu/fddb. Last checked on 10th March, 2018.
Content type: Conference Abstract
Appears in Collections:Data stream mining and processing : proceedings of the IEEE second international conference



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.