A Novel Eye Gaze Estimation Method Using Ant Colony Optimizer

Document Type : Original Research (Full Papers)


Department of Computer Engineering, Amirkabir University of Technology, Tehran, Iran


This paper addresses the eye gaze estimation problem in low-resolution images, using the low-cost camera in order to eliminate problems caused by infrared high-resolution imaging such as needing an expensive camera, complex setup, special light sources, and being limited in lab research environments. In the proposed method, the human face is detected with Ant Colony Optimization (ACO) algorithm, and then the Kirsch compass mask is utilized to detect the position of humans’ eyes. For iris detection, a novel strategy based on ACO algorithm, which has been rarely used before, is applied. The pupil is recognized by morphological processing. Finally, the extracted features, obtained from the radius and position of the irises of the pupils, are given to the Support Vector Machine (SVM) classifier to detect the gaze pointing. In order to receive assurance of the reliability and superiority of the newly designed ACO algorithm, some other metaheuristic algorithms such as (GA, PSO, and BBO) are implemented and evaluated. Additionally, a novel dataset, comprising 700 images gazing at seven different major orientations, is created in this research. The extensive experiments are performed on three various datasets, including Eye-Chimera with 92.55% accuracy, BIOID dataset with 96% accuracy, and the newly constructed dataset with 90.71% accuracy. The suggested method outperformed the state of the art gaze estimation methods in terms of the robustness and accuracy.


[1] Kim, B. C.; Ko, D.; Jang, U.; Han, H.; Lee, E. C., 3D Gaze tracking by  combining  eye-and  facial-gaze  vectors.  The  Journal  of Supercomputing, vol. 73, no. 7, pp. 3038-3052 (2017). 
[2] Stanovich,  K.  E.,  "Concepts  in  developmental  theories  of  reading skill:  Cognitive  resources,  automaticity,  and  modularity" Developmental review, vol. 10, no. 1, pp. 72-100 (1990). 
[3] Armato,  A.;  Lanatà,  A.;    Scilingo,  E.  P.,  "Comparative  study  on photometric normalization algorithms for an innovative, robust and real-time  eye  gaze  tracker",  Journal  of  real-time  image  processing, vol. 8, no. 1, pp. 21-33 (2013). 
[4] Biswas, P.; Langdon, P., "Multimodal intelligent eye-gaze tracking system", International Journal of Human-Computer Interaction, vol. 31, no. 4, pp. 277-294 (2015). 
[5] Chen,  J.;  Ji,  Q.,  "A  Probabilistic  Approach  to  Online  Eye  Gaze Tracking Without Explicit Personal Calibration", IEEE Transactions On Image Processing, vol. 24, no. 3, pp. 1076-1086 (2015). 
[6] Maheswari, S. U.; Anbalagan, P.; Priya, T., "Efficient iris recognition through improvement in iris segmentation algorithm", International Journal on Graphics, Vision and Image Processing, vol. 8, no. 2, pp. 29-35 (2008). 
[7] Jagadeesan, A.; Thillaikkarasi, T.; Duraiswamy, K., "Cryptographic key generation from multiple biometric modalities: Fusing minutiae with iris feature", Int. J. Comput. Appl, vol. 2, no. 6, pp. 16-26 (2010). 
[8] Krisshna, N. A.; Deepak, V. K.; Manikantan, K.; Ramachandran, S., "Face  recognition  using  transform  domain  feature  extraction  and PSO-based feature selection", Applied Soft Computing, vol. 22, pp. 141-161 (2014). 
[9] Tan, K. H.; Kriegman, D. J.; Ahuja, N., "Appearance-based eye gaze estimation",  In  Applications  of  Computer  Vision,  (WACV  2002). Proceedings. Sixth IEEE Workshop on pp. 191-195 IEEE (2002). 
[10] Lu, F.; Okabe, T.; Sugano, Y.; Sato, Y., "A head pose-free approach for appearance-based gaze estimation", In BMVC, pp. 1-11 (2011) . 
[11] Sugano,  Y.;  Matsushita,  Y.;  Sato,  Y.;  Koike,  H.,  "An  incremental learning  method  for  unconstrained  gaze  estimation",  In  European Conference on  Computer  Vision,  Springer,  Berlin,  Heidelberg,  pp. 656-667 (2008). 
[12] Kim, H.; Lee, S. H.; Sohn, M. K.; Kim, D. J., "Illumination invariant head  pose  estimation  using  random  forests  classifier  and  binary pattern  run  length  matrix",  Human-centric  Computing  and Information Sciences, vol. 4, no. 1 (2014). 
[13] Simon, D., "Biogeography-based optimization", IEEE transactions on evolutionary computation, vol. 12, no. 6, pp. 702-713 (2008). 
[14] Cho, D. C.; Yap, W. S.; Lee, H.; Lee, I.; Kim, W. Y., "Long range eye gaze  tracking  system  for  a  large  screen",  IEEE  Transactions  on Consumer Electronics, vol. 58, no. 4 (2012). 
[15]  Bostanci,  E.;  Kanwal,  N.;  Clark,  A.  F.,  "Augmented  reality applications  for  cultural  heritage  using  Kinect",  Human-centric Computing and Information Sciences, vol. 5, no. 1 (2015). 
[16]  Wang,  J.  G.;  Sung,  E.,  "Study  on  eye  gaze  estimation",  IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), vol. 32, no. 3, pp. 332-350 (2002). 
[17]  Wang, J. G.; Sung, E.; Venkateswarlu, R., "Estimating the eye gaze from one eye", Computer Vision and Image Understanding, vol. 98, no. 1, pp. 83-103 (2005). 
[18]  Zhang, W.; Zhang, T. N.; Chang, S. J., "Eye gaze estimation from the elliptical  features  of  one  iris",  Optical  Engineering,  vol.  50,  no.  4 (2011). 
[19]  Eberhart,  R.;  Kennedy,  J.,  "A  new  optimizer  using  particle  swarm theory",  In  Micro  Machine  and  Human  Science,  1995.  MHS'95, Proceedings  of  the  Sixth  International  Symposium  on  (pp.  39-43). IEEE (1995). 
[20]  Valenti,  R.;  Gevers,  T.,  "Accurate  eye  center  location  through invariant isocentric patterns", IEEE transactions on pattern analysis and machine intelligence, vol. 34, no. 9, pp. 1785-1798 (2012). 
[21]  Valenti, R.; Gevers, T., "Accurate eye center location and tracking using  isophote  curvature",  In  Computer  Vision  and  Pattern Recognition, CVPR 2008. IEEE Conference on pp. 1-8 (2008). 
[22]  Cho, D. C.; Kim, W. Y., "Long-range gaze tracking system for large movements", IEEE Transactions on Biomedical Engineering, vol. 60, no. 12, pp. 3432-3440 (2013). 
[23]  Baek,  S.  J.;  Choi,  K.  A.;  Ma,  C.;  Kim,  Y.  H.;  Ko,  S.  J.,  "Eyeball model-based iris center localization for visible image-based eye-gaze tracking systems", IEEE Transactions on Consumer Electronics, vol. 59, no. 2, pp. 415-421 (2013). 
[24]  Timm, F.; Barth, E., "Accurate Eye Centre Localization by Means of Gradients" Visapp, vol. 11, pp. 125-130 (2011). 
[25]  Campadelli, P.; Lanzarotti, R.; Lipori, G., "Precise Eye Localization through a General-to-specific Model Definition", In BMVC vol. 1, pp. 187-196 (2006). 
[26]  Dorigo, M.; Birattari, M., "Ant colony optimization", In Encyclopedia of machine learning, pp. 36-39 (2011). 
[27]  Prakasam,  A.;  Savarimuthu,  N.,  "Metaheuristic  algorithms  and probabilistic  behaviour:  a  comprehensive  analysis  of  Ant  Colony Optimization and its variants", Artificial Intelligence Review, vol. 45, no. 1, pp. 97-130 (2016). 
[28]  Hao, Z.; Zhang, X.; Yu, P.; Li, H., "Video object tracing based on particle filter with ant colony optimization", In Advanced Computer Control (ICACC), 2010 2nd International Conference on vol. 3, pp. 232-236. IEEE (2010). 
[29]  Kim, H. I.; Kim, J. B.; Park, R. H., "Efficient and Fast Iris Localization Using  Binary  Radial  Gradient  Features  for  Human–Computer Interaction",  International  Journal  of  Pattern  Recognition  and Artificial Intelligence, vol. 31, no. 11, (2017). 
[30]  Chen, B.; Chen, L.; Chen, Y., "Efficient ant colony optimization for image feature selection", Signal processing, vol. 93, no. 6, pp. 1566-1576 (2013). 
[31]  Valenti,  R.;  Gevers,  T.,  "Accurate  eye  center  location  through invariant isocentric patterns", IEEE transactions on pattern analysis and machine intelligence, vol. 34, no. 9, pp.1785-1798 (2012). 
[32]  Srivastava,  D.  K.;  Budhraja,  T.,  "An  Effective  Model  for  Face Detection  Using  R,  G,  B  Color  Segmentation  with  Genetic Algorithm",  In  Proceedings  of  First  International  Conference  on Information and Communication Technology for Intelligent Systems, vol. 2, pp. 47-55 (2016). 
[33]  Kumar, P.; Shashidhara, M., "Skin color segmentation for detecting human  face  region  in  image",  In  Communications  and  Signal Processing (ICCSP), 2014 International Conference on pp. 001-005. IEEE (2014). 
[34]  Rivera, A. R.; Castillo, J. R.; Chae, O. O., "Local directional number pattern  for  face  analysis:  Face  and  expression  recognition",  IEEE transactions  on  image  processing,  vol.  22,  no.  5,  pp.  1740-1752 (2013). 
[35]  Zhang,  T.;  Tang,  Y.  Y.;  Fang,  B.;  Shang,  Z.;  Liu,  X.,  "Face recognition  under  varying  illumination  using  gradientfaces",  IEEE Transactions  on  Image  Processing,  vol.  18,  no.  11,  pp.  2599-2606 (2009). 
[36]  Kirsch, R. A., "Computer determination of the constituent structure of biological images", Computers and biomedical research, vol. 4, no. 3, pp. 315-328 (1971). 
[37]  Cortes, C.; Vapnik, V., "Support-vector networks", Machine learning, vol. 20, no. 3, pp. 273-297 (1995). 
[38]  Florea, L.; Florea, C.; Vrânceanu, R.; Vertan, C., "Can Your Eyes Tell Me  How  You  Think?  A  Gaze  Directed  Estimation  of  the  Mental Activity", In BMVC (2013). 
[39]  Valenti,  R.;  Sebe,  N.;  Gevers,  T.,  "Combining  head  pose  and  eye location  information  for  gaze  estimation",  IEEE  Transactions  on Image Processing, vol. 21, no. 2, pp. 802-815 (2012). 
[40]  Goldberg, D. E., "Genetic Algorithms in Search, Optimization, and Machine Language", Addison-Wesley: Reading, UK (1989). 
[41]  Luengo-Oroz, M. A.; Faure, E.; Angulo, J., "Robust iris segmentation on  uncalibrated  noisy  images  using  mathematical  morphology", Image and Vision Computing, vol. 28, no. 2, pp. 278-284 (2010). 
[42]  Haralick, R. M.; Sternberg, S. R.; Zhuang, X., "Image analysis using mathematical morphology", IEEE transactions on pattern analysis and machine intelligence, vol. 4, pp. 532-550 (1987).