Abstract
We analyzed the way to increase computational efficiency of video-based image recognition methods with matching of high dimensional feature vectors extracted by deep convolutional neural networks. We proposed an algorithm for approximate nearest neighbor search. At the first step, for a given video frame the algorithm verifies a reference image obtained when recognizing the previous frame. After that the frame is compared with a few number of reference images. Each next examined reference image is chosen so that to maximize conditional probability density of distances to the reference instances tested at previous steps. To decrease the required memory space we beforehand calculate only distances from all the images to small number of instances (pivots). When experimenting with either face photos from Labeled Faces in the Wild and PubFig83 datasets or with video data from YouTube Faces we showed that our algorithm allows accelerating the recognition procedure by 1.4–4 times comparing with known approximate nearest neighbor methods.
Similar content being viewed by others
References
Bautista, C.M., Dy, C.A., Maýalac, M.I., Orbe, R.A., and Cordel, M., Convolutional neural network for vehicle detection in low resolution traffic videos, Proc. of the Region 10 Symposium (TENSYMP), IEEE, 2016, pp. 277–281.
Savchenko, A.V., Adaptive video image recognition system using a committee machine, Opt. Mem. Neural Networks (Inform. Opt.), 2012, vol. 21, no. 4, pp. 219–226.
Wang, H., Wang, Y., and Cao, Y., Video-based face recognition: a survey, World Acad. Sci. Eng. Technol., 2009, vol. 60, pp. 293–302.
Huang, Z., Wang, R., Shan, S., and Chen, X., Projection metric learning on Grassmann manifold with application to video based face recognition. Proc. of Int. Conf. on Computer Vision and Pattern Recognition (CVPR), IEEE, 2015, pp. 140–149.
LeCun, Y., Bengio, Y., and Hinton, G., Deep learning, Nature, 2015, vol. 521, no. 7553, pp. 436–444.
Parkhi, O.M., Vedaldi, A., and Zisserman, A., Deep face recognition, Proc. of the British Machine Vision, 2015, pp. 6–17.
Savchenko, A.V., Search Techniques in Intelligent Classification Systems, Switzerland: Springer International Publishing, 2016, p. 83.
Savchenko, A.V., Maximum-likelihood approximate nearest neighbor method in real-time Image recognition, Pattern Recognition, 2017, vol. 61, pp. 459–469.
Viola, P. and Jones, M., Rapid object detection using a boosted cascade of simple features, Proc. of Int. Conf. on Computer Vision and Pattern Recognition (CVPR), IEEE, 2001, pp. 511–518.
Tresp, V., Committee machines, Handbook for Neural Network Signal Processing, CRC Press, 2001, pp. 135–151.
Lumini, A., Nanni, L., and Brahnam, S., Ensemble of texture descriptors and classifiers for face recognition, Appl. Comput. Inform., 2016.
Prince, S.J., Computer Vision: Models, Learning, and Reference, Cambridge University Press, 2012, p. 598.
Malkov, Y., Ponomarenko, A., Logvinov, A., and Krylov, V., Approximate nearest neighbor algorithm based on navigable small world graphs, Inform. Systems, 2014, vol. 45, pp. 61–68.
Savchenko, A.V., Face recognition in real-time applications: Comparison of directed enumeration method and K-d trees, Proc. of Int. Conf. on Business Informatics Research (BIR), LNBIP, 2012, vol. 128, pp. 187–199.
Silpa-Anan, C. and Hartley, R., Optimised KD-trees for fast image descriptor matching, Proc. of Int. Conf. on Computer Vision and Pattern Recognition (CVPR), IEEE, 2008, pp. 1–8.
Savchenko, A.V., The maximal likelihood enumeration method for the problem of classifying piecewise regular objects, Autom. Remote Control, 2016, vol. 77, no. 3, pp. 443–450.
Burghouts, G., Smeulders, A., and Geusebroek, J.-M., The distribution family of similarity distances, Proc. of Int. Conf. on Advances in Neural Information Processing Systems (NIPS), 2008, pp. 201–208.
P’kalska, E. and Duin, R.P., Classifiers for dissimilarity-based pattern recognition, Proc. of the Int. Conf. on Pattern Recognition (CVPR), IEEE, 2000, pp. 12–16.
Gonzalez, E.C., Figueroa, K., and Navarro, G., Effective proximity retrieval by ordering permutations, IEEE Trans. Pattern Analysis Machine Intelligence, 2008, vol. 30, no. 9, pp. 1647–1658.
Best-Rowden, L., Han, H., Otto, C., Klare, B.F., and Jain, A.K., Unconstrained face recognition: identifying a person of interest from a media collection, IEEE Trans. Inform. Forensics Security, 2014, vol. 9, pp. 2144–2157.
Chellappa, R., Du, M., Turaga, P., and Zhou, S.K., Face tracking and recognition in video, in Handbook of Face Recognition, 2011, pp. 323–351.
Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., and Darrell, T., Caffe: Convolutional architecture for fast feature embedding, Proc. of the 22nd Int. Conf. on Multimedia. ACM, 2014, pp. 675–678.
Savchenko, A.V., Pattern recognition and increasing of the computational efficiency of a parallel realization of the probabilistic neural network with homogeneity testing, Opt. Mem. Neural Networks (Inform. Opt.), 2013, vol. 22, no. 3, pp. 184–192.
Savchenko, A.V., Real-time image recognition with the parallel directed Enumeration method, Proc. of Int. Conf. on Vision Systems (ICVS), LNCS, 2013, vol. 7963, pp. 123–132.
Learned-Miller, E., Huang, G.B., RoyChowdhury, A., Li, H., and Hua, G., Labeled faces in the wild: A survey, in Advances in Face Detection and Facial Image Analysis, 2016, pp. 189–248.
Pinto, N., Stone, Z., Zickler, T., and Cox, D., Scaling up biologically-inspired computer vision: A case study in unconstrained face recognition on Facebook, Proc. of Int. Conf. on Computer Vision and Pattern Recognition (CVPR 2011 Workshops), IEEE, 2011, pp. 35–42.
Wolf, L., Hassner, T., and Maoz, I., Face recognition in unconstrained videos with matched background similarity, Proc. of Int. Conf. on Computer Vision and Pattern Recognition (CVPR), IEEE, 2011, pp. 529–534.
Author information
Authors and Affiliations
Corresponding author
About this article
Cite this article
Savchenko, A.V. Deep neural networks and maximum likelihood search for approximate nearest neighbor in video-based image recognition. Opt. Mem. Neural Networks 26, 129–136 (2017). https://doi.org/10.3103/S1060992X17020102
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.3103/S1060992X17020102