Pattern recognition and increasing of the computational efficiency of a parallel realization of the probabilistic neural network with homogeneity testing
The research subject is the computational complexity of the probabilistic neural network (PNN) in the pattern recognition problem for large model databases. We examined the following methods of increasing the efficiency of a neural-network classifier: a parallel multithread realization, reducing the PNN to a criterion with testing of homogeneity of feature histograms of input and reference images, approximate nearest-neighbor analyses (Best-Bin First, directed enumeration methods). The approach was tested in facial-recognition experiments with FERET dataset.
Keywordspattern recognition probabilistic neural network test of homogeneity directed enumeration method parallel multithread computations
Unable to display preview. Download preview PDF.
- 2.Forsyth, D.A. and Ponce, J., Computer Vision: A Modern Approach, Pearson Education, Prentice Hall, 2011, p. 792.Google Scholar
- 3.Lapko, A.V. and Lapko, V.A., Nonparametric pattern recognition systems in the conditions of large learning samples, Pattern Recognition and Image Analysis, (Advances in Mathematical Theory and Applications), 2010, vol. 20, no. 2, pp. 129–136.Google Scholar
- 5.Savchenko, A.V., Statistical Recognition of a Set of Patterns Using Novel Probability Neural Network (Proc. of Int. Conf. ANNPR’12 LNCS), 2012, vol. 7477, pp. 93–103.Google Scholar
- 6.Borovkov, A.A., Mathematical Statistics: Additional Chapters, Nauka, 1984, p. 144.Google Scholar
- 10.Beis, J. and Lowe, D.G., Shape indexing using approximate nearest-neighbour search in high dimensional spaces (Proc. of Int. Conf. on Computer Vision and Pattern Recognition), 1997, pp. 1000–1006.Google Scholar
- 15.Savchenko, A.V., Real-time image recognition with the parallel directed enumeration method (Proc. of Int. Conf. ICVS 2013 LNCS), 2013, vol. 7963, pp. 123–132.Google Scholar
- 18.Malkov, Y., Ponomarenko, A., Logvinov, A., and Krylov, V., Scalable distributed algorithm for approximate nearest neighbor search problem in high dimensional general metric spaces (Proc. of Int. Conf SISAP’12 LNCS), 2012, vol. 7404, pp. 132–147.Google Scholar
- 20.Batko, M., Gennaro, C., and Zezula, P., Similarity Grid for Searching in Metric Spaces (Proc. of Int. Conf. DELOS LNCS), 2005, vol. 3664, pp. 25–44.Google Scholar
- 21.Beaumont, O., Kermarrec, A.-M., Marchal, L., and Riviere, E., VoroNet: A scalable object network based on Voronoi tessellations (Proc. of Int. Symposium Parallel and Distributed Processing), 2007, pp. 1–10.Google Scholar
- 22.Savchenko, A.V., Face Recognition in Real-Time Applications: Comparison of Directed Enumeration Method and K-d Trees (Proc. of Int. Conf. BIR’12 LNBIP), 2012, vol. 128, pp. 187–199.Google Scholar
- 24.The FERET dataset, http://www.itl.nist.gov/iad/humanid/feret/feret-master.html
- 25.Dalal, N. and Triggs, B., Histograms of Oriented Gradients for Human Detection. Proceedings (Proc. of Int. Conf. on Computer Vision & Pattern Recognition), 2005, pp. 886–893.Google Scholar