Pattern recognition and increasing of the computational efficiency of a parallel realization of the probabilistic neural network with homogeneity testing

Authors:
A. V. Savchenko
Affiliations:
Business Informatics and Applied Mathematics Department, National Research University Higher School of Economics, Nizhny Novgorod, Russia
Venue:
Optical Memory and Neural Networks
Year:
2013

Citing 19
Cited 1

Probabilistic neural networks

Neural Networks
Support-Vector Networks

Machine Learning
Neural networks for pattern recognition

Neural networks for pattern recognition
An optimal algorithm for approximate nearest neighbor searching fixed dimensions

Journal of the ACM (JACM)
Analysis of an Algorithm for Finding Nearest Neighbors in Euclidean Space

ACM Transactions on Mathematical Software (TOMS)
Optimal Expected-Time Algorithms for Closest Point Problems

ACM Transactions on Mathematical Software (TOMS)
Computer Vision: A Modern Approach

Computer Vision: A Modern Approach
Shape Indexing Using Approximate Nearest-Neighbour Search in High-Dimensional Spaces

CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision
Histograms of Oriented Gradients for Human Detection

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Using the Language MC# for the Implementation of a Parallel Pattern Classifier

Cybernetics and Systems Analysis
Local invariant feature detectors: a survey

Foundations and Trends® in Computer Graphics and Vision
Similarity grid for searching in metric spaces

DELOS'04 Proceedings of the 6th Thematic conference on Peer-to-Peer, Grid, and Service-Orientation in Digital Library Architectures
Directed enumeration method in image recognition

Pattern Recognition
Scalable distributed algorithm for approximate nearest neighbor search problem in high dimensional general metric spaces

SISAP'12 Proceedings of the 5th international conference on Similarity Search and Applications
Statistical recognition of a set of patterns using novel probability neural network

ANNPR'12 Proceedings of the 5th INNS IAPR TC 3 GIRPR conference on Artificial Neural Networks in Pattern Recognition
Adaptive video image recognition system using a committee machine

Optical Memory and Neural Networks
Probabilistic neural network with homogeneity testing in recognition of discrete patterns set

Neural Networks
Real-time image recognition with the parallel directed enumeration method

ICVS'13 Proceedings of the 9th international conference on Computer Vision Systems

About neural-network algorithms application in viseme classification problem with face video in audiovisual speech recognition systems

Optical Memory and Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

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.