Missouri S&T Scholar's Mine Research RepositoryMissouri S&T Research
print 
Title: Permutation coding technique for image recognition systems
Author (s): Kussul, E. M.
Baidyk, T. N.
Wunsch, Donald C.
Makeyev, O.
Martn, A.
Department/Lab Affiliations: Applied Computational Intelligence Laboratory
Electrical and Computer Engineering
Keywords: MNIST database
Olivetti Research Laboratory (ORL) database
face recognition
feature extraction
handwritten digit recognition
image coding
image recognition
image recognition systems
neural classifier
neural nets
permutation coding neural classifier
permutation coding technique
random local descriptors
Issue Date: 2006
Publisher: Institute of Electrical and Electronics Engineers
Citation: Kussul, E. M.; Baidyk, T. N.; Wunsch II, D. C.; Makeyev, O.; Martn, A. "Permutation Coding Technique for Image Recognition Systems" IEEE Transactions on Neural Networks, Vol.17, Iss.6, Nov. 2006 Pages:1566-1579
Abstract: A feature extractor and neural classifier for image recognition systems are proposed. The proposed feature extractor is based on the concept of random local descriptors (RLDs). It is followed by the encoder that is based on the permutation coding technique that allows to take into account not only detected features but also the position of each feature on the image and to make the recognition process invariant to small displacements. The combination of RLDs and permutation coding permits us to obtain a sufficiently general description of the image to be recognized. The code generated by the encoder is used as an input data for the neural classifier. Different types of images were used to test the proposed image recognition system. It was tested in the handwritten digit recognition problem, the face recognition problem, and the microobject shape recognition problem. The results of testing are very promising. The error rate for the Modified National Institute of Standards and Technology (MNIST) database is 0.44% and for the Olivetti Research Laboratory (ORL) database it is 0.1%
Type: Article - Journal
text
Copyright Notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.
FULL COPYRIGHT INFORMATION:
http://www.ieee.org/web/publications/rights/policies.html
Publisher URL:
http://ieeexplore.ieee.org/iel5/72/4012015/04012029.pdf?arnumber=401202
Link to this page:
http://scholarsmine.mst.edu/post_prints/04012029_09007dcc8030dbca.html
Full Text:
04012029_09007dcc8030dbcf.pdf



titlePermutation coding technique for image recognition systems
contributor.authorKussul, E. M.
contributor.authorBaidyk, T. N.
contributor.authorWunsch, Donald C.
contributor.authorMakeyev, O.
contributor.authorMartn, A.
contributor.deptlabApplied Computational Intelligence Laboratory
contributor.deptlabElectrical and Computer Engineering
subjectMNIST database
subjectOlivetti Research Laboratory (ORL) database
subjectface recognition
subjectfeature extraction
subjecthandwritten digit recognition
subjectimage coding
subjectimage recognition
subjectimage recognition systems
subjectneural classifier
subjectneural nets
subjectpermutation coding neural classifier
subjectpermutation coding technique
subjectrandom local descriptors
date.issued2006
date.submitted2007
publisherInstitute of Electrical and Electronics Engineers
identifier.citationKussul, E. M.; Baidyk, T. N.; Wunsch II, D. C.; Makeyev, O.; Martn, A. "Permutation Coding Technique for Image Recognition Systems" IEEE Transactions on Neural Networks, Vol.17, Iss.6, Nov. 2006 Pages:1566-1579
identifier.issn1045-9227
identifier.pub.URI
http://ieeexplore.ieee.org/iel5/72/4012015/04012029.pdf?arnumber=401202
description.abstractA feature extractor and neural classifier for image recognition systems are proposed. The proposed feature extractor is based on the concept of random local descriptors (RLDs). It is followed by the encoder that is based on the permutation coding technique that allows to take into account not only detected features but also the position of each feature on the image and to make the recognition process invariant to small displacements. The combination of RLDs and permutation coding permits us to obtain a sufficiently general description of the image to be recognized. The code generated by the encoder is used as an input data for the neural classifier. Different types of images were used to test the proposed image recognition system. It was tested in the handwritten digit recognition problem, the face recognition problem, and the microobject shape recognition problem. The results of testing are very promising. The error rate for the Modified National Institute of Standards and Technology (MNIST) database is 0.44% and for the Olivetti Research Laboratory (ORL) database it is 0.1%
typeArticle - Journal
type.DCMITypetext
type.statusFinal version
rightsThis material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.
rights.URI
http://www.ieee.org/web/publications/rights/policies.html
date.accessioned2007-04-05T14:28:28Z
date.available2007-04-05T14:28:28Z
identifier.persist.URI
http://scholarsmine.mst.edu/post_prints/04012029_09007dcc8030dbca.html
Full Text
04012029_09007dcc8030dbcf.pdf