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%


Electrical and Computer Engineering

Second Department

Computer Science

Keywords and Phrases

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

International Standard Serial Number (ISSN)


Document Type

Article - Journal

Document Version

Final Version

File Type





© 2006 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.

Full Text Link