Image Recognition Systems based on Random Local Descriptors
Abstract
Two image recognition systems based on Random Local Descriptors are described. Random Local Descriptors play the role of features that have to be extracted from the image. The advantage of this type of features is a possibility to create sufficiently general description of the image. This approach was tested in different image recognition tasks: handwritten digit recognition, face recognition, metal surface texture recognition and micro work piece shape recognition. The best result for handwritten digit recognition on the MNIST database is the error rate of 0.37% and for face recognition on the ORL database is the error rate of 0.1%. The results for texture and micro work piece shape recognition are also promising.
Recommended Citation
E. M. Kussul et al., "Image Recognition Systems based on Random Local Descriptors," Proceedings of the 2006 International Joint Conference on Neural Networks (2006, Vancouver, BC, Canada), pp. 2415 - 2450, Institute of Electrical and Electronics Engineers (IEEE), Jul 2006.
The definitive version is available at https://doi.org/10.1109/IJCNN.2006.247067
Meeting Name
2006 International Joint Conference on Neural Networks, IJCNN '06 (2006: Jul. 16-21, Vancouver, BC, Canada)
Department(s)
Electrical and Computer Engineering
International Standard Book Number (ISBN)
978-0780394902
International Standard Serial Number (ISSN)
1098-7576
Document Type
Article - Conference proceedings
Document Version
Citation
File Type
text
Language(s)
English
Rights
© 2006 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.
Publication Date
21 Jul 2006
