Abstract
A new hierarchical Walsh memory which can store and quickly recognize any number of patterns is proposed. A Walsh function based associative memory was found to be capable of storing and recognizing patterns in parallel via purely a software algorithmic technique (namely, without resorting to parallel hardware) while the memory itself only takes a single pattern space of computer memory, due to the Walsh encoding of each pattern. This type of distributed associative memory lends itself to high speed pattern recognition and has been reported earlier in a single memory version. In this paper, the single memory concept has first been extended to a parallel memory module and then to a tree-shaped hierarchy of these parallel modules that are capable of storing and recognizing any number of patterns for practical large scale data applications exemplified by image and speech recognition.
The memory hierarchy was built by successively applying k-means clustering to the training data set. In the proposed architecture, the clustered data subsets are stored respectively into a parallel memory module where the module allocation is optimized using the genetic algorithm to realize a minimal implementation of the memory structure. The system can recognize all the training patterns with 100% accuracy and further, can also generalize on similar data. In order to demonstrate its efficacy with large scale real world data, we stored and recognized over 500 faces while at same time, achieving much reduced recognition time and storage space than template matching.
Similar content being viewed by others
References
Brunelli R, Poggio T (1993) Face recognition: features versus templates. IEEE Trans Pattern Anal Mach Intell 15(10):1042–1049
Jolliffe IT (1986) Principal component analysis. Springer, Berlin
Zhang H, Zhang B, Huang W, Tian Q (2005) Gabor wavelet associative memory for face recognition. IEEE Trans Neural Netw 16(1):275–278
Sim T, Sukthankar R, Mullin M, Baluja S (2000) Memory-based face recognition for visitor identification. In: Proc IEEE int conf face and gesture, pp 214–220
Kohonen T (1984) Self-organization and associative memory. Springer, Berlin
Kosko B (1988) Bidirectional associative memories. IEEE Trans Syst Man Cybern 18(1):49–60
Kang H (1994) Multilayer associative neural networks (MANN’s): Storage capacity versus perfect recall. IEEE Trans Neural Netw 5(5):812–822
Murdock BB Jr (1982) A theory for the storage and retrieval of item and associative information. Psychol Rev 89(6):609–626
Eich JM (1982) A composite holographic associative recall model. Psychol Rev 89(6):627–661
Beauchamp KG (1984) Applications of Walsh and related functions with an introduction to sequency theory. Academic Press, San Diego
Pao YH, Merat FL (1975) Distributed associative memory for patterns. IEEE Trans Syst Man Cybern 5:620–625
Schultz WL (1979) Characteristics and applications of distributed associative memory algorithms. PhD Thesis, Case Western Reserve University
Oh SY (1984) A Walsh-Hadamard based distributed storage device for the associative search of information. IEEE Trans Pattern Anal Mach Intell 6(5):617–623
Oh SY (1986) A pattern recognition and associative memory approach to power system security assessment. IEEE Trans Syst Man Cybern 16(1):62–72
Kim K-A, Oh S-Y (2003) A Walsh-based distributed associative memory with genetic algorithm maximization of storage capacity for face recognition. In: International symposium on advanced intelligent systems (ISIS), Jeju, Korea, pp 640–643, September 2003
Han SJ, Oh SY (2006) Enhanced Walsh function based distributed associative memory for pattern recognition. In: Proc int joint conf neural networks, Vancouver, Canada, pp 7025–7030, July 2006
Goldberg DE (1989) Genetic algorithms in search, optimization, and machine learning. Addison–Wesley, Reading
Image Group, Information Access Division, ITL, NIST (2001) FERET Facial Image Database Release 2, March, 2001
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Han, SJ., Oh, SY. A new paradigm for real-time parallel storage and recognition of patterns based on a hierarchical organization of associative memories utilizing Walsh function encoding. Appl Intell 31, 305–317 (2009). https://doi.org/10.1007/s10489-008-0128-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-008-0128-9