Skip to main content
Journal cover image

A Neuromorphic Architecture for Context Aware Text Image Recognition

Publication ,  Journal Article
Qiu, Q; Li, Z; Ahmed, K; Liu, W; Habib, SF; Li, H; Hu, M
Published in: Journal of Signal Processing Systems
September 1, 2016

Although existing optical character recognition (OCR) tools can achieve excellent performance in text image detection and pattern recognition, they usually require a clean input image. Most of them do not perform well when the image is partially occluded or smudged. Humans are able to tolerate much worse image quality during reading because the perception errors can be corrected by the knowledge in word and sentence level context. In this paper, we present a brain-inspired information processing framework for context-aware Intelligent Text Recognition (ITR) and its acceleration using memristor based crossbar array. The ITRS has a bottom layer of massive parallel Brain-state-in-a-box (BSB) engines that give fuzzy pattern matching results and an upper layer of statistical inference based error correction. Optimizations on each layer of the framework are introduced to improve system performance. A parallel architecture is presented that incorporates the memristor crossbar array to accelerate the pattern matching. Compared to traditional multicore microprocessor, the accelerator has the potential to provide tremendous area and power savings and more than 8,000 times speedups.

Duke Scholars

Altmetric Attention Stats
Dimensions Citation Stats

Published In

Journal of Signal Processing Systems

DOI

EISSN

1939-8115

ISSN

1939-8018

Publication Date

September 1, 2016

Volume

84

Issue

3

Start / End Page

355 / 369

Related Subject Headings

  • Networking & Telecommunications
  • Computer Hardware & Architecture
  • 4611 Machine learning
  • 4008 Electrical engineering
  • 4006 Communications engineering
  • 0906 Electrical and Electronic Engineering
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Qiu, Q., Li, Z., Ahmed, K., Liu, W., Habib, S. F., Li, H., & Hu, M. (2016). A Neuromorphic Architecture for Context Aware Text Image Recognition. Journal of Signal Processing Systems, 84(3), 355–369. https://doi.org/10.1007/s11265-015-1067-4
Qiu, Q., Z. Li, K. Ahmed, W. Liu, S. F. Habib, H. Li, and M. Hu. “A Neuromorphic Architecture for Context Aware Text Image Recognition.” Journal of Signal Processing Systems 84, no. 3 (September 1, 2016): 355–69. https://doi.org/10.1007/s11265-015-1067-4.
Qiu Q, Li Z, Ahmed K, Liu W, Habib SF, Li H, et al. A Neuromorphic Architecture for Context Aware Text Image Recognition. Journal of Signal Processing Systems. 2016 Sep 1;84(3):355–69.
Qiu, Q., et al. “A Neuromorphic Architecture for Context Aware Text Image Recognition.” Journal of Signal Processing Systems, vol. 84, no. 3, Sept. 2016, pp. 355–69. Scopus, doi:10.1007/s11265-015-1067-4.
Qiu Q, Li Z, Ahmed K, Liu W, Habib SF, Li H, Hu M. A Neuromorphic Architecture for Context Aware Text Image Recognition. Journal of Signal Processing Systems. 2016 Sep 1;84(3):355–369.
Journal cover image

Published In

Journal of Signal Processing Systems

DOI

EISSN

1939-8115

ISSN

1939-8018

Publication Date

September 1, 2016

Volume

84

Issue

3

Start / End Page

355 / 369

Related Subject Headings

  • Networking & Telecommunications
  • Computer Hardware & Architecture
  • 4611 Machine learning
  • 4008 Electrical engineering
  • 4006 Communications engineering
  • 0906 Electrical and Electronic Engineering