1 May 2017 Contemporary deep recurrent learning for recognition
Author Affiliations +
Abstract
Large-scale feed-forward neural networks have seen intense application in many computer vision problems. However, these networks can get hefty and computationally intensive with increasing complexity of the task. Our work, for the first time in literature, introduces a Cellular Simultaneous Recurrent Network (CSRN) based hierarchical neural network for object detection. CSRN has shown to be more effective to solving complex tasks such as maze traversal and image processing when compared to generic feed forward networks. While deep neural networks (DNN) have exhibited excellent performance in object detection and recognition, such hierarchical structure has largely been absent in neural networks with recurrency. Further, our work introduces deep hierarchy in SRN for object recognition. The simultaneous recurrency results in an unfolding effect of the SRN through time, potentially enabling the design of an arbitrarily deep network. This paper shows experiments using face, facial expression and character recognition tasks using novel deep recurrent model and compares recognition performance with that of generic deep feed forward model. Finally, we demonstrate the flexibility of incorporating our proposed deep SRN based recognition framework in a humanoid robotic platform called NAO.
© (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
K. M. Iftekharuddin, M. Alam, L. Vidyaratne, "Contemporary deep recurrent learning for recognition", Proc. SPIE 10203, Pattern Recognition and Tracking XXVIII, 1020302 (1 May 2017); doi: 10.1117/12.2266450; https://doi.org/10.1117/12.2266450
PROCEEDINGS
10 PAGES


SHARE
RELATED CONTENT

Frequency-based pattern recognition using neural networks
Proceedings of SPIE (October 01 1991)
Two-level processing for real-time image understanding
Proceedings of SPIE (April 03 1997)
Object Recognition by a Hopfield Neural Network
Proceedings of SPIE (March 01 1990)
Robust object tracking based on sparse representation
Proceedings of SPIE (August 04 2010)
Recognizing license plate character based on simplified PCNN
Proceedings of SPIE (November 15 2007)
Handwritten digit recognition using neural networks
Proceedings of SPIE (March 01 1992)

Back to Top