Spiking cortical model for geometry invariant and antinoise texture retrieval

In recent years, CBIR (content-based image retrieval) becomes a new hotspot. In the technology, image querying is achieved based on the characteristics of the color, shape, texture, spatial position of the object or the combination of these features. As the images are the most intuitive contents in the multimedia, content-based image retrieval is a very important problem in the multimedia information processing. Spiking cortical model (SCM) used in this paper is a neural network algorithm that generates a series of binary pulse images when excited by the grayscale or color images. And it has a superior performance in the feature extraction and the texture retrieval of images due to the properties of anti-noise and the geometry invariant of rotation, scale and translation. In order to improve the speed of texture retrieval, SCM is modeled based on FPGA in this paper.

[1]  W. Singer,et al.  Gamma or no gamma, that is the question , 2014, Trends in Cognitive Sciences.

[2]  W. Singer,et al.  Oscillatory responses in cat visual cortex exhibit inter-columnar synchronization which reflects global stimulus properties , 1989, Nature.

[3]  P. Fries.  Neuronal gamma-band synchronization as a fundamental process in cortical computation. , 2009, Annual review of neuroscience.

[4]  Phil Brodatz,et al.  Textures: A Photographic Album for Artists and Designers , 1966 .

[5]  J. L. Johnson,et al.  Observation of periodic waves in a pulse-coupled neural network. , 1993, Optics letters.

[6]  R. Eckhorn,et al.  Coherent oscillations: A mechanism of feature linking in the visual cortex? , 1988, Biological Cybernetics.

[7]  W. Singer,et al.  Gamma oscillations: precise temporal coordination without a metronome , 2013, Trends in Cognitive Sciences.

[8]  Clark S. Lindsey,et al.  INTELLIGENT DETECTORS MODELLED FROM THE CAT'S EYE , 1997 .

[9]  Yide Ma,et al.  New Spiking Cortical Model for Invariant Texture Retrieval and Image Processing , 2009, IEEE Transactions on Neural Networks.

[10]  Yide Ma,et al.  Applications of Pulse-Coupled Neural Networks , 2011 .

[11]  W. Singer,et al.  The gamma cycle , 2007, Trends in Neurosciences.

[12]  John L. Johnson,et al.  Stabilized input with a feedback pulse‐coupled neural network , 1996 .

[14]  Jason M. Kinser,et al.  Simplified pulse-coupled neural network , 1996, Defense + Commercial Sensing.

[15]  G. Buzsáki,et al.  Mechanisms of gamma oscillations. , 2012, Annual review of neuroscience.

[16]  R. Desimone,et al.  Stimulus repetition modulates gamma-band synchronization in primate visual cortex , 2014, Proceedings of the National Academy of Sciences.

[17]  Yide Ma,et al.  A Novel Method of Iris Feature Extraction Based on the ICM , 2006, 2006 IEEE International Conference on Information Acquisition.

[18]  Qiaoqiao Li,et al.  Computational Mechanisms of Pulse-Coupled Neural Networks: A Comprehensive Review , 2016, Archives of Computational Methods in Engineering.