Silicon Models of Visual Cortical Processing - Neural Networks, 1996., IEEE International Conference on
نویسنده
چکیده
Receptive field structures found in the visual cortex of the mammalian brain act as oriented, localized spatial frequency filters. There has been recent interest in the use of such receptive field profiles for image coding and texture processing. These receptive field structures resemble Gabor filters. Systems employing such Gabor filters have been implemented in software for a variety of applications. We believe a hardware implementation of such cells will be helpful in artificial visual processing. We have implemented analog VLSI cells whose outputs resemble the receptive field profiles found in the visual cortex. We describe experimental results of our circuit. Our circuit is the first silicon model of visual cortical processing.
منابع مشابه
Biologically-Inspired Cognitive Architecture for Integrated Learning, Action and Perception (BICA-LEAP)
s/Presentations/Posters/Conference Proceedings Khosla D.,&Moore C.,et al. Online visual attention and recognition, submitted to SPIE Defense and Security Symposium Khosla D.& Moore C. et al. A bio-inspired system for Spatio-temporal Recognition in Static and Video Imagery, submitted to SPIE Defense and Security Symposium. Itti L., Dhavale N.,& Pighin F. Photorealistic attention-based gaze anima...
متن کاملSynaptic Weight Generation in VLSI Stochastic Neural Networks. - Neural Networks, 1995. Proceedings., IEEE International Conference on
Fully parallel stochastic neural network implementations can be realized nowdays. However, in these implementations most of the silicon area is consumed in the stochastic pulse sequence generation circuits. In order to improve their efficiency in terms of consumed silicon area, new techniques must be developped. This is specially important in applications where a large number of synaptic weight...
متن کاملThe Silicon Vocal Tract - Neural Networks, 1996., IEEE International Conference on
The human vocal tract has been successfully modeled as a series of uniform cross-section tubes concatenated end-to-end. Such a model has been part of the study of the human speech generation system for many years. The similarity of the equations for sound propagation in these tubes and transmission line equations has been exploited in articulatory speech synthesis systems. Each section of tube ...
متن کاملThe VI International Conference on Arti cial Neural NetworksICANN
Artiicial neural networks achieve fast parallel processing via massively parallel non-linear computational elements. Most neural network models base their ability to adapt to problems on changing the strength of the interconnections between computational elements according to a given learning algorithm. However, constrained interconnection structures may limit such ability. Field programmable h...
متن کاملEfficient Lossless Coding of Medical Image Volumes Using Reversible Integer Wavelet Transforms
of 1996 Data Compression Conference, 1996, p. 436. [22] C. S. Barreto and G. V. Mendonca, “Enhanced zerotree wavelet transform image coding exploiting similarities inside subbands,” in Proc. of International Conference on Image Processing, 1996, vol. 2, pp. 549–551. [23] X. Wu and J.-H. Chen, “Context modeling and entropy coding of wavelet coefficients for image compression,” in Proc. of 1997 I...
متن کامل