Scene segmentation using neuromorphic oscillatory networks
Authors:
- 10 November 2003
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 14 (5) , 1278-1296
Abstract
Using the neuromorphic approach, we propose an analog very large-scale integration (VLSI) implementation of an oscillatory segmentation algorithm based on local excitatory couplings and global inhibition. The original model has been simplified and adapted for its efficient VLSI implementation while preserving its segmentation properties. To demonstrate the feasibility of the approach, a 16/spl times/16-pixel testchip has been manufactured. Extensive experimental results demonstrate that it can properly segment binary images. Power consumption, segmentation time per cell, and system complexity are very low compared to other hardware and software implementation schemes. We also show two main differences between the original algorithm and the analog approach. First, the network is noise tolerant without the need of additional elements and second, delays between oscillators due to the combination of mismatch and output capacitances have to be accounted for network performance.Keywords
This publication has 24 references indexed in Scilit:
- A VLSI implementation of a neuromorphic network for scene segmentation2003
- Motion segmentation based on motion/brightness integration and oscillatory correlationIEEE Transactions on Neural Networks, 2000
- A neural network for scene segmentation based on compact astable oscillators1999
- Segmentation of medical images using LEGIONIEEE Transactions on Medical Imaging, 1999
- ANALOG VLSI IMPLEMENTATION OF A RELAXATION OSCILLATOR FOR NEUROMORPHIC NETWORKS1998
- Fast numerical integration of relaxation oscillator networks based on singular limit solutionsIEEE Transactions on Neural Networks, 1998
- Modelling the perceptual segregation of double vowels with a network of neural oscillatorsNeural Networks, 1997
- Image Segmentation Based on Oscillatory CorrelationNeural Computation, 1997
- A CMOS implementation of FitzHugh-Nagumo neuron modelIEEE Journal of Solid-State Circuits, 1991
- CMOS current schmitt trigger with fully adjustable hysteresisElectronics Letters, 1989