No abstract

No abstract

We propose a convolutional spiking neural network (CSNN) model with population coding for robust face detection. Basic structure of the network includes hierarchically alternating layers for feature detection and feature pooling. The proposed model implements hierarchical template matchmg by temporal integration of structured pulse packet. The packet signal represents some intermediate or complex visual feature (e.g., a pair of line segments, comers, eye, nose, etc.) that constitutes a face model. The output pulse of a feature pooling neuron represents some local feature (e.g., line segments). Introducing a population coding scheme in the CSNN architecture, we show how the biologically inspired model attains invariance to changes in size and position of face and ensures the efficiency of face detection.

Abstract. Hierarchical convolutional neural networks are a well-known robust image-recognition model. In order to apply this model to robot vision or various intelligent vision systems, its VLSI implementation with high performance and low power consumption is required. This paper proposes a convolutional network VLSI architecture using a hybrid approach composed of pulse-width modulation (PWM) and digital circuits. We call this approach merged/mixed analog-digital architecture. The VLSI includes PWM neuron circuits, PWM/digital converters, digital adder-subtracters, and digital memory. We have designed and fabricated a VLSI chip by using a 0.35 m CMOS process. The VLSI chip can perform 6-bit precision convolution calculations for an image of 100¢100 pixels with a receptive field area of up to 20¢20 pixels within 5 ms, which means a performance of 2 GOPS. Power consumption of PWM neuron circuits is estimated to be 20 mW. We have verified successful operations using a fabricated VLSI chip.

Detection of salient objects in images has been an active area of research in the computer vision community. However, existing approaches tend to perform poorly in noisy environments because probability density estimation involved in the evaluation of visual saliency is not reliable. Recently, a novel machine learning approach that directly estimates the ratio of probability densities was demonstrated to be a promising alternative to density estimation. In this paper, we propose a salient object detection method based on direct density-ratio estimation, and demonstrate its usefulness in experiments.