论文信息 - A face/object recognition system using FPGA implementation of coarse region segmentation

A face/object recognition system using FPGA implementation of coarse region segmentation

A PC system for recognition of natural scene images including human faces and various objects is proposed. Coarse region segmentation of real images with 64/spl times/64 pixels at the video rate is achieved by using the FPGA implementation of resistive-fuse networks. A flexible template matching based on dynamic-link architecture is performed on our PC system.

[1] T. Morie,et al. Image Segmentation/Extraction Using Nonlinear Cellular Networks and Their VLSI Implementation Using Pulse-Modulation Techniques , 2002, IEICE Trans. Fundam. Electron. Commun. Comput. Sci..

[2] Jin Luo,et al. Resistive Fuses: Analog Hardware for Detecting Discontinuities in Early Vision , 1989, Analog VLSI Implementation of Neural Systems.

[3] Joachim M. Buhmann,et al. Distortion Invariant Object Recognition in the Dynamic Link Architecture , 1993, IEEE Trans. Computers.

[4] Makoto Miyake,et al. A Multi-Functional Cellular Neural Network Circuit Using Pulse Modulation Signals for Image Recognition , 2000 .

[5] T. Morie,et al. Coarse Image Region Segmentation Using Resistive-fuse Networks Implemented in FPGA , 2003 .

[6] Takashi Matsumoto,et al. A Floating-Gate MOS Implementation of Resistive Fuse , 1998, Neural Computation.

[7] John L. Wyatt,et al. CMOS resistive fuses for image smoothing and segmentation , 1992 .

[8] Atsushi Iwata,et al. DESIGN OF A PIXEL-PARALLEL FEATURE EXTRACTION VLSI SYSTEM FOR BIOLOGICALLY-INSPIRED OBJECT RECOGNITION METHODS , 2001 .

[9] Makoto Miyake,et al. A 1-D CMOS PWM Cellular Neural Network Circuit and Resistive-Fuse Network Operation , 2001 .