A VLSI architecture for 3-D self-organizing map based color quantization and its FPGA implementation

Authors:
N. Sudha;T. Srikanthan;Babu Mailachalam
Affiliations:
Department of Electrical Engineering, Indian Institute of Technology, Madras, India;Center for High Performance Embedded Systems, Nanyang Technological University, Singapore 639798, Singapore;Lattice Semiconductors
Venue:
Journal of Systems Architecture: the EUROMICRO Journal
Year:
2003

Citing 4
Cited 4

Color image quantization by minimizing the maximum intercluster distance

ACM Transactions on Graphics (TOG)
Self-organizing maps

Self-organizing maps
An adaptive clustering algorithm for color quantization

Pattern Recognition Letters
Color image compression and limited display using self-organization Kohonen map

IEEE Transactions on Circuits and Systems for Video Technology

A novel Kohonen SOM-based image compression architecture suitable for moderate density FPGAs

Image and Vision Computing
A novel hardware-oriented Kohonen SOM image compression algorithm and its FPGA implementation

Journal of Systems Architecture: the EUROMICRO Journal
Utilization of a fast MSE calculation approach to improve the image quality and accelerate the operation of a hardware K-SOM quantizer

Microprocessors & Microsystems
Utilization of a rational-based representation to improve the image quality of a hardware-based K-SOM quantizer

Journal of Real-Time Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Color quantization is the process of computing a color palette containing few best colors from a full color image and then associating to each pixel of the image, a color from the palette to yield a color quantized image that is close to the original image. It is of interest in applications such as digital display and image capture. To satisfy real time require, ments, it is of vital importance to perform color quantization as fast as possible. This paper presents a novel architecture of a hardware unit for color quantization that is based on Kohonen's self-organizing map. The proposed architecture is of the SIMD type and results in a scheme with linear time complexity (in the size of the image). The architecture has been implemented in Xilinx FPGA and results show that the proposed design achieves high speed taking only a few milliseconds for color quantization of images up to size of 512 × 512 with low area requirement.