Toward color image segmentation in analog VLSI: Algorithm and hardware

  title={Toward color image segmentation in analog VLSI: Algorithm and hardware},
  author={Frank Perez and Christof Koch},
  journal={International Journal of Computer Vision},
  • F. Perez, C. Koch
  • Published 1 February 1994
  • Computer Science
  • International Journal of Computer Vision
Standard techniques for segmenting color images are based on finding normalized RGB discontinuities, color histogramming, or clustering techniques in RGB or CIE color spaces. The use of the psychophysical variable hue in HSI space has not been popular due to its numerical instability at low saturations. In this article, we propose the use of a simplified hue description suitable for implementation in analog VLSI. We demonstrate that if theintegrated white condition holds, hue is invariant to… 

A Vision Chip for Color Segmentation and Pattern Matching

To the knowledge, this is the first chip that integrates imaging, color segmentation, and color-based object recognition at the focal plane and it uses 1 mW.

ColorCam: a color-based object recognition camera (Invited Paper)

To the authors' knowledge, this is the first chip that integrates imaging, color segmentation and color-based object recognition at the focal plane and it uses 1mW.

Edge Steered Region Segmentation by Photometric Color

Experiments show that the proposed segmentation methods are able to generate proper segmentation results independent of viewpoint of the camera, orientation of the object, direction and intensity of the illumination, and highlights.

A Taxonomy of Color Constancy and Invariance Algorithm

This chapter investigates two common methodologies to attain reliable color description of recorded image data, color constancy and color invariance.

Color Image Segmentation : A State-ofthe-Art Survey

This paper provides a review of methods advanced in the past few years for segmentation of color images and various techniques, ofted from the background of gray-level image segmentation, have been proposed.

Shadow segmentation and tracking in real-world conditions

The problem of separating moving cast shadows from moving objects in image sequences is particularly relevant for an always wider range of applications, ranging from video analysis to video coding, and from video manipulation to interactive environments, Therefore, particular attention has been dedicated to the segmentation of shadows in video.


Compared to traditional edge detection methods, this method can improve the accuracy of edge detection and withstand greater levels of noise in images; and the GPU implementation achieves speedups over related CUDA implementations.

On the Reliability Degree of Hue and Saturation Values of a Pixel for Color Image Classification

A method is proposed that, based on predicted hue and saturation deviations, provides the reliability degree of the H-S color components based obtained HIS values.



Color gamut transform pairs

A set of alternative models of the RGB monitor gamut based on the perceptual variables hue, saturation, and value (V) or brightness (L) are presented and algorithms for transforming between these models are derived.

A color clustering technique for image segmentation

  • M. Celenk
  • Computer Science
    Comput. Vis. Graph. Image Process.
  • 1990

Expansion of color images using three perceptual attributes

  • S. Tominaga
  • Environmental Science
    Pattern Recognit. Lett.
  • 1987

An experimental comparison of RGB, YIQ, LAB, HSV, and opponent color models

A color matching experiment in which subjects used one of two tablet-based input techniques, interfaced through one of five color models, to interactively match target colors displayed on a CRT shows small but significant differences between models in the ability of subjects to match the five target colors.

The measurement of highlights in color images

An approach to color image understanding that accounts for color variations due to highlights and shading, and presents a method that exploits the difference between object color and highlight color to separate the color of every pixel into a matte component and a highlight component.

Using color to separate reflection components

This paper presents an algorithm for analyzing a standard color image to determine intrinsic images of the amount of interface (specular) and body (diffuse) reflection at each pixel, based upon a physical model of reflection.

Color information for region segmentation

A physical approach to color image understanding

  • G. Klinker
  • Physics
    International Journal of Computer Vision
  • 2004
An approach to color image understanding that can be used to segment and analyze surfaces with color variations due to highlights and shading and is capable of generating physical descriptions of the reflection processes occurring in the scene.

A color classification method for color images using a uniform color space

  • S. Tominaga
  • Art
    [1990] Proceedings. 10th International Conference on Pattern Recognition
  • 1990
A color classification method that partitions color image data into a set of uniform color regions is described, showing that a fundamental set of colors composing an image with shades and shadows is extracted at the basic classification stage and that the objects in the original image are extracts at the reclassification stage.

Color vision and image intensities: When are changes material?

In this paper, a preliminary goal for color vision is proposed and analyzed, and it is shown there is a minimal and unique condition, the spectral crosspoint, that rejects instances of these confounding processes.