Book ChapterDOI
A color classification algorithm for color images
Shoji Tominaga
- pp 163-172
Reads0
Chats0
TLDR
In this article, a color classification algorithm that partitions color image data into a set of uniform color regions is described, which can be divided into two main steps: first, the device dependent image data is mapped into an approximately uniform perceptual color space, and then the histogram analysis is applied to the data represented in this perceptually uniform space.Abstract:
We describe a color classification algorithm that partitions color image data into a set of uniform color regions. The algorithm uses a recursive method to detect clusters of color data. The algorithm can be divided into two main steps. First, we map the device dependent image data into an approximately uniform perceptual color space. Second, we apply a recursive histogram analysis to the data represented in this perceptually uniform space. The histogram analysis is designed to identify the spatial subregions within the image that correspond to a uniform color. Once a region has been identified, the corresponding data are removed and the histogram analysis is repeated on the remaining data set. The performance of the algorithm is discussed with respect to a test image.read more
Citations
More filters
Proceedings ArticleDOI
A color classification method for color images using a uniform color space
TL;DR: 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.
Journal ArticleDOI
A hierarchical and scalable model for contemporary document image segmentation
TL;DR: A novel color segmentation approach robust against digitization noise and adapted to contemporary document images is introduced, which is scalable, hierarchical, versatile and completely automated, i.e. user independent.
A hierarchical and scalable model for contemporary document image segmentation
TL;DR: In this article, a color seg- mentation approach robust against digitization noise and adapted to contemporary document images is proposed. But it is not suitable for the use of large scale images, and the color segmentation output is used to localize text areas and enhance optical character recognition.
References
More filters
Journal ArticleDOI
Color information for region segmentation
TL;DR: In this article, a set of color features, (R + G + B) 3, R − B, and (2G − R− B) 2, were derived by systematic experiments of region segmentation.
Book
Color in Business, Science and Industry
TL;DR: For a number of years the Optical Society of America has run parallel sessions one of which is devoted to papers on spectroscopy and the other one devoted to articles on color as mentioned in this paper, with the ardent spectroscopist carefully isolated from color problems since instantaneous transitions between the quantum levels of the Keystone and Georgian rooms have a low probability if they are not altogether excluded by some corollary of the Pauli principle.
Journal ArticleDOI
Picture segmentation using a recursive region splitting method
TL;DR: A general segmentation method which can be applied to many different types of scenes and the potential performance of other segmentation techniques on general scenes is discussed.
Journal ArticleDOI
Expansion of color images using three perceptual attributes
TL;DR: A mapping method for transforming the measured images into the color space pixel-by-pixel, and obtaining the estimated attribute images of Hue, Value, and Chroma is presented.