Block-based histogram packing of color-quantized images
نویسندگان
چکیده
Reordering the color table of color-quantized images is a very effective approach towards the improvement of the compression efficiency of color-indexed images. In this paper, we provide experimental results showing that, for images generated by colorquantization of full color natural images, histogram packing applied on a block basis is able to provide additional compression improvements of around 15%. In other words, we show that the improvements provided by a global color table reordering can be further increased by applying a local preprocessing technique which packs the histograms of regions (blocks) of the index image.
منابع مشابه
Variable Size Block-Based Histogram Packing For Lossless Coding of Color-Quantized Images
Previous work has shown that the lossless compression of color-quantized images, by general purpose continuoustone encoders, can be improved if histogram packing is performed on a block by block basis, prior to compression. In this paper, we extend this idea, proposing an algorithm that adaptively finds a more appropriate region size for histogram packing. With this new algorithm, a balance bet...
متن کاملJPEG 2000 coding of color-quantized images
The efficiency of compressing color-quantized images using general purpose lossless image coding methods depends on the degree of smoothness of the index images. A wellknown and very effective approach for increasing smoothness relies on palette reordering techniques. In this paper, we show that these reordering methods may leave some room for further improvements in the compression performance...
متن کاملColor scene transform between images using Rosenfeld-Kak histogram matching method
In digital color imaging, it is of interest to transform the color scene of an image to the other. Some attempts have been done in this case using, for example, lαβ color space, principal component analysis and recently histogram rescaling method. In this research, a novel method is proposed based on the Resenfeld and Kak histogram matching algorithm. It is suggested that to transform the color...
متن کاملEnhancing Content-based Image Retrieval using Moving K-Means Clustering Algorithm
In this paper, new content-based image retrieval (CBIR) system based on color and shape feature combining with clustering concept that considers the similarities among images in database is proposed. Firstly, the color space of an image is quantized with 128 bin quantization and then color histogram is extracted from the quantized image. Secondly, the shape feature is extracted using horizontal...
متن کاملEnhancing Content-based Image Retrieval using Moving K-Means Clustering Algorithm
In this paper, new content-based image retrieval (CBIR) system based on color and shape feature combining with clustering concept that considers the similarities among images in database is proposed. Firstly, the color space of an image is quantized with 128 bin quantization and then color histogram is extracted from the quantized image. Secondly, the shape feature is extracted using horizontal...
متن کامل