Enhanced layer based compound image compression

Abstract

Information explosion along with the tremendous growth in software and hardware technology are moving industries, educational institutions, organizations towards "paperless" environment. This change has a direct impact on the amount of information digitized, thus increasing the need for efficient storage mechanisms. Digitized information mostly consist of compound images, which are a combination of different data types like text, graphics, line art, photographs, etc. Layer based compression is one of the frequently used solution to compress these kind of images. This paper proposes a novel layer based compound image compression technique. Care is taken to produce lossless compression for text part of the image and to improve the quality of the image as a whole after decompression. Experimental results were conducted to analyze the performance of the proposed compressor.

Elaboration of structural representation of regions of scanned document images for MRC model

“…If for some reason the MRC is not suitable for representing a particular image, you can select only one layer and compress it using the appropriate compression method. In [2,3,[5][6][7][8], the RC representation was used mainly for compressing images containing text and illustrations. Segmentation was a preliminary stage of processing for the subsequent compression of images.…”

“…Thus, in [2], the image of the scanned document was represented as a set of text and non-text regions, the latter including photos and graphics. In [2,3], the RC representation of the MRC model was used to construct a two-level model of the image of a scanned document. At first such an image was divided into blocks, each of which belonged to one of five classes: background, text, photo, graphics, and also an overlapping block that could contain fragments of blocks of the first four classes.…”

A Survey of Interactive Remote Rendering Systems

“…Shape Primitive Extraction and Coding (SPEC) [Lin and Hao 2005] segments each image into texts/graphics and natural image regions, and encodes the texts/graphics regions using a lossless compression algorithm, and the natural regions using JPEG. A similar idea was proposed by Maheswari and Radha in [2010]. Wang and Lin [2009] proposed to concurrently compress each macroblock using H.264 [Wiegand et al 2003] and gzip [Gailly 1992], and choose the better compressed macroblock in the rate-distortion fashion; they later proposed a generalized system called United Coding (UC) [Wang and Lin 2012] based on multiple lossless coders, such as Run-Length Encoding (RLE), gzip, and Portable Network Graphics (PNG).…”

Image compression based on genetic algorithm optimization

“…Therefore, many approches that aim to reduce the size of raw images and videos have been proposed in the literature. Digital image compression is considered to be a mature branch in image processing area, where several researches have already focused on developing algorithms that produce good compression rates with adequate image quality [3]. Image compression methods are of different approaches, but most of them focus on the characteristics of image data to produce good compression results.…”