Unlock instant, AI-driven research and patent intelligence for your innovation.

Method for compressing text image

A text image and compression method technology, applied in image coding, image communication, image data processing, etc., can solve the problem that the compression effect is not as good as English text image, etc., and achieve the effect of improving compression rate, high execution efficiency, and improving compression rate

Active Publication Date: 2013-05-29
PEKING UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Due to the large number of symbols in Chinese, when the above-mentioned method based on pattern matching technology is used to compress Chinese text images, the compression effect is not as good as that of English text images.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method for compressing text image
  • Method for compressing text image
  • Method for compressing text image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] Below in conjunction with accompanying drawing and embodiment the present invention will be further described:

[0033] This embodiment takes specific text image compression as an example, and describes the text image compression method based on multi-level feature extraction according to the present invention with reference to the accompanying drawings. The example used in this embodiment is to scan an e-book in black and white, and the resolution of the scanned picture is 300dpi.

[0034] figure 1 Shown is the flow chart of the inventive method, and concrete realization step is as follows:

[0035] (1) Read in the input image, and extract the symbols in the image according to a certain algorithm. The extraction of symbols uses the flood-filling algorithm to extract continuous pixel blocks in the image as symbols to be processed.

[0036] (2) Extract multi-level feature data for the extracted symbols. The feature data extracted in this embodiment are as follows:

...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a method for compressing a text image and belongs to the technical field of text image compression. The method provided by the invention comprises the steps of: (1) reading in the text image and extracting symbols in the image; (2) extracting multistage characteristic data in the extracted symbols; (3) clustering the symbols by adopting a clustering algorithm and utilizingthe extracted multistage characteristic data; and (4) compressing the text image according to a result obtained through clustering in the step (3). Compared with the prior art, the method provided bythe invention can be used for increasing the compression ratio of Chinese and English text images; and the execution efficiency of procedures is also higher.

Description

technical field [0001] The invention relates to a text image compression method, which belongs to the technical field of text image compression. Background technique [0002] Text image (Textual Image or Text Image) is a special type of black and white binary image, its main feature is that its content is generally composed of text parts. From the perspective of data compression, text images have two levels of redundancy, bitmap and symbol, and the latter is caused by repeated symbols in the image. At present, the compression standards and algorithms for text images mainly include G3, G4, JBIG and JBIG2, among which G3, G4 and JBIG are all compression methods based on the bitmap level, while JBIG2 is based on two layers of bitmap and symbol level redundancy. compression method. In addition, DjVu based on mixed raster content (MixedRaster Content, MRC) is mainly used for the compression of compound documents. It divides the image into foreground and background through a bla...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06T9/00H04N1/41
Inventor 胡奎汤帜
Owner PEKING UNIV