Compression of smart contents with classification between text and picture blocks using sub-pixel gradient information

Chulhee Lee, Kyudong Kim, Hyuk Jae Lee

Research output: Contribution to journalArticle

Abstract

This paper presents a novel algorithm to classify complex-rendered text images by examining the color levels of the adjacent sub-pixels. The proposed algorithm is different from the previous approaches in that it uses the combined characteristics of RGB sub-channels, whereas the previous approaches use independent characteristics of RGB sub-channels. Experimental results demonstrate that the proposed algorithm improves the classification accuracy over the previous best algorithm by 15.9% for complex-rendered texts. Furthermore, the compression method optimized for text sub-images significantly reduces the computational complexity without degradation in compression efficiency.

Original languageEnglish
Pages (from-to)10-18
Number of pages9
JournalDisplays
Volume55
DOIs
Publication statusPublished - 2018 Dec

Fingerprint

Pixels
Computational complexity
Color
Degradation

All Science Journal Classification (ASJC) codes

  • Human-Computer Interaction
  • Hardware and Architecture
  • Electrical and Electronic Engineering

Cite this

@article{78f490a0e1a54df3be67cf063f36dcfd,
title = "Compression of smart contents with classification between text and picture blocks using sub-pixel gradient information",
abstract = "This paper presents a novel algorithm to classify complex-rendered text images by examining the color levels of the adjacent sub-pixels. The proposed algorithm is different from the previous approaches in that it uses the combined characteristics of RGB sub-channels, whereas the previous approaches use independent characteristics of RGB sub-channels. Experimental results demonstrate that the proposed algorithm improves the classification accuracy over the previous best algorithm by 15.9{\%} for complex-rendered texts. Furthermore, the compression method optimized for text sub-images significantly reduces the computational complexity without degradation in compression efficiency.",
author = "Chulhee Lee and Kyudong Kim and Lee, {Hyuk Jae}",
year = "2018",
month = "12",
doi = "10.1016/j.displa.2018.10.004",
language = "English",
volume = "55",
pages = "10--18",
journal = "Displays",
issn = "0141-9382",
publisher = "Elsevier",

}

Compression of smart contents with classification between text and picture blocks using sub-pixel gradient information. / Lee, Chulhee; Kim, Kyudong; Lee, Hyuk Jae.

In: Displays, Vol. 55, 12.2018, p. 10-18.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Compression of smart contents with classification between text and picture blocks using sub-pixel gradient information

AU - Lee, Chulhee

AU - Kim, Kyudong

AU - Lee, Hyuk Jae

PY - 2018/12

Y1 - 2018/12

N2 - This paper presents a novel algorithm to classify complex-rendered text images by examining the color levels of the adjacent sub-pixels. The proposed algorithm is different from the previous approaches in that it uses the combined characteristics of RGB sub-channels, whereas the previous approaches use independent characteristics of RGB sub-channels. Experimental results demonstrate that the proposed algorithm improves the classification accuracy over the previous best algorithm by 15.9% for complex-rendered texts. Furthermore, the compression method optimized for text sub-images significantly reduces the computational complexity without degradation in compression efficiency.

AB - This paper presents a novel algorithm to classify complex-rendered text images by examining the color levels of the adjacent sub-pixels. The proposed algorithm is different from the previous approaches in that it uses the combined characteristics of RGB sub-channels, whereas the previous approaches use independent characteristics of RGB sub-channels. Experimental results demonstrate that the proposed algorithm improves the classification accuracy over the previous best algorithm by 15.9% for complex-rendered texts. Furthermore, the compression method optimized for text sub-images significantly reduces the computational complexity without degradation in compression efficiency.

UR - http://www.scopus.com/inward/record.url?scp=85055126415&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85055126415&partnerID=8YFLogxK

U2 - 10.1016/j.displa.2018.10.004

DO - 10.1016/j.displa.2018.10.004

M3 - Article

AN - SCOPUS:85055126415

VL - 55

SP - 10

EP - 18

JO - Displays

JF - Displays

SN - 0141-9382

ER -