Visual Information Evaluation with Entropy of Primitive

Songchao Tan; Shurun Wang; Xiang Zhang; Shanshe Wang; Shiqi Wang; Siwei Ma; Wen Gao

doi:10.1109/ACCESS.2018.2825368

Visual Information Evaluation with Entropy of Primitive

Songchao Tan^*
, Shurun Wang
, Xiang Zhang
, Shanshe Wang
, Shiqi Wang
, Siwei Ma
, Wen Gao

^*Corresponding author for this work

Dalian University of Technology
Peking University
City University of Hong Kong

Research output: Contribution to journal › Article › peer-review

5 Scopus citations

Abstract

In this paper, we overview the recent work on entropy of primitive (EoP), including its concept, design, extension, and mathematical analysis in evaluating the visual information of natural images. The design philosophy of EoP is establishing an entropy model that quantifies the visual information based on patch-level sparse representation, due to the close relationship between sparse representation and the hierarchical cognitive process of human perception. Furthermore, based on the concept and definition of EoP, we also demonstrate several applications, including just noticeable difference estimation and visual quality assessment. The future research directions of visual information evaluation are also envisioned, where we can perceive both promises and challenges.

Original language	English
Pages (from-to)	31750-31758
Number of pages	9
Journal	IEEE Access
Volume	6
DOIs	https://doi.org/10.1109/ACCESS.2018.2825368
State	Published - 17 Apr 2018
Externally published	Yes

Keywords

Entropy of primitive
just noticeable difference
quality assessment
sparse representation
visual information

Access to Document

10.1109/ACCESS.2018.2825368

Cite this

@article{12d03425bdc34745b189cfbab520a070,

title = "Visual Information Evaluation with Entropy of Primitive",

abstract = "In this paper, we overview the recent work on entropy of primitive (EoP), including its concept, design, extension, and mathematical analysis in evaluating the visual information of natural images. The design philosophy of EoP is establishing an entropy model that quantifies the visual information based on patch-level sparse representation, due to the close relationship between sparse representation and the hierarchical cognitive process of human perception. Furthermore, based on the concept and definition of EoP, we also demonstrate several applications, including just noticeable difference estimation and visual quality assessment. The future research directions of visual information evaluation are also envisioned, where we can perceive both promises and challenges.",

keywords = "Entropy of primitive, just noticeable difference, quality assessment, sparse representation, visual information",

author = "Songchao Tan and Shurun Wang and Xiang Zhang and Shanshe Wang and Shiqi Wang and Siwei Ma and Wen Gao",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE.",

year = "2018",

month = apr,

day = "17",

doi = "10.1109/ACCESS.2018.2825368",

language = "英语",

volume = "6",

pages = "31750--31758",

journal = "IEEE Access",

issn = "2169-3536",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Visual Information Evaluation with Entropy of Primitive

AU - Tan, Songchao

AU - Wang, Shurun

AU - Zhang, Xiang

AU - Wang, Shanshe

AU - Wang, Shiqi

AU - Ma, Siwei

AU - Gao, Wen

PY - 2018/4/17

Y1 - 2018/4/17

N2 - In this paper, we overview the recent work on entropy of primitive (EoP), including its concept, design, extension, and mathematical analysis in evaluating the visual information of natural images. The design philosophy of EoP is establishing an entropy model that quantifies the visual information based on patch-level sparse representation, due to the close relationship between sparse representation and the hierarchical cognitive process of human perception. Furthermore, based on the concept and definition of EoP, we also demonstrate several applications, including just noticeable difference estimation and visual quality assessment. The future research directions of visual information evaluation are also envisioned, where we can perceive both promises and challenges.

AB - In this paper, we overview the recent work on entropy of primitive (EoP), including its concept, design, extension, and mathematical analysis in evaluating the visual information of natural images. The design philosophy of EoP is establishing an entropy model that quantifies the visual information based on patch-level sparse representation, due to the close relationship between sparse representation and the hierarchical cognitive process of human perception. Furthermore, based on the concept and definition of EoP, we also demonstrate several applications, including just noticeable difference estimation and visual quality assessment. The future research directions of visual information evaluation are also envisioned, where we can perceive both promises and challenges.

KW - Entropy of primitive

KW - just noticeable difference

KW - quality assessment

KW - sparse representation

KW - visual information

UR - https://www.scopus.com/pages/publications/85045756253

U2 - 10.1109/ACCESS.2018.2825368

DO - 10.1109/ACCESS.2018.2825368

M3 - 文章

AN - SCOPUS:85045756253

SN - 2169-3536

VL - 6

SP - 31750

EP - 31758

JO - IEEE Access

JF - IEEE Access

ER -

Visual Information Evaluation with Entropy of Primitive

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this