Hierarchical visual perception and two-dimensional compressive sensing for effective content-based color image retrieval

Yan Zhou, Fan-Zhi Zeng, Hui-min Zhao, Paul Murray, Jinchang Ren

Research output: Contribution to journalSpecial issue

16 Citations (Scopus)

Abstract

Content-based image retrieval (CBIR) has been an active research theme in the computer vision community for over two decades. While the field is relatively mature, significant research is still required in this area to develop solutions for practical applications. One reason that practical solutions have not yet been realized could be due to a limited understanding of the cognitive aspects of the human vision system. Inspired by three cognitive properties of human vision, namely, hierarchical structuring, color perception and embedded compressive sensing, a new CBIR approach is proposed. In the proposed approach, the Hue, Saturation and Value (HSV) color model and the Similar Gray Level Co-occurrence Matrix (SGLCM) texture descriptors are used to generate elementary features. These features then form a hierarchical representation of the data to which a two-dimensional compressive sensing (2D CS) feature mining algorithm is applied. Finally, a weighted feature matching method is used to perform image retrieval. We present a comprehensive set of results of applying our proposed Hierarchical Visual Perception Enabled 2D CS approach using publicly available datasets and demonstrate the efficacy of our techniques when compared with other recently published, state-of-the-art approaches.
LanguageEnglish
Number of pages13
JournalCognitive Computation
Early online date8 Aug 2016
DOIs
Publication statusE-pub ahead of print - 8 Aug 2016

Fingerprint

Visual Perception
Image retrieval
Color
Color Perception
Research
Computer vision
Textures
Datasets

Keywords

  • hierarchical visual perception
  • two-dimensional compressive sensing
  • content-based image retrieval
  • image matching
  • human vision
  • cognitive abilities
  • hierarchical structuring
  • color perception
  • colour perception
  • embedded compressed sensing

Cite this

@article{747789f6070043cf8dcc8e89e69295b7,
title = "Hierarchical visual perception and two-dimensional compressive sensing for effective content-based color image retrieval",
abstract = "Content-based image retrieval (CBIR) has been an active research theme in the computer vision community for over two decades. While the field is relatively mature, significant research is still required in this area to develop solutions for practical applications. One reason that practical solutions have not yet been realized could be due to a limited understanding of the cognitive aspects of the human vision system. Inspired by three cognitive properties of human vision, namely, hierarchical structuring, color perception and embedded compressive sensing, a new CBIR approach is proposed. In the proposed approach, the Hue, Saturation and Value (HSV) color model and the Similar Gray Level Co-occurrence Matrix (SGLCM) texture descriptors are used to generate elementary features. These features then form a hierarchical representation of the data to which a two-dimensional compressive sensing (2D CS) feature mining algorithm is applied. Finally, a weighted feature matching method is used to perform image retrieval. We present a comprehensive set of results of applying our proposed Hierarchical Visual Perception Enabled 2D CS approach using publicly available datasets and demonstrate the efficacy of our techniques when compared with other recently published, state-of-the-art approaches.",
keywords = "hierarchical visual perception, two-dimensional compressive sensing, content-based image retrieval, image matching, human vision, cognitive abilities, hierarchical structuring, color perception, colour perception, embedded compressed sensing",
author = "Yan Zhou and Fan-Zhi Zeng and Hui-min Zhao and Paul Murray and Jinchang Ren",
note = "The final publication is available at Springer via http://dx.doi.org/10.1007/s12559-016-9424-6",
year = "2016",
month = "8",
day = "8",
doi = "10.1007/s12559-016-9424-6",
language = "English",
journal = "Cognitive Computation",
issn = "1866-9956",

}

Hierarchical visual perception and two-dimensional compressive sensing for effective content-based color image retrieval. / Zhou, Yan; Zeng, Fan-Zhi; Zhao, Hui-min; Murray, Paul; Ren, Jinchang.

In: Cognitive Computation, 08.08.2016.

Research output: Contribution to journalSpecial issue

TY - JOUR

T1 - Hierarchical visual perception and two-dimensional compressive sensing for effective content-based color image retrieval

AU - Zhou, Yan

AU - Zeng, Fan-Zhi

AU - Zhao, Hui-min

AU - Murray, Paul

AU - Ren, Jinchang

N1 - The final publication is available at Springer via http://dx.doi.org/10.1007/s12559-016-9424-6

PY - 2016/8/8

Y1 - 2016/8/8

N2 - Content-based image retrieval (CBIR) has been an active research theme in the computer vision community for over two decades. While the field is relatively mature, significant research is still required in this area to develop solutions for practical applications. One reason that practical solutions have not yet been realized could be due to a limited understanding of the cognitive aspects of the human vision system. Inspired by three cognitive properties of human vision, namely, hierarchical structuring, color perception and embedded compressive sensing, a new CBIR approach is proposed. In the proposed approach, the Hue, Saturation and Value (HSV) color model and the Similar Gray Level Co-occurrence Matrix (SGLCM) texture descriptors are used to generate elementary features. These features then form a hierarchical representation of the data to which a two-dimensional compressive sensing (2D CS) feature mining algorithm is applied. Finally, a weighted feature matching method is used to perform image retrieval. We present a comprehensive set of results of applying our proposed Hierarchical Visual Perception Enabled 2D CS approach using publicly available datasets and demonstrate the efficacy of our techniques when compared with other recently published, state-of-the-art approaches.

AB - Content-based image retrieval (CBIR) has been an active research theme in the computer vision community for over two decades. While the field is relatively mature, significant research is still required in this area to develop solutions for practical applications. One reason that practical solutions have not yet been realized could be due to a limited understanding of the cognitive aspects of the human vision system. Inspired by three cognitive properties of human vision, namely, hierarchical structuring, color perception and embedded compressive sensing, a new CBIR approach is proposed. In the proposed approach, the Hue, Saturation and Value (HSV) color model and the Similar Gray Level Co-occurrence Matrix (SGLCM) texture descriptors are used to generate elementary features. These features then form a hierarchical representation of the data to which a two-dimensional compressive sensing (2D CS) feature mining algorithm is applied. Finally, a weighted feature matching method is used to perform image retrieval. We present a comprehensive set of results of applying our proposed Hierarchical Visual Perception Enabled 2D CS approach using publicly available datasets and demonstrate the efficacy of our techniques when compared with other recently published, state-of-the-art approaches.

KW - hierarchical visual perception

KW - two-dimensional compressive sensing

KW - content-based image retrieval

KW - image matching

KW - human vision

KW - cognitive abilities

KW - hierarchical structuring

KW - color perception

KW - colour perception

KW - embedded compressed sensing

UR - http://link.springer.com/journal/12559

U2 - 10.1007/s12559-016-9424-6

DO - 10.1007/s12559-016-9424-6

M3 - Special issue

JO - Cognitive Computation

T2 - Cognitive Computation

JF - Cognitive Computation

SN - 1866-9956

ER -