A bibliography of object class recognition and object recognition based on visual attention

Vahid Alizadseh Sahzabi, Khairuddin Omar

Research output: Contribution to journalArticle

Abstract

Object class recognition has exhibited significant progress in recent years and is now an integral component of many machine vision applications. However, object class recognition using visual attention image segmentation is a novel idea, which has only been developed in the past decade. This paper presents a comprehensive survey on object class recognition and object recognition algorithms, in addition to their applications based on visual attention region selection methods that as recently published. Additionally, increased efforts have been directed to the development of a generic method for categorizing all objects in a domain including examples such as Winn’s Method, used to recognize object classes at a glance. The Majority of object class recognition algorithms are highly dependent on shape matching results. The purpose of this review is to provide a comparison among the visual attention (bottom-up and top-down), object recognition (e.g., SIFT, SURF and PCA-SIFT) and object class recognition methods, aimed to researchers identifying the most appropriate method for a particular purpose. This survey is suitable for researchers in the pattern recognition field, providing familiarity with the existing algorithms for object classification from image acquisition steps to final output (i.e., image segmentation, object recognition and object classification). At the end of each part, the challenges, critical analysis table are provided and future directions of every method are suggested for developing new ideas end of this paper. Additionally, this approach allows researchers to find the definition of keywords and to obtain brief knowledge concerning how each method works and what obtained results are for various datasets.

Original languageEnglish
Pages (from-to)104-119
Number of pages16
JournalJournal of Theoretical and Applied Information Technology
Volume74
Issue number1
Publication statusPublished - 2015

Fingerprint

Visual Attention
Bibliographies
Object recognition
Object Recognition
Image segmentation
Image acquisition
Object Classification
Scale Invariant Feature Transform
Computer vision
Recognition Algorithm
Pattern recognition
Image Segmentation
Shape Matching
Machine Vision
Image Acquisition
Bottom-up
Object
Bibliography
Class
Pattern Recognition

Keywords

  • Bottom-up visual attention
  • Bottom-up visual attention
  • Object categorization
  • Object class recognition
  • Object classification
  • Saliency visual attention
  • Visual object recognition

ASJC Scopus subject areas

  • Computer Science(all)
  • Theoretical Computer Science

Cite this

A bibliography of object class recognition and object recognition based on visual attention. / Sahzabi, Vahid Alizadseh; Omar, Khairuddin.

In: Journal of Theoretical and Applied Information Technology, Vol. 74, No. 1, 2015, p. 104-119.

Research output: Contribution to journalArticle

@article{011bd9a0a89f4a2b98f5048945f45e6b,
title = "A bibliography of object class recognition and object recognition based on visual attention",
abstract = "Object class recognition has exhibited significant progress in recent years and is now an integral component of many machine vision applications. However, object class recognition using visual attention image segmentation is a novel idea, which has only been developed in the past decade. This paper presents a comprehensive survey on object class recognition and object recognition algorithms, in addition to their applications based on visual attention region selection methods that as recently published. Additionally, increased efforts have been directed to the development of a generic method for categorizing all objects in a domain including examples such as Winn’s Method, used to recognize object classes at a glance. The Majority of object class recognition algorithms are highly dependent on shape matching results. The purpose of this review is to provide a comparison among the visual attention (bottom-up and top-down), object recognition (e.g., SIFT, SURF and PCA-SIFT) and object class recognition methods, aimed to researchers identifying the most appropriate method for a particular purpose. This survey is suitable for researchers in the pattern recognition field, providing familiarity with the existing algorithms for object classification from image acquisition steps to final output (i.e., image segmentation, object recognition and object classification). At the end of each part, the challenges, critical analysis table are provided and future directions of every method are suggested for developing new ideas end of this paper. Additionally, this approach allows researchers to find the definition of keywords and to obtain brief knowledge concerning how each method works and what obtained results are for various datasets.",
keywords = "Bottom-up visual attention, Bottom-up visual attention, Object categorization, Object class recognition, Object classification, Saliency visual attention, Visual object recognition",
author = "Sahzabi, {Vahid Alizadseh} and Khairuddin Omar",
year = "2015",
language = "English",
volume = "74",
pages = "104--119",
journal = "Journal of Theoretical and Applied Information Technology",
issn = "1992-8645",
publisher = "Asian Research Publishing Network (ARPN)",
number = "1",

}

TY - JOUR

T1 - A bibliography of object class recognition and object recognition based on visual attention

AU - Sahzabi, Vahid Alizadseh

AU - Omar, Khairuddin

PY - 2015

Y1 - 2015

N2 - Object class recognition has exhibited significant progress in recent years and is now an integral component of many machine vision applications. However, object class recognition using visual attention image segmentation is a novel idea, which has only been developed in the past decade. This paper presents a comprehensive survey on object class recognition and object recognition algorithms, in addition to their applications based on visual attention region selection methods that as recently published. Additionally, increased efforts have been directed to the development of a generic method for categorizing all objects in a domain including examples such as Winn’s Method, used to recognize object classes at a glance. The Majority of object class recognition algorithms are highly dependent on shape matching results. The purpose of this review is to provide a comparison among the visual attention (bottom-up and top-down), object recognition (e.g., SIFT, SURF and PCA-SIFT) and object class recognition methods, aimed to researchers identifying the most appropriate method for a particular purpose. This survey is suitable for researchers in the pattern recognition field, providing familiarity with the existing algorithms for object classification from image acquisition steps to final output (i.e., image segmentation, object recognition and object classification). At the end of each part, the challenges, critical analysis table are provided and future directions of every method are suggested for developing new ideas end of this paper. Additionally, this approach allows researchers to find the definition of keywords and to obtain brief knowledge concerning how each method works and what obtained results are for various datasets.

AB - Object class recognition has exhibited significant progress in recent years and is now an integral component of many machine vision applications. However, object class recognition using visual attention image segmentation is a novel idea, which has only been developed in the past decade. This paper presents a comprehensive survey on object class recognition and object recognition algorithms, in addition to their applications based on visual attention region selection methods that as recently published. Additionally, increased efforts have been directed to the development of a generic method for categorizing all objects in a domain including examples such as Winn’s Method, used to recognize object classes at a glance. The Majority of object class recognition algorithms are highly dependent on shape matching results. The purpose of this review is to provide a comparison among the visual attention (bottom-up and top-down), object recognition (e.g., SIFT, SURF and PCA-SIFT) and object class recognition methods, aimed to researchers identifying the most appropriate method for a particular purpose. This survey is suitable for researchers in the pattern recognition field, providing familiarity with the existing algorithms for object classification from image acquisition steps to final output (i.e., image segmentation, object recognition and object classification). At the end of each part, the challenges, critical analysis table are provided and future directions of every method are suggested for developing new ideas end of this paper. Additionally, this approach allows researchers to find the definition of keywords and to obtain brief knowledge concerning how each method works and what obtained results are for various datasets.

KW - Bottom-up visual attention

KW - Bottom-up visual attention

KW - Object categorization

KW - Object class recognition

KW - Object classification

KW - Saliency visual attention

KW - Visual object recognition

UR - http://www.scopus.com/inward/record.url?scp=84926612613&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84926612613&partnerID=8YFLogxK

M3 - Article

VL - 74

SP - 104

EP - 119

JO - Journal of Theoretical and Applied Information Technology

JF - Journal of Theoretical and Applied Information Technology

SN - 1992-8645

IS - 1

ER -