Visual descriptors for scene categorization: experimental evaluation

Humans are endowed with the ability to grasp the overall meaning or the gist of a complex visual scene at a glance. We need only a fraction of a second to decide if a scene is indoors, outdoors, on a busy street, or on a clear beach. In recent years, computational gist recognition or scene categoriz...

Full description

Saved in:
Bibliographic Details
Published in:The Artificial intelligence review 2016-03, Vol.45 (3), p.333-368
Main Authors: Wei, Xue, Phung, Son Lam, Bouzerdoum, Abdesselam
Format: Article
Language:English
Subjects:
Algorithms
Artificial Intelligence
Categories
Classification
Computer Science
Datasets
Feature extraction
Imaging
Market segmentation
Neural networks
Object recognition
Principal components analysis
Searching
Semantics
Streets
Surveillance
Visual
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Humans are endowed with the ability to grasp the overall meaning or the gist of a complex visual scene at a glance. We need only a fraction of a second to decide if a scene is indoors, outdoors, on a busy street, or on a clear beach. In recent years, computational gist recognition or scene categorization has been actively pursued, given its numerous applications in image and video search, surveillance, and assistive navigation. Many visual descriptors have been developed to address the challenges in scene categorization, including the large number of semantic categories and the tremendous variations caused by imaging conditions. This paper provides a critical review of visual descriptors used for scene categorization, from both methodological and experimental perspectives. We present an empirical study conducted on four benchmark data sets assessing the classification accuracy and class separability of state-of-the-art visual descriptors.
ISSN:0269-2821
1573-7462
DOI:10.1007/s10462-015-9448-4