Selective Search for Object Recognition

This paper addresses the problem of generating possible object locations for use in object recognition. We introduce selective search which combines the strength of both an exhaustive search and segmentation. Like segmentation, we use the image structure to guide our sampling process. Like exhaustiv...

Full description

Saved in:
Bibliographic Details
Published in:International journal of computer vision Vol. 104; no. 2; pp. 154 - 171
Main Authors: Uijlings, J. R. R., van de Sande, K. E. A., Gevers, T., Smeulders, A. W. M.
Format: Journal Article
Language:English
Published: Boston Springer US 01.09.2013
Springer
Springer Nature B.V
Subjects:
Applied sciences
Artificial Intelligence
Computer Imaging
Computer programs
Computer Science
Computer science; control theory; systems
Datasets
Exact sciences and technology
Image Processing and Computer Vision
Image processing systems
Information management
Localization
Object recognition
Pattern Recognition
Pattern Recognition and Graphics
Pattern recognition. Digital image processing. Computational geometry
Recall
Sampling
Search engines
Searching
Segmentation
Software
Studies
Vision
United States > US
Object Recognition
Colour Space
Object Location
Exhaustive Search
Appearance Model
Computer vision
Bag of words
Segmentation
Information retrieval
Data driven modelling
Pattern recognition
Sampling
Overlay
Object recognition
Artificial intelligence
Modeling
Object location
ISSN:0920-5691, 1573-1405
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper addresses the problem of generating possible object locations for use in object recognition. We introduce selective search which combines the strength of both an exhaustive search and segmentation. Like segmentation, we use the image structure to guide our sampling process. Like exhaustive search, we aim to capture all possible object locations. Instead of a single technique to generate possible object locations, we diversify our search and use a variety of complementary image partitionings to deal with as many image conditions as possible. Our selective search results in a small set of data-driven, class-independent, high quality locations, yielding 99 % recall and a Mean Average Best Overlap of 0.879 at 10,097 locations. The reduced number of locations compared to an exhaustive search enables the use of stronger machine learning techniques and stronger appearance models for object recognition. In this paper we show that our selective search enables the use of the powerful Bag-of-Words model for recognition. The selective search software is made publicly available (Software: http://disi.unitn.it/~uijlings/SelectiveSearch.html ).
Bibliography:SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 14
ObjectType-Article-2
content type line 23
ISSN:0920-5691
1573-1405
DOI:10.1007/s11263-013-0620-5