Spatial Pooling of Heterogeneous Features for Image Classification

In image classification tasks, one of the most successful algorithms is the bag-of-features (BoFs) model. Although the BoF model has many advantages, such as simplicity, generality, and scalability, it still suffers from several drawbacks, including the limited semantic description of local descript...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on image processing Vol. 23; no. 5; pp. 1994 - 2008
Main Authors: Xie, Lingxi, Tian, Qi, Wang, Meng, Zhang, Bo
Format: Journal Article
Language:English
Published: New York, NY IEEE 01.05.2014
Institute of Electrical and Electronics Engineers
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Accuracy
Algorithms
Applied sciences
Basic converters
Construction
Exact sciences and technology
Feature extraction
Image classification
Image edge detection
Image processing
Information, signal and communications theory
Mathematical models
Oxygen steel making
Pattern recognition
Quantization (signal)
Shape
Signal and communications theory
Signal processing
Signal representation. Spectral analysis
Signal, noise
Telecommunications and information theory
Texture
Vectors
Visualization
BoF model
geometric phrases pooling
complementary descriptors
spatial weighting
Image classification
Performance evaluation
State of the art
Image processing
Scalability
Pattern recognition
Signal representation
Shape detection
Algorithm
Modeling
Texture
Interest region
Weighting
Semantics
Image representation
Edge detection
ISSN:1057-7149, 1941-0042, 1941-0042
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In image classification tasks, one of the most successful algorithms is the bag-of-features (BoFs) model. Although the BoF model has many advantages, such as simplicity, generality, and scalability, it still suffers from several drawbacks, including the limited semantic description of local descriptors, lack of robust structures upon single visual words, and missing of efficient spatial weighting. To overcome these shortcomings, various techniques have been proposed, such as extracting multiple descriptors, spatial context modeling, and interest region detection. Though they have been proven to improve the BoF model to some extent, there still lacks a coherent scheme to integrate each individual module together. To address the problems above, we propose a novel framework with spatial pooling of complementary features. Our model expands the traditional BoF model on three aspects. First, we propose a new scheme for combining texture and edge-based local features together at the descriptor extraction level. Next, we build geometric visual phrases to model spatial context upon complementary features for midlevel image representation. Finally, based on a smoothed edgemap, a simple and effective spatial weighting scheme is performed to capture the image saliency. We test the proposed framework on several benchmark data sets for image classification. The extensive results show the superior performance of our algorithm over the state-of-the-art methods.
Bibliography:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 14
ObjectType-Article-1
ObjectType-Feature-2
content type line 23
ISSN:1057-7149
1941-0042
1941-0042
DOI:10.1109/TIP.2014.2310117