Learning to Extract Focused Objects From Low DOF Images

This paper proposes an approach to extract focused objects (i.e., attention objects) from low depth-of-field images. To recognize the focused object, we decompose the image into multiple regions, which are described by using three types of visual descriptors. Each descriptor is extracted from a repr...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on circuits and systems for video technology 2011-11, Vol.21 (11), p.1571-1580
Main Authors: Hongliang Li, Ngan, K. N.
Format: Article
Language:English
Subjects:
Algorithms
Applied sciences
Attention
boosting
Classification
Classifiers
Detection, estimation, filtering, equalization, prediction
Exact sciences and technology
Feature extraction
Image color analysis
Image edge detection
Image processing
Image segmentation
Information, signal and communications theory
low depth-of-field
object segmentation
Pattern recognition
Pixel
Segmentation
Signal and communications theory
Signal processing
Signal representation. Spectral analysis
Signal, noise
Studies
Surface layer
Telecommunications and information theory
Texture
Training
Visual
visual descriptor
Visualization
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:This paper proposes an approach to extract focused objects (i.e., attention objects) from low depth-of-field images. To recognize the focused object, we decompose the image into multiple regions, which are described by using three types of visual descriptors. Each descriptor is extracted from a representation of some aspects of local appearance, e.g., a spatially localized texture, color, or geometrical property. Therefore, the focus detection of a region can be achieved by the classification of extracted visual descriptors based on a binary classifier. We employ a boosting algorithm to learn the classifier with a cascade of decision structure. Given a test image, initial segmentation can be achieved using obtained classification results. Finally, we apply a post-processing technique to improve the results by incorporating region grouping and pixel-level segmentation. Experimental evaluation on a number of images demonstrates the performance advantages of the proposed method, when compared with state-of-the-art methods.
ISSN:1051-8215
1558-2205
DOI:10.1109/TCSVT.2011.2129150