Object classification with efficient global self-similarity descriptors based on sparse representations

Guruprasad Somasundaram, Vassilios Morellas, Nikolaos P Papanikolopoulos

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

Object recognition entails extracting information about which object class(es) are present in an image. In order to enhance the performance of object recognition, reducing the redundancy in the data is absolutely essential. Prior literature [1, 2] introduced local and global self-similarity features to highlight the areas in an image which are useful for object classification and detection. We introduce an efficient self-similarity measure based on sparse representations and propose two different descriptors. Our measure of self-similarity is determined across multiple scales and is more efficient than prior work. We test our self similarity descriptor using support vector machine based classification on the PASCAL VOC 2007 database consisting of 20 object classes. Comparative results indicate performance competitive with the prior approaches of computing self-similarity descriptors.

Original languageEnglish (US)
Title of host publication2012 IEEE International Conference on Image Processing, ICIP 2012 - Proceedings
Pages2165-2168
Number of pages4
DOIs
StatePublished - Dec 1 2012
Event2012 19th IEEE International Conference on Image Processing, ICIP 2012 - Lake Buena Vista, FL, United States
Duration: Sep 30 2012Oct 3 2012

Other

Other2012 19th IEEE International Conference on Image Processing, ICIP 2012
CountryUnited States
CityLake Buena Vista, FL
Period9/30/1210/3/12

Fingerprint

Object recognition
Volatile organic compounds
Support vector machines
Redundancy

Keywords

  • Feature Extraction
  • Object Classification
  • Self-Similarity

Cite this

Somasundaram, G., Morellas, V., & Papanikolopoulos, N. P. (2012). Object classification with efficient global self-similarity descriptors based on sparse representations. In 2012 IEEE International Conference on Image Processing, ICIP 2012 - Proceedings (pp. 2165-2168). [6467322] https://doi.org/10.1109/ICIP.2012.6467322

Object classification with efficient global self-similarity descriptors based on sparse representations. / Somasundaram, Guruprasad; Morellas, Vassilios; Papanikolopoulos, Nikolaos P.

2012 IEEE International Conference on Image Processing, ICIP 2012 - Proceedings. 2012. p. 2165-2168 6467322.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Somasundaram, G, Morellas, V & Papanikolopoulos, NP 2012, Object classification with efficient global self-similarity descriptors based on sparse representations. in 2012 IEEE International Conference on Image Processing, ICIP 2012 - Proceedings., 6467322, pp. 2165-2168, 2012 19th IEEE International Conference on Image Processing, ICIP 2012, Lake Buena Vista, FL, United States, 9/30/12. https://doi.org/10.1109/ICIP.2012.6467322
Somasundaram G, Morellas V, Papanikolopoulos NP. Object classification with efficient global self-similarity descriptors based on sparse representations. In 2012 IEEE International Conference on Image Processing, ICIP 2012 - Proceedings. 2012. p. 2165-2168. 6467322 https://doi.org/10.1109/ICIP.2012.6467322
Somasundaram, Guruprasad ; Morellas, Vassilios ; Papanikolopoulos, Nikolaos P. / Object classification with efficient global self-similarity descriptors based on sparse representations. 2012 IEEE International Conference on Image Processing, ICIP 2012 - Proceedings. 2012. pp. 2165-2168
@inproceedings{bd25ed43cb344228ada3a201a3670ab2,
title = "Object classification with efficient global self-similarity descriptors based on sparse representations",
abstract = "Object recognition entails extracting information about which object class(es) are present in an image. In order to enhance the performance of object recognition, reducing the redundancy in the data is absolutely essential. Prior literature [1, 2] introduced local and global self-similarity features to highlight the areas in an image which are useful for object classification and detection. We introduce an efficient self-similarity measure based on sparse representations and propose two different descriptors. Our measure of self-similarity is determined across multiple scales and is more efficient than prior work. We test our self similarity descriptor using support vector machine based classification on the PASCAL VOC 2007 database consisting of 20 object classes. Comparative results indicate performance competitive with the prior approaches of computing self-similarity descriptors.",
keywords = "Feature Extraction, Object Classification, Self-Similarity",
author = "Guruprasad Somasundaram and Vassilios Morellas and Papanikolopoulos, {Nikolaos P}",
year = "2012",
month = "12",
day = "1",
doi = "10.1109/ICIP.2012.6467322",
language = "English (US)",
isbn = "9781467325332",
pages = "2165--2168",
booktitle = "2012 IEEE International Conference on Image Processing, ICIP 2012 - Proceedings",

}

TY - GEN

T1 - Object classification with efficient global self-similarity descriptors based on sparse representations

AU - Somasundaram, Guruprasad

AU - Morellas, Vassilios

AU - Papanikolopoulos, Nikolaos P

PY - 2012/12/1

Y1 - 2012/12/1

N2 - Object recognition entails extracting information about which object class(es) are present in an image. In order to enhance the performance of object recognition, reducing the redundancy in the data is absolutely essential. Prior literature [1, 2] introduced local and global self-similarity features to highlight the areas in an image which are useful for object classification and detection. We introduce an efficient self-similarity measure based on sparse representations and propose two different descriptors. Our measure of self-similarity is determined across multiple scales and is more efficient than prior work. We test our self similarity descriptor using support vector machine based classification on the PASCAL VOC 2007 database consisting of 20 object classes. Comparative results indicate performance competitive with the prior approaches of computing self-similarity descriptors.

AB - Object recognition entails extracting information about which object class(es) are present in an image. In order to enhance the performance of object recognition, reducing the redundancy in the data is absolutely essential. Prior literature [1, 2] introduced local and global self-similarity features to highlight the areas in an image which are useful for object classification and detection. We introduce an efficient self-similarity measure based on sparse representations and propose two different descriptors. Our measure of self-similarity is determined across multiple scales and is more efficient than prior work. We test our self similarity descriptor using support vector machine based classification on the PASCAL VOC 2007 database consisting of 20 object classes. Comparative results indicate performance competitive with the prior approaches of computing self-similarity descriptors.

KW - Feature Extraction

KW - Object Classification

KW - Self-Similarity

UR - http://www.scopus.com/inward/record.url?scp=84875823666&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84875823666&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2012.6467322

DO - 10.1109/ICIP.2012.6467322

M3 - Conference contribution

SN - 9781467325332

SP - 2165

EP - 2168

BT - 2012 IEEE International Conference on Image Processing, ICIP 2012 - Proceedings

ER -