Supervised local sparse coding of sub-image features for image retrieval

Jayaraman J. Thiagarajan, Karthikeyan Natesan Ramamurthy, Prasanna Sattigeri, Andreas Spanias

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

7 Citations (Scopus)

Abstract

The success of sparse representations in image modeling and recovery has motivated its use in computer vision applications. Image retrieval and classification tasks require extracting features that discriminate different image classes. State-of-the-art object recognition methods based on sparse coding use spatial pyramid features obtained from dense descriptors. In this paper, we develop a feature extraction method that uses multiple global/local features extracted from large overlapping regions of an image, which we refer to as sub-images. We propose a procedure for dictionary design and supervised local sparse coding of sub-image heterogeneous features. We perform image retrieval on the Microsoft Research Cambridge image dataset and show that the proposed features outperform the spatial pyramid features obtained using dense descriptors.

Original languageEnglish (US)
Title of host publicationProceedings - International Conference on Image Processing, ICIP
Pages3117-3120
Number of pages4
DOIs
StatePublished - 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

Image retrieval
Image classification
Object recognition
Glossaries
Computer vision
Feature extraction
Recovery

Keywords

  • dictionary learning
  • image retrieval
  • Local linear modeling
  • Sparse coding

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems

Cite this

Thiagarajan, J. J., Natesan Ramamurthy, K., Sattigeri, P., & Spanias, A. (2012). Supervised local sparse coding of sub-image features for image retrieval. In Proceedings - International Conference on Image Processing, ICIP (pp. 3117-3120). [6467560] https://doi.org/10.1109/ICIP.2012.6467560

Supervised local sparse coding of sub-image features for image retrieval. / Thiagarajan, Jayaraman J.; Natesan Ramamurthy, Karthikeyan; Sattigeri, Prasanna; Spanias, Andreas.

Proceedings - International Conference on Image Processing, ICIP. 2012. p. 3117-3120 6467560.

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

Thiagarajan, JJ, Natesan Ramamurthy, K, Sattigeri, P & Spanias, A 2012, Supervised local sparse coding of sub-image features for image retrieval. in Proceedings - International Conference on Image Processing, ICIP., 6467560, pp. 3117-3120, 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.2012.6467560
Thiagarajan JJ, Natesan Ramamurthy K, Sattigeri P, Spanias A. Supervised local sparse coding of sub-image features for image retrieval. In Proceedings - International Conference on Image Processing, ICIP. 2012. p. 3117-3120. 6467560 https://doi.org/10.1109/ICIP.2012.6467560
Thiagarajan, Jayaraman J. ; Natesan Ramamurthy, Karthikeyan ; Sattigeri, Prasanna ; Spanias, Andreas. / Supervised local sparse coding of sub-image features for image retrieval. Proceedings - International Conference on Image Processing, ICIP. 2012. pp. 3117-3120
@inproceedings{d751c32d5bbe41aa9419174d78836d3f,
title = "Supervised local sparse coding of sub-image features for image retrieval",
abstract = "The success of sparse representations in image modeling and recovery has motivated its use in computer vision applications. Image retrieval and classification tasks require extracting features that discriminate different image classes. State-of-the-art object recognition methods based on sparse coding use spatial pyramid features obtained from dense descriptors. In this paper, we develop a feature extraction method that uses multiple global/local features extracted from large overlapping regions of an image, which we refer to as sub-images. We propose a procedure for dictionary design and supervised local sparse coding of sub-image heterogeneous features. We perform image retrieval on the Microsoft Research Cambridge image dataset and show that the proposed features outperform the spatial pyramid features obtained using dense descriptors.",
keywords = "dictionary learning, image retrieval, Local linear modeling, Sparse coding",
author = "Thiagarajan, {Jayaraman J.} and {Natesan Ramamurthy}, Karthikeyan and Prasanna Sattigeri and Andreas Spanias",
year = "2012",
doi = "10.1109/ICIP.2012.6467560",
language = "English (US)",
isbn = "9781467325332",
pages = "3117--3120",
booktitle = "Proceedings - International Conference on Image Processing, ICIP",

}

TY - GEN

T1 - Supervised local sparse coding of sub-image features for image retrieval

AU - Thiagarajan, Jayaraman J.

AU - Natesan Ramamurthy, Karthikeyan

AU - Sattigeri, Prasanna

AU - Spanias, Andreas

PY - 2012

Y1 - 2012

N2 - The success of sparse representations in image modeling and recovery has motivated its use in computer vision applications. Image retrieval and classification tasks require extracting features that discriminate different image classes. State-of-the-art object recognition methods based on sparse coding use spatial pyramid features obtained from dense descriptors. In this paper, we develop a feature extraction method that uses multiple global/local features extracted from large overlapping regions of an image, which we refer to as sub-images. We propose a procedure for dictionary design and supervised local sparse coding of sub-image heterogeneous features. We perform image retrieval on the Microsoft Research Cambridge image dataset and show that the proposed features outperform the spatial pyramid features obtained using dense descriptors.

AB - The success of sparse representations in image modeling and recovery has motivated its use in computer vision applications. Image retrieval and classification tasks require extracting features that discriminate different image classes. State-of-the-art object recognition methods based on sparse coding use spatial pyramid features obtained from dense descriptors. In this paper, we develop a feature extraction method that uses multiple global/local features extracted from large overlapping regions of an image, which we refer to as sub-images. We propose a procedure for dictionary design and supervised local sparse coding of sub-image heterogeneous features. We perform image retrieval on the Microsoft Research Cambridge image dataset and show that the proposed features outperform the spatial pyramid features obtained using dense descriptors.

KW - dictionary learning

KW - image retrieval

KW - Local linear modeling

KW - Sparse coding

UR - http://www.scopus.com/inward/record.url?scp=84875854962&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84875854962&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2012.6467560

DO - 10.1109/ICIP.2012.6467560

M3 - Conference contribution

SN - 9781467325332

SP - 3117

EP - 3120

BT - Proceedings - International Conference on Image Processing, ICIP

ER -