Spatially Aware Dictionary Learning and Coding for Fossil Pollen Identification

Shu Kong, Surangi W Punyasena, Charless Fowlkes

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

Abstract

We propose a robust approach for performing automatic species-level recognition of fossil pollen grains in microscopy images that exploits both global shape and local texture characteristics in a patch-based matching methodology. We introduce a novel criteria for selecting meaningful and discriminative exemplar patches. We optimize this function during training using a greedy submodular function optimization framework that gives a near-optimal solution with bounded approximation error. We use these selected exemplars as a dictionary basis and propose a spatially-aware sparse coding method to match testing images for identification while maintaining global shape correspondence. To accelerate the coding process for fast matching, we introduce a relaxed form that uses spatiallyaware soft-thresholding during coding. Finally, we carry out an experimental study that demonstrates the effectiveness and efficiency of our exemplar selection and classification mechanisms, achieving 86.13% accuracy on a difficult fine-grained species classification task distinguishing three types of fossil spruce pollen 1.

Original languageEnglish (US)
Title of host publicationProceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2016
PublisherIEEE Computer Society
Pages1305-1314
Number of pages10
ISBN (Electronic)9781467388504
DOIs
StatePublished - Dec 16 2016
Event29th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2016 - Las Vegas, United States
Duration: Jun 26 2016Jul 1 2016

Publication series

NameIEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
ISSN (Print)2160-7508
ISSN (Electronic)2160-7516

Other

Other29th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2016
CountryUnited States
CityLas Vegas
Period6/26/167/1/16

Fingerprint

Glossaries
Microscopic examination
Textures
Testing

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Cite this

Kong, S., Punyasena, S. W., & Fowlkes, C. (2016). Spatially Aware Dictionary Learning and Coding for Fossil Pollen Identification. In Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2016 (pp. 1305-1314). [7789655] (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops). IEEE Computer Society. https://doi.org/10.1109/CVPRW.2016.165

Spatially Aware Dictionary Learning and Coding for Fossil Pollen Identification. / Kong, Shu; Punyasena, Surangi W; Fowlkes, Charless.

Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2016. IEEE Computer Society, 2016. p. 1305-1314 7789655 (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops).

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

Kong, S, Punyasena, SW & Fowlkes, C 2016, Spatially Aware Dictionary Learning and Coding for Fossil Pollen Identification. in Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2016., 7789655, IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, IEEE Computer Society, pp. 1305-1314, 29th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2016, Las Vegas, United States, 6/26/16. https://doi.org/10.1109/CVPRW.2016.165
Kong S, Punyasena SW, Fowlkes C. Spatially Aware Dictionary Learning and Coding for Fossil Pollen Identification. In Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2016. IEEE Computer Society. 2016. p. 1305-1314. 7789655. (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops). https://doi.org/10.1109/CVPRW.2016.165
Kong, Shu ; Punyasena, Surangi W ; Fowlkes, Charless. / Spatially Aware Dictionary Learning and Coding for Fossil Pollen Identification. Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2016. IEEE Computer Society, 2016. pp. 1305-1314 (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops).
@inproceedings{85680eaa7762445d8ce0821764e380b0,
title = "Spatially Aware Dictionary Learning and Coding for Fossil Pollen Identification",
abstract = "We propose a robust approach for performing automatic species-level recognition of fossil pollen grains in microscopy images that exploits both global shape and local texture characteristics in a patch-based matching methodology. We introduce a novel criteria for selecting meaningful and discriminative exemplar patches. We optimize this function during training using a greedy submodular function optimization framework that gives a near-optimal solution with bounded approximation error. We use these selected exemplars as a dictionary basis and propose a spatially-aware sparse coding method to match testing images for identification while maintaining global shape correspondence. To accelerate the coding process for fast matching, we introduce a relaxed form that uses spatiallyaware soft-thresholding during coding. Finally, we carry out an experimental study that demonstrates the effectiveness and efficiency of our exemplar selection and classification mechanisms, achieving 86.13{\%} accuracy on a difficult fine-grained species classification task distinguishing three types of fossil spruce pollen 1.",
author = "Shu Kong and Punyasena, {Surangi W} and Charless Fowlkes",
year = "2016",
month = "12",
day = "16",
doi = "10.1109/CVPRW.2016.165",
language = "English (US)",
series = "IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops",
publisher = "IEEE Computer Society",
pages = "1305--1314",
booktitle = "Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2016",

}

TY - GEN

T1 - Spatially Aware Dictionary Learning and Coding for Fossil Pollen Identification

AU - Kong, Shu

AU - Punyasena, Surangi W

AU - Fowlkes, Charless

PY - 2016/12/16

Y1 - 2016/12/16

N2 - We propose a robust approach for performing automatic species-level recognition of fossil pollen grains in microscopy images that exploits both global shape and local texture characteristics in a patch-based matching methodology. We introduce a novel criteria for selecting meaningful and discriminative exemplar patches. We optimize this function during training using a greedy submodular function optimization framework that gives a near-optimal solution with bounded approximation error. We use these selected exemplars as a dictionary basis and propose a spatially-aware sparse coding method to match testing images for identification while maintaining global shape correspondence. To accelerate the coding process for fast matching, we introduce a relaxed form that uses spatiallyaware soft-thresholding during coding. Finally, we carry out an experimental study that demonstrates the effectiveness and efficiency of our exemplar selection and classification mechanisms, achieving 86.13% accuracy on a difficult fine-grained species classification task distinguishing three types of fossil spruce pollen 1.

AB - We propose a robust approach for performing automatic species-level recognition of fossil pollen grains in microscopy images that exploits both global shape and local texture characteristics in a patch-based matching methodology. We introduce a novel criteria for selecting meaningful and discriminative exemplar patches. We optimize this function during training using a greedy submodular function optimization framework that gives a near-optimal solution with bounded approximation error. We use these selected exemplars as a dictionary basis and propose a spatially-aware sparse coding method to match testing images for identification while maintaining global shape correspondence. To accelerate the coding process for fast matching, we introduce a relaxed form that uses spatiallyaware soft-thresholding during coding. Finally, we carry out an experimental study that demonstrates the effectiveness and efficiency of our exemplar selection and classification mechanisms, achieving 86.13% accuracy on a difficult fine-grained species classification task distinguishing three types of fossil spruce pollen 1.

UR - http://www.scopus.com/inward/record.url?scp=85010187370&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85010187370&partnerID=8YFLogxK

U2 - 10.1109/CVPRW.2016.165

DO - 10.1109/CVPRW.2016.165

M3 - Conference contribution

AN - SCOPUS:85010187370

T3 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops

SP - 1305

EP - 1314

BT - Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2016

PB - IEEE Computer Society

ER -