A comparison of Fisher vectors and Gaussian supervectors for document versus non-document image classification

David C. Smith; Keri A. Kornelson

doi:10.1117/12.2023329

26 September 2013 A comparison of Fisher vectors and Gaussian supervectors for document versus non-document image classification

David C. Smith, Keri A. Kornelson

Author Affiliations +

Proceedings Volume 8856, Applications of Digital Image Processing XXXVI; 88560N (2013) https://doi.org/10.1117/12.2023329
Event: SPIE Optical Engineering + Applications, 2013, San Diego, California, United States

Abstract

This research addresses the document vs. non-document image classification problem. The ability to select images containing text from an OCR processing stream that also includes images of scenes, people, faces, etc., will eliminate unnecessary computation and free up valuable computer resources for other tasks. This is particularly true for high volume OCR systems. Fisher vectors represent images as gradients of a global generative Gaussian Mixture Model (GMM) of low level image descriptors, and exhibit state-of-the-art performance for object categorization. Gaussian supervectors represent images by soft clustering low level image descriptors according to posterior GMM mixture probabilities, optionally using MAP adaptation, and have demonstrated state-of-the-art performance for scene categorization. We compare results obtained by applying linear SVMs to Fisher vector and Gaussian supervector representations to categorize images as having only text, no text, or a mixture of text and non-text. We also report the performance of GMM-based soft versions of vectors of locally aggregated descriptors (VLAD) and Bag of Visual words (BOV).

Citation Download Citation

David C. Smith and Keri A. Kornelson "A comparison of Fisher vectors and Gaussian supervectors for document versus non-document image classification", Proc. SPIE 8856, Applications of Digital Image Processing XXXVI, 88560N (26 September 2013); https://doi.org/10.1117/12.2023329

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available