HaarHOG: Improving the HOG descriptor for image classification

Sugata Banerji, Atreyee Sinha, Chengjun Liu

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

5 Scopus citations

Abstract

The Histograms of Oriented Gradients (HOG) descriptor represents shape information by storing the local gradients in an image. The Haar wavelet transform is a simple yet powerful technique that can separately enhance the horizontal and vertical local features in an image. In this paper, we enhance the HOG descriptor by subjecting the image to the Haar wavelet transform and then computing HOG from the result in a manner that enriches the shape information encoded in the descriptor. First, we define the novel HaarHOG descriptor for grayscale images and extend this idea for color images. Second, we compare the image recognition performance of the HaarHOG descriptor with the traditional HOG descriptor in four different color spaces and grayscale. Finally, we compare the image classification performance of the HaarHOG descriptor with some popular descriptors used by other researchers on four grand challenge datasets.

Original languageEnglish (US)
Title of host publicationProceedings - 2013 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2013
Pages4276-4281
Number of pages6
DOIs
StatePublished - Dec 1 2013
Event2013 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2013 - Manchester, United Kingdom
Duration: Oct 13 2013Oct 16 2013

Publication series

NameProceedings - 2013 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2013

Other

Other2013 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2013
Country/TerritoryUnited Kingdom
CityManchester
Period10/13/1310/16/13

All Science Journal Classification (ASJC) codes

  • Human-Computer Interaction

Keywords

  • Haar wavelets
  • Haarhog descriptor
  • Histograms of oriented gradients descriptor
  • Object and scene image classification
  • Shape descriptor

Fingerprint

Dive into the research topics of 'HaarHOG: Improving the HOG descriptor for image classification'. Together they form a unique fingerprint.

Cite this