Face recognition using spectral and spatial information

Stefan A. Robila, Marco Chang, Nisha B. D'Amico

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review


We present a novel unsupervised method for facial recognition using hyperspectral imaging and decision fusion. In previous work we have separately investigated the use of spectra matching and image based matching. In spectra matching, face spectra are being classified based on spectral similarities. In image based matching, we investigated various approaches based on orthogonal subspaces (such as PCA and OSP). In the current work we provide an automated unsupervised method that starts by detecting the face in the image and then proceeds to performs both spectral and image based matching. The results are fused in a single classification decision. The algorithm is tested on an experimental hyperspectral image database of 17 subjects each with five different facial expressions and viewing angles. Our results show that the decision fusion leads to improvement of recognition accuracy when compared to the individual approaches as well as to recognition based on regular imaging.

Original languageEnglish
Title of host publicationApplications of Digital Image Processing XXXIV
StatePublished - 2011
EventApplications of Digital Image Processing XXXIV - San Diego, CA, United States
Duration: 22 Aug 201124 Aug 2011

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
ISSN (Print)0277-786X


OtherApplications of Digital Image Processing XXXIV
Country/TerritoryUnited States
CitySan Diego, CA


  • face recognition
  • hyperspectral imagery
  • orthogonal subspace projection


Dive into the research topics of 'Face recognition using spectral and spatial information'. Together they form a unique fingerprint.

Cite this