Compressively Sensed Image Recognition

Ayşen Değerli, Sinem Aslan, Mehmet Yamac, Bulent Sankur, Moncef Gabbouj

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

22 Citations (Scopus)


Compressive Sensing (CS) theory asserts that sparse signal reconstruction is possible from a small number of linear measurements. Although CS enables low-cost linear sampling, it requires non-linear and costly reconstruction. Recent literature works show that compressive image classification is possible in CS domain without reconstruction of the signal. In this work, we introduce a DCT base method that extracts binary discriminative features directly from CS measurements. These CS measurements can be obtained by using (i) a random or a pseudorandom measurement matrix, or (ii) a measurement matrix whose elements are learned from the training data to optimize the given classification task. We further introduce feature fusion by concatenating Bag of Words (BoW) representation of our binary features with one of the two state-of-the-art CNN-based feature vectors. We show that our fused feature outperforms the state-of-the-art in both cases.

Original languageEnglish
Title of host publicationProceedings of the 2018 7th European Workshop on Visual Information Processing, EUVIP 2018
EditorsI. Tabus, K. Egiazarian, F. Battisti, L. Oudre, C. Larabi, A. Beghdadi
Number of pages6
ISBN (Electronic)9781538668979
Publication statusPublished - 2 Jul 2018
MoE publication typeA4 Article in a conference publication


  • Compressive Classification
  • Compressive Learning
  • Compressive Sensing
  • DCT-based Binary Descriptor
  • Inference on Measurement Domain
  • Learned Measurement Matrix


Dive into the research topics of 'Compressively Sensed Image Recognition'. Together they form a unique fingerprint.

Cite this