6533b861fe1ef96bd12c4e20
RESEARCH PRODUCT
Multimodal Images Classification using Dense SURF, Spectral Information and Support Vector Machine
Alamin MansouriAissam BekkariDriss MammassGaëtan Le GoïcHanan Anzidsubject
Computer scienceComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONImage processing02 engineering and technologyImage (mathematics)0202 electrical engineering electronic engineering information engineeringFeature descriptorRepresentation (mathematics)Spectral informationSpeeded up robust features SURFGeneral Environmental SciencePixelbusiness.industry[INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]020206 networking & telecommunicationsPattern recognitionSVM classificationSupport vector machineCultural heritageMultimodal imagesCielab spaceDense features[INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV]General Earth and Planetary Sciences020201 artificial intelligence & image processingArtificial intelligencebusinessFeature learningdescription
International audience; The multimodal image classification is a challenging area of image processing which can be used to examine the wall painting in the cultural heritage domain. In such classification, a common space of representation is important. In this paper, we present a new method for multimodal representation learning, by using a pixel-wise feature descriptor named dense Speed Up Robust Features (SURF) combined with the spectral information carried by the pixel. For classification of extracted features we have used support vector machine (SVM). Our database was extracted from acquisition on cultural heritage wall paintings that contain four modalities UV, Visible, IRR and fluorescence. The experimental results show that the overall accuracy of this method reaches 98.1%, 92.01%, 98.2% and 94.705% in visible, fluorescence image, UVR and IRR respectively.
| year | journal | country | edition | language |
|---|---|---|---|---|
| 2019-01-01 |