Conference Papers

Permanent URI for this collectionhttps://idr.nitk.ac.in/handle/123456789/28506

Browse

Subject: search.filters.subject.Scale Invariant Feature Transform (SIFT)

Search Results

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Semantic image retrieval system based on object relationships
    (2013) Shivakumar, S.; Goel, N.; Ananthanarayana, V.S.; Cyriac, C.; Rajaram, P.
    Semantic-based image retrieval has recently become popular as an avenue to improve retrieval accuracy. The 'semantic gap' between the visual features and the high-level semantic features could be narrowed down by utilizing this kind of retrieval method. However, most of the current methods of semantic-based image retrieval utilize visual semantic features and do not consider spatial relationships. We build a system for content-based image retrieval from image collections on the web and tackle the challenges of distinguishing between images that contain similar objects, in order to capture the semantic meaning of a search query. In order to do so, we utilize a combination of segmentation into objects as well as the relationships of these objects with each other. © 2013 IEEE.
  • No Thumbnail Available
    Item
    Locality-constrained linear coding based fused visual features for robust acoustic event classification
    (International Speech Communication Association, 2019) Mulimani, M.; Koolagudi, G.K.
    In this paper, a novel Fused Visual Features (FVFs) are proposed for Acoustic Event Classification (AEC) in the meeting room and office environments. The codes of Visual Features (VFs) are evaluated from row vectors and Scale Invariant Feature Transform (SIFT) vectors of the grayscale Gammatonegram of an acoustic event separately using Locality-constrained Linear Coding (LLC). Further, VFs from row vectors and SIFT vectors of the grayscale Gammatonegram are fused to get FVFs. Performance of the proposed FVFs is evaluated on acoustic events of publicly available UPC-TALP and DCASE datasets in clean and noisy conditions. Results show that proposed FVFs are robust to noise and achieve overall recognition accuracy of 96.40% and 90.45% on UPC-TALP and DCASE datasets, respectively. © 2019 ISCA