Content-Based Image Retrieval Using Angles Across Scales
Komal Nain Sukhia, Syed Sohaib Ali, Muhammad Mohsin Riaz, Abdul Ghafoor, Benish Amin
Abstract
This letter proposes a content-based image retrieval technique using novel dense angle descriptor and dictionary learning (DL). The histogram of oriented gradients (HOG) descriptor fails to obtain rotation invariance and well-defined rotation behavior, and therefore, a dense angle-based HOG descriptor has been presented to address the image rotation invariance. The technique computes angles across multiple scales and uses bag-of-visual features at different scales for DL. Experiments conducted on building and remote sensing datasets show that the proposed technique achieves high retrieval performance.
Topics & Concepts
HistogramRotation (mathematics)Artificial intelligenceImage retrievalComputer scienceHistogram of oriented gradientsPattern recognition (psychology)Image (mathematics)Computer visionContent (measure theory)Content-based image retrievalViewing angleMathematicsOperating systemMathematical analysisLiquid-crystal displayAdvanced Image and Video Retrieval TechniquesImage Retrieval and Classification TechniquesRemote-Sensing Image Classification