University of Waterloo

Category: Statistical Textural Distinctiveness for Salient Region Detection in Natural Images

  • Bi Hongbo

    Bi Hongbo

    My research interests are in the fields of digital watermarking, signal processing, pattern recognition and related fields. I am currently particularly interested in statistical modeling and feature extraction of natural images.

  • Christian Scharfenberger

    Christian Scharfenberger

    My research interests are in the fields of computer vision, image processing, and pattern recognition with an emphasis on saliency computation, camera calibration and stereo vision. I am particularly interested in practical applications of computer vision and image processing methods to problems in robotics and driver assistance systems.

  • Statistical Textural Distinctiveness for Salient Region Detection in Natural Images

    Statistical Textural Distinctiveness for Salient Region Detection in Natural Images

    A novel statistical textural distinctiveness approach for robustly detecting salient regions in natural images is proposed. Rotational-invariant neighborhood-based textural representations are extracted and used to learn a set of representative texture atoms for defining a sparse texture model for the image. Based on the learnt sparse texture model, a weighted graphical model is constructed to…

  • Alexander Wong

    Alexander Wong

    My research interests lie in the field of artificial intelligence and computational imaging, with a focus on scalable and explainable deep learning and computational biomedical imaging systems.

  • David Clausi

    David Clausi

    My research interests are in the fields of computer vision, image processing, and pattern recognition with an emphasis on the automated interpretation of SAR (synthetic aperture radar) and biomedical imagery. I am an active interdisciplinary and multidisciplinary researcher, publishing refereed journal and conference papers in the diverse fields of remote sensing, computer vision, algorithm design,…