Texture features for object salience
MetadataShow full item record
Although texture is important for many vision-related tasks, it is not used in most salience models. As a consequence, there are images where all existing salience algorithms fail. We introduce a novel set of texture features built on top of a fast model of complex cells in striate cortex, i.e., visual area V1. The texture at each position is characterised by the two-dimensional local power spectrum obtained from Gabor filters which are tuned to many scales and orientations. We then apply a parametric model and describe the local spectrum by the combination of two one-dimensional Gaussian approximations: the scale and orientation distributions. The scale distribution indicates whether the texture has a dominant frequency and what frequency it is. Likewise, the orientation distribution attests the degree of anisotropy. We evaluate the features in combination with the state-of-the-art VOCUS2 salience algorithm. We found that using our novel texture features in addition to colour improves AUC by 3.8% on the PASCAL-S dataset when compared to the colour-only baseline, and by 62% on a novel texture-based dataset.
Terzić , K , Krishna , S & du Buf , J M H 2017 , ' Texture features for object salience ' Image and Vision Computing , vol. 67 , pp. 43-51 . https://doi.org/10.1016/j.imavis.2017.09.007
Image and Vision Computing
© 2017 Elsevier Ltd. This work has been made available online in accordance with the publisher’s policies. This is the author created, accepted version manuscript following peer review and may differ slightly from the final published version. The final published version of this work is available at https://doi.org/10.1016/j.imavis.2017.09.007
DescriptionThis work was supported by the EU under the FP-7 grant ICT-2009.2.1-270247 NeuralDynamics and by the FCT under the grants LarSYS UID/EEA/50009/2013 and SparseCoding EXPL/EEI-SII/1982/2013.
Items in the St Andrews Research Repository are protected by copyright, with all rights reserved, unless otherwise indicated.