Browsing by Author "Krishna, Sai"
Now showing 1 - 2 of 2
Results Per Page
Sort Options
- A parametric spectral model for texture-based saliencePublication . Terzic, Kasim; Krishna, Sai; du Buf, J. M. H.; Gall, J.; Gehler, P.; Leibe, B.We present a novel saliency mechanism based on texture. Local texture at each pixel is characterised by the 2D spectrum obtained from oriented Gabor filters. We then apply a parametric model and describe the texture at each pixel by a combination of two 1D Gaussian approximations. This results in a simple model which consists of only four parameters. These four parameters are then used as feature channels and standard Difference-of-Gaussian blob detection is applied in order to detect salient areas in the image, similar to the Itti and Koch model. Finally, a diffusion process is used to sharpen the resulting regions. Evaluation on a large saliency dataset shows a significant improvement of our method over the baseline Itti and Koch model.
- Texture features for object saliencePublication . Terzic, Kasim; Krishna, Sai; du Buf, J. M. H.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. (C) 2017 Elsevier B.V. All rights reserved.