• Publications
  • Influence
SLIC Superpixels Compared to State-of-the-Art Superpixel Methods
TLDR
We empirically compare five state-of-the-art superpixel algorithms for their ability to adhere to image boundaries, speed, memory efficiency, and their impact on segmentation performance. Expand
  • 5,637
  • 954
  • PDF
Frequency-tuned salient region detection
TLDR
We introduce a method for salient region detection that outputs full resolution saliency maps with well-defined boundaries of salient objects. Expand
  • 2,186
  • 435
Frequency-tuned salient region detection
TLDR
We introduce a frequency-tuned approach to estimate center-surround contrast using color and luminance features that offers three advantages over existing methods: uniformly highlighted salient regions with welldefined boundaries. Expand
  • 1,068
  • 161
  • PDF
SLIC Superpixels ?
Superpixels are becoming increasingly popular for use in computer vision applications. However, there are few algorithms that output a desired number of regular, compact superpixels with a lowExpand
  • 567
  • 91
  • PDF
A Frequency Domain Approach to Registration of Aliased Images with Application to Super-resolution
TLDR
We propose a frequency domain technique to precisely register a set of aliased images, based on their low-frequency, aliasing-free part of the images. Expand
  • 526
  • 58
  • PDF
Saliency detection using maximum symmetric surround
TLDR
We present a novel saliency detection algorithm based on the idea of maximum symmetric surround. Expand
  • 353
  • 57
  • PDF
Salient Region Detection and Segmentation
TLDR
We present a novel method to determine salient regions in images using low-level features of luminance and color. Expand
  • 836
  • 49
  • PDF
Multi-spectral SIFT for scene category recognition
TLDR
We show that the addition of near-infrared information leads to significantly improved performance in a scene-recognition task, and that the improvements are greater still when an appropriate 4-dimensional colour representation is used. Expand
  • 251
  • 40
  • PDF
Linear demosaicing inspired by the human visual system
TLDR
We have developed a Fourier-domain model for spatial multiplexing of color, common to CFA images and the human retina, allowing for demosaicing by spatial frequency filtering. Expand
  • 328
  • 39
  • PDF
Superpixels and Polygons Using Simple Non-iterative Clustering
TLDR
We present an improved version of the Simple Linear Iterative Clustering (SLIC) superpixel segmentation. Expand
  • 96
  • 22
  • PDF