The Visual Computer

, Volume 30, Issue 4, pp 443–453

SalientShape: group saliency in image collections

  • Ming-Ming Cheng
  • Niloy J. Mitra
  • Xiaolei Huang
  • Shi-Min Hu
Original Article

DOI: 10.1007/s00371-013-0867-4

Cite this article as:
Cheng, MM., Mitra, N.J., Huang, X. et al. Vis Comput (2014) 30: 443. doi:10.1007/s00371-013-0867-4

Abstract

Efficiently identifying salient objects in large image collections is essential for many applications including image retrieval, surveillance, image annotation, and object recognition. We propose a simple, fast, and effective algorithm for locating and segmenting salient objects by analysing image collections. As a key novelty, we introduce group saliency to achieve superior unsupervised salient object segmentation by extracting salient objects (in collections of pre-filtered images) that maximize between-image similarities and within-image distinctness. To evaluate our method, we construct a large benchmark dataset consisting of 15 K images across multiple categories with 6000+ pixel-accurate ground truth annotations for salient object regions where applicable. In all our tests, group saliency consistently outperforms state-of-the-art single-image saliency algorithms, resulting in both higher precision and better recall. Our algorithm successfully handles image collections, of an order larger than any existing benchmark datasets, consisting of diverse and heterogeneous images from various internet sources.

Keywords

Saliency detectionGroup saliencyObject of interest segmentationImage retrieval

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Ming-Ming Cheng
    • 1
  • Niloy J. Mitra
    • 2
  • Xiaolei Huang
    • 3
  • Shi-Min Hu
    • 1
  1. 1.TNListTsinghua UniversityBeijingChina
  2. 2.University College LondonLondonUK
  3. 3.Lehigh UniversityBethlehemUSA