SalientShape: Group saliency in image collections

Ming Ming Cheng, Niloy J. Mitra, Xiaolei Huang, Shi Min Hu

Research output: Contribution to journalArticle

170 Scopus citations

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.

Original languageEnglish (US)
Pages (from-to)443-453
Number of pages11
JournalVisual Computer
Volume30
Issue number4
DOIs
StatePublished - Apr 2014

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition
  • Computer Graphics and Computer-Aided Design

Fingerprint Dive into the research topics of 'SalientShape: Group saliency in image collections'. Together they form a unique fingerprint.

  • Cite this