Large image collection visualization using perception-based similarity with color features


Conference


Z. Chen, C. G. Healey
12 International Symposium on Visual Computing (ISVC '16), 2016, pp. 379-390

View PDF Semantic Scholar DBLP DOI
Cite

Cite

APA   Click to copy
Chen, Z., & Healey, C. G. (2016). Large image collection visualization using perception-based similarity with color features (pp. 379–390).


Chicago/Turabian   Click to copy
Chen, Z., and C. G. Healey. “Large Image Collection Visualization Using Perception-Based Similarity with Color Features.” In , 379–390, 2016.


MLA   Click to copy
Chen, Z., and C. G. Healey. Large Image Collection Visualization Using Perception-Based Similarity with Color Features. 2016, pp. 379–90.


BibTeX   Click to copy

@conference{z2016a,
  title = {Large image collection visualization using perception-based similarity with color features},
  year = {2016},
  journal = {},
  pages = {379-390},
  doi = {},
  author = {Chen, Z. and Healey, C. G.},
  booktitle = {12 International Symposium on Visual Computing (ISVC '16)}
}

Abstract

This paper introduces the basic steps to build a similarity-based visualization tool for large image collections. We build the similarity metric s based on human perception. Psychophysical experiments have shown that human observers can recognize the gist of scenes within 100 milliseconds (msec) by comprehending the global properties of an image. Color also plays an important role in human rapid scene recognition. However, previous works often neglect color features. We propose new scene descriptors that preserve the information from coherent color regions, as well as the spatial layouts of scenes. Experiments show that our descriptors outperform existing state-of-the-art approaches. Given the similarity metrics, a hierarchical structure of an image collection can be built in a top-down manner. Representative images are chosen for image clusters and visualized using a force-directed graph.


Share



Follow this website


You need to create an Owlstown account to follow this website.


Sign up

Already an Owlstown member?

Log in