Semantic Image Enhancement

Joint Statistical Analysis of Images and Keywords with Applications in Semantic Image Enhancement

A. Lindner; A. Shaji; N. Bonnier; S. Süsstrunk

2012. ACM Multimedia , Osaka, Japan , October 29 - November 2, 2012. p. 489-498.

DOI : 10.1145/2393347.2393417.

With the advent of social image-sharing communities, millions of images with associated semantic tags are now available online for free and allow us to exploit this abundant data in new ways. We present a fast non-parametric statistical framework designed to analyze a large data corpus of images and semantic tag pairs and find correspondences between image characteristics and semantic concepts. We learn the relevance of different image characteristics for thousands of keywords from one million annotated images. We demonstrate the framework's effectiveness with three different examples of semantic image enhancement: we adapt the gray-level tone-mapping, emphasize semantically relevant colors, and perform a defocus magnification for an image based on its semantic context. The performance of our algorithms is validated with psychophysical experiments.

Example Images

Semantic tone-mapping:

dark/sand before
output: dark
dark after
output: sand
sand after
See more example images for semantic tone-mapping and the psychophysical experiments.

Color enhancement:

dark after
output: strawberry
sand after
See more example images for color re-rendering.

Depth-of-field adaptation:

dark after
output: macro
sand after
See more example images for spatial frequency re-rendering.

Supplementary material for the statistical framework


Questions or feedback are welcome. Please mail the author or visit his website.