Computationally efficient data and application driven color transforms for the compression and enhancement of images and video

Massimo Minervini*, Cristian Rusu, Sotirios A. Tsaftaris

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

An important step in color image or video coding and enhancement is the linear transformation of input (typically red-green-blue (RGB)) data into a color space more suitable for compression, subsequent analysis, or visualization. The choice of this transform becomes even more critical when operating in distributed and low-computational power environments, such as visual sensor networks or remote sensing. Data-driven transforms are rarely used due to increased complexity. Most schemes adopt fixed transforms to decorrelate the color channels which are then processed independently. Here we propose two frameworks to find appropriate data-driven transforms in different settings. The first, named approximate Karhunen-Loève Transform (aKLT), performs comparable to the KLT at a fraction of the computational complexity, thus favoring adoption on sensors and resource-constrained devices. Furthermore, we consider an application-aware setting in which an expert system (e.g., a classifier) analyzes imaging data at the receiver’s end. In a compression context, distortion may jeopardize the accuracy of the analysis. Since the KLT is not optimal in this setting, we investigate formulations that maximize post-compression expert system performance. Relaxing decorrelation and energy compactness constraints, a second transform can be obtained offline with supervised learning methods. Finally, we propose transforms that accommodate both constraints, and are found using regularized optimization.

Original languageEnglish
Title of host publicationColor Image and Video Enhancement
PublisherSpringer International Publishing AG
Pages371-393
Number of pages23
ISBN (Electronic)9783319093635
ISBN (Print)9783319093628
DOIs
Publication statusPublished - 1 Jan 2015
Externally publishedYes

Keywords

  • application-aware compression
  • Color space transformation
  • Foley-Sammon transform
  • image coding
  • Karhunen-Loève transform
  • low computational complexity
  • unsupervised and supervised learning
  • UPEG 2000

Fingerprint

Dive into the research topics of 'Computationally efficient data and application driven color transforms for the compression and enhancement of images and video'. Together they form a unique fingerprint.

Cite this