A quality analysis on JPEG 2000 compressed leukocyte images by means of segmentation algorithms

  • Authors:

  • Alexander Falcón-Ruiz;Juan Paz-Viera;Alberto Taboada-Crispí;Hichem Sahli

  • Affiliations:

  • Center for Studies on Electronics and Information Technologies, Universidad Central de Las Villas, Santa Clara, VC, Cuba;Center for Studies on Electronics and Information Technologies, Universidad Central de Las Villas, Santa Clara, VC, Cuba;Center for Studies on Electronics and Information Technologies, Universidad Central de Las Villas, Santa Clara, VC, Cuba;Vrije Universiteit Brussel, Dept. Electronics & Informatics, Brussels, Belgium

  • Venue:
  • CIARP'10 Proceedings of the 15th Iberoamerican congress conference on Progress in pattern recognition, image analysis, computer vision, and applications
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

Reducing image file size by means of lossy compression algorithms can lead to distortions inimage contentaffectingdetection of fine detail structures, either by human orautomated observation. In the case of microscopic images of blood cells, which usually occupy large amounts of disk space, the use of such procedures is justified within a controlled quality loss. Although JPEG 2000 remains as the accepted standard for lossycompression, still a set of guidelines need to be established in order to use this codec in its lossy mode and for particular applications. The present paper deals with a quality analysis of reconstructed microscopic leukocytes images after they have beenlossy compressed. The quality loss is investigated near the lower compression boundby evaluating the performance of several segmentation algorithms together with objective quality metrics. The value of compression rate of142:1 is estimated from the experiments.