Several pathologies are detected by counting different types of leukocytes in digital microscopic images. However, manipulation of these images, i.e. storage and/or transmission, can be complicated by the large sizes of the files containing them. In order to tackle this particular situation, lossy compression codecs such as JPEG 2000 have been employed while preserving the overall perceived image quality. In this paper a strategy based on objective quality metrics and performance of segmentation algorithms is proposed for the estimation of the maximal allowable compression rate (CR) where deterioration introduced in the images by the JPEG 2000 codec does not affect identification of white blood cells. Results indicate that the estimated value lays around CR = 142:1 as measured by the metrics employed
Falcón-Ruiz, A, Paz-Viera, J, Sahli, H & Carrasco-ochoa, JA (ed.) 2010, 'Estimating quality bounds of JPEG 2000 compressed leucocytes images', Lecture Notes in Computer Science, vol. 6225, pp. 107-114.
Falcón-Ruiz, A., Paz-Viera, J., Sahli, H., & Carrasco-ochoa, J. A. (Ed.) (2010). Estimating quality bounds of JPEG 2000 compressed leucocytes images. Lecture Notes in Computer Science, 6225, 107-114.
@article{a7f2131f42a243d6bff0ff7df4b45487,
title = "Estimating quality bounds of JPEG 2000 compressed leucocytes images",
abstract = "Several pathologies are detected by counting different types of leukocytes in digital microscopic images. However, manipulation of these images, i.e. storage and/or transmission, can be complicated by the large sizes of the files containing them. In order to tackle this particular situation, lossy compression codecs such as JPEG 2000 have been employed while preserving the overall perceived image quality. In this paper a strategy based on objective quality metrics and performance of segmentation algorithms is proposed for the estimation of the maximal allowable compression rate (CR) where deterioration introduced in the images by the JPEG 2000 codec does not affect identification of white blood cells. Results indicate that the estimated value lays around CR = 142:1 as measured by the metrics employed",
keywords = "segmentation, compression, cell images",
author = "Alexander Falc{\'o}n-Ruiz and J. Paz-Viera and Hichem Sahli and Carrasco-ochoa, {J. Ariel}",
note = "J. Ariel Carrasco-Ochoa; MCPR 2010 - Mexican Conference on Pattern Recognition ; Conference date: 27-09-2010 Through 29-09-2010",
year = "2010",
language = "English",
volume = "6225",
pages = "107--114",
journal = "Lecture Notes in Computer Science",
issn = "0302-9743",
publisher = "Springer Verlag",
}