JPEG-deblocking of Blood Cell Images using Deep Learning
(2020) In Master's Theses in Mathematical Sciences FMAM05 20202Mathematics (Faculty of Engineering)
- Abstract
- This thesis investigates the use of convolutional neural networks as a reconstruction or JPEG- deblocking model for JPEG-compressed blood cell images, needed due to the well known block artifacts caused by JPEG-compression. CellaVision develops automated microscopy for blood analysis that detects and classifies blood cells from images. The automated analysis is carried out on high resolu- tion microscope images, before the images are compressed to JPEG-75 format, where 75 is the quality factor. We investigate how hard the blood cell images can be compressed to still enable acceptable reconstruction quality for display to the user.
We propose a CNN-model that reconstructs blood cell JPEG-images of quality factor 50 and higher, to PSNR... (More) - This thesis investigates the use of convolutional neural networks as a reconstruction or JPEG- deblocking model for JPEG-compressed blood cell images, needed due to the well known block artifacts caused by JPEG-compression. CellaVision develops automated microscopy for blood analysis that detects and classifies blood cells from images. The automated analysis is carried out on high resolu- tion microscope images, before the images are compressed to JPEG-75 format, where 75 is the quality factor. We investigate how hard the blood cell images can be compressed to still enable acceptable reconstruction quality for display to the user.
We propose a CNN-model that reconstructs blood cell JPEG-images of quality factor 50 and higher, to PSNR and SSIM values on average higher than JPEG-75 blood cell images. Using our method, 99.9% of the blood cell images are improved in terms of PSNR and SSIM. However, these metrics do not take into account opinions of professional laboratory technicians who are the main users of CellaVision’s application. A comparison is made between a model predicting in the RGB colorspace and the YCbCr colorspace, the later being exploited by the JPEG-compression algorithm.
Results show that models trained on input images of higher or random quality outperform models trained on lower quality, even in the reconstruction of low quality images. Predicting from a higher quality factor is safer when considering quality criteria for medical images and their use in diagnosing, where image quality is critical. With our thesis we propose that CellaVision could store the images with JPEG-50 and still achieve a reconstructed image with a quality as good as JPEG-75, based on the SSIM and PSNR metrics, and thereby save 31% of storage space compared to today. (Less) - Popular Abstract (Swedish)
- En genomgående trend i alla företag och industrier är att deras förmåga att producera data växer fortare än deras förmåga att lagra den, och detta gäller även hos CellaVision som producerar mikroskopiska blodcellsbilder. Lösningen är att komprimera bilderna med konsekvensen att viss information förloras. Vi har använt oss av djupinlärnings-metoder för att rekonstruera den försvunna datan i bilderna och visat att man kan komprimera bilderna hårdare och fortfarande rekonstruera dem.
Please use this url to cite or link to this publication:
http://lup.lub.lu.se/student-papers/record/9030829
- author
- Ma, Justin LU and Hafsbrandt Fovaeus, Julia LU
- supervisor
- organization
- alternative title
- Bildförbättring av JPEG-komprimerade blodcellsbilder med hjälp av djupinlärning
- course
- FMAM05 20202
- year
- 2020
- type
- H2 - Master's Degree (Two Years)
- subject
- keywords
- Image Analysis, Image Reconstruction, Image Restoration, Image Compression, Machine Learning, Deep Learning, JPEG, JPEG-deblocking, CellaVision, Neural Networks, Convolutional Neural Networks, Blood Cells, White Blood Cells, Microscopy, Microscope
- publication/series
- Master's Theses in Mathematical Sciences
- report number
- LUTFMA-3433-2020
- ISSN
- 1404-6342
- other publication id
- 2020:E77
- language
- English
- id
- 9030829
- date added to LUP
- 2020-12-14 19:19:26
- date last changed
- 2020-12-14 19:19:26
@misc{9030829,
abstract = {{This thesis investigates the use of convolutional neural networks as a reconstruction or JPEG- deblocking model for JPEG-compressed blood cell images, needed due to the well known block artifacts caused by JPEG-compression. CellaVision develops automated microscopy for blood analysis that detects and classifies blood cells from images. The automated analysis is carried out on high resolu- tion microscope images, before the images are compressed to JPEG-75 format, where 75 is the quality factor. We investigate how hard the blood cell images can be compressed to still enable acceptable reconstruction quality for display to the user.
We propose a CNN-model that reconstructs blood cell JPEG-images of quality factor 50 and higher, to PSNR and SSIM values on average higher than JPEG-75 blood cell images. Using our method, 99.9% of the blood cell images are improved in terms of PSNR and SSIM. However, these metrics do not take into account opinions of professional laboratory technicians who are the main users of CellaVision’s application. A comparison is made between a model predicting in the RGB colorspace and the YCbCr colorspace, the later being exploited by the JPEG-compression algorithm.
Results show that models trained on input images of higher or random quality outperform models trained on lower quality, even in the reconstruction of low quality images. Predicting from a higher quality factor is safer when considering quality criteria for medical images and their use in diagnosing, where image quality is critical. With our thesis we propose that CellaVision could store the images with JPEG-50 and still achieve a reconstructed image with a quality as good as JPEG-75, based on the SSIM and PSNR metrics, and thereby save 31% of storage space compared to today.}},
author = {{Ma, Justin and Hafsbrandt Fovaeus, Julia}},
issn = {{1404-6342}},
language = {{eng}},
note = {{Student Paper}},
series = {{Master's Theses in Mathematical Sciences}},
title = {{JPEG-deblocking of Blood Cell Images using Deep Learning}},
year = {{2020}},
}