Multimedia Tools and Applications
https://doi.org/10.1007/s11042-018-7056-4
A software supported image enhancement approach based
on DCT and quantile dependent enhancement with a total
control on enhancement level
DCT-Quantile
Mayank Tiwari
1
· Subir Singh Lamba
1
· Bhupendra Gupta
1
Received: 22 February 2018 / Revised: 30 August 2018 / Accepted: 11 December 2018 /
© Springer Science+Business Media, LLC, part of Springer Nature 2018
Abstract
In many computer vision applications like medical imaging, pattern recognition etc., image
enhancement is an important pre-processing requirement which is used to improve the effi-
ciency of an application. A significantly large literature is available on image enhancement;
unfortunately, most of these schemes have certain shortcomings for e.g. the lack of control
over the contrast starching, noise enhancement and ‘mean-shift’ problem etc. To deal with
the aforementioned problems, this study suggests an efficient method which is based on dis-
crete cosine transformation (DCT) and quantile dependent sub-division of the histogram of
given input image. In the proposed method, we apply DCT on the input image to get low-
frequency component (LFC) and then use the quantile-based sub-division on the histogram
of LFC. Finally, histogram equalization is performed on all these sub-histograms separately.
The main advantage of quantile-based segmentation is that here entire intensity spectrum
participates in the enhancement process, which provides a total control over the enhance-
ment level. In the proposed method the high-frequency component remains untouched and
hence the structural information of the input image and the noise in the input image remains
unaffected by the image enhancement process.
Keywords Discrete cosine transform · Contrast enhancement · Linearly quantile separated
histogram equalization · Greyscale images · Mean-shift problem
Mayank Tiwari
mayanktiwariggits@gmail.com
Subir Singh Lamba
subirs@gmail.com
Bhupendra Gupta
gupta.bhupendra@gmail.com
1
Department of Mathematics, PDPM Indian Institute of Information Technology,
Design & Manufacturing, Jabalpur, MP 482005, India