Multimed Tools Appl (2018) 77:31095–31114 https://doi.org/10.1007/s11042-018-6197-9 Sparse representation based facial image compression via multiple dictionaries and separated ROI 1 1,2 Amir Masoud Taheri & Homayoun Mahdavi-Nasab Received: 13 October 2017 /Revised: 29 March 2018 /Accepted: 23 May 2018 / Published online: 4 June 2018 Springer Science+Business Media, LLC, part of Springer Nature 2018 Abstract Constant increasing of visual information necessitates most efficient image compression schemes for saving storage space or reducing required transmission band- width. In compressing a class of images, such as a fingerprint database, facial images of an organization or MR images of a hospital, overall information redundancy is increased and compression becomes more significant. In this paper, image signal sparse represen- tation and RLS-DLA dictionary design are utilized for compressing whole or part of a facial image database by exploiting the structural similarity of the class members. In the proposed algorithm, images are compressed by multiple overcomplete learned dictionar- ies which are designed to provide least required bit-rates for different target qualities. To fortify the process, more interested head and shoulders regions of the images are extracted to provide dictionary training sets. A combined edge detection and active contour segmentation method is used for a robust
Multimedia Tools and Applications – Springer Journals
Published: Jun 4, 2018
It’s your single place to instantly
discover and read the research
that matters to you.
Enjoy affordable access to
over 18 million articles from more than
15,000 peer-reviewed journals.
All for just $49/month
Query the DeepDyve database, plus search all of PubMed and Google Scholar seamlessly
Save any article or search result from DeepDyve, PubMed, and Google Scholar... all in one place.
Get unlimited, online access to over 18 million full-text articles from more than 15,000 scientific journals.
Read from thousands of the leading scholarly journals from SpringerNature, Elsevier, Wiley-Blackwell, Oxford University Press and more.
All the latest content is available, no embargo periods.
“Hi guys, I cannot tell you how much I love this resource. Incredible. I really believe you've hit the nail on the head with this site in regards to solving the research-purchase issue.”Daniel C.
“Whoa! It’s like Spotify but for academic articles.”@Phil_Robichaud
“I must say, @deepdyve is a fabulous solution to the independent researcher's problem of #access to #information.”@deepthiw
“My last article couldn't be possible without the platform @deepdyve that makes journal papers cheaper.”@JoseServera