Image coding using fuzzy edge classifier and fuzzy F-transform: dualFuzzy
by Deepak Gambhir; Navin Rajpal
International Journal of Fuzzy Computation and Modelling (IJFCM), Vol. 1, No. 3, 2015

Abstract: To achieve high compression ratio and good quality of compressed image, a new image compression scheme using fuzzy edge classifier and fuzzy F-transform is proposed. In the proposed scheme, fuzzy edge classifier decides the smooth or edge block, based on membership value of each block which is obtained from Gaussian function. Each smooth fuzzy block is encoded with block mean and edge block is processed using fuzzy F-transform. This encoding scheme is further decoded by applying inverse fuzzy F-transform to edge blocks and mean value to smooth block, to reconstruct the image. The output image of the decoding process shows some artefacts due to mean value of smooth blocks which is further improved by proposed Gaussian block image enhancement scheme. The experimental results show that the proposed scheme to compress the images not only improves the artefacts appearing in reconstructed image but also improves the compression ratio. The PSNR calculated in the dual fuzzy proposed method is superior than PSNR calculated in JPEG, fuzzy F-transform and fuzzy F-transform with single mean value of smooth blocks.

Online publication date: Tue, 16-Jun-2015

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Fuzzy Computation and Modelling (IJFCM):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com