The following information was submitted:
Transactions: WSEAS TRANSACTIONS ON INFORMATION SCIENCE AND APPLICATIONS
Transactions ID Number: 52-652
Full Name: Feng Zhilin
Position: Ph.D. Candidate
Age: ON
Sex: Male
Address: zhejiang university
Country: CHINA
Tel:
Tel prefix:
Fax:
E-mail address: zjuhzjacky@gmail.com
Other E-mails: zjhzjacky@126.com
Title of the Paper: A Unified Image Denoising and Segmentation Algorithm for Ink-Jet Printing Image Based on Fuzzy Optimization Technology
Authors as they appear in the Paper:
Email addresses of all the authors:
Number of paper pages: 14
Abstract: In this paper, a novel unified image denoising and segmentation algorithm is proposed for ink-jet printing texture images, which is built based on the techniques of Beltrami manifold, phase field model and shape prior technology. The energy functional for the proposed model consists of three terms, i.e., Beltrami flow term, phase field term and shape prior term. Beltrami flow is applied to enhance image features while preserving natural fine structures. The phase field model is introduced to extract specific pattern structures within an ink-jet printing image. The shape prior term for the deformable framework through a non-linear energy term is designed to attract a shape towards the Beltrami flow and phase field at given directions. A novel fuzzy optimization method (Multi-start Fuzzy Optimization Method, MSFOM) is also proposed to find numerical solving of the unified image denoising and segmentation model. MSFOM is a hybrid algorithm with fuzzy logic and genetic!
algorithms, which is able to find global minimum with low computational cost. Experimental results show that the proposed method offers effective noise removal in real noisy ink-jet printing images while maintaining fine structure of patterns.
Keywords: Ink-jet printing; Beltrami manifold; Phase field; Fuzzy optimization; Image segmentation; Image denoising
EXTENSION of the file: .pdf
Special (Invited) Session:
Organizer of the Session:
How Did you learn about congress:
IP ADDRESS: 58.100.176.125
