A Global Sampling Based Image Matting Using Non-Negative Matrix Factorization
Journal Title: Mehran University Research Journal of Engineering and Technology - Year 2017, Vol 36, Issue 4
Abstract
Image matting is a technique in which a foreground is separated from the background of a given image along with the pixel wise opacity. This foreground can then be seamlessly composited in a different background to obtain a novel scene. This paper presents a global non-parametric sampling algorithm over image patches and utilizes a dimension reduction technique known as NMF (Non-Negative Matrix Factorization). Although some existing non-parametric approaches use large nearby foreground and background regions to sample patches but these approaches fail to take the whole image to sample patches. It is because of the high memory and computational requirements. The use of NMF in the proposed algorithm allows the dimension reduction which reduces the computational cost and memory requirement. The use of NMF also allow the proposed approach to use the whole foreground and background region in the image and reduces the patch complexity and help in efficient patch sampling. The use of patches not only allows the incorporation of the pixel colour but also the local image structure. The use of local structures in the image is important to estimate a high-quality alpha matte especially in the images which have regions containing high texture. The proposed algorithm is evaluated on the standard data set and obtained results are comparable to the state-of-the-art matting techniques
Authors and Affiliations
N. Alam, M. Sarim, A. B. Shaikh
Keywords
Related Articles
- EP ID EP224757
- DOI 10.22581/muet1982.1704.01
- Views 104
- Downloads 0
Utilization of Sawdust in Concrete Masonry Blocks: A Review
SDC (Sawdust Concrete) was developed in 19th century. It has been well recognized due to its lightweight and cost-effectiveness. Presently, developed countries have created opportunities to use wood waste in the concrete...
Just-in-Time Compilation-Inspired Methodology for Parallelization of Compute Intensive Java Code
Compute intensive programs generally consume significant fraction of execution time in a small amount of repetitive code. Such repetitive code is commonly known as hotspot code. We observed that compute intensive hotspot...
An Effective Channel Allocation Scheme to Reduce Co-Channel and Adjacent Channel Interference for WMN Backhaul
Two folded work presents channel allocation scheme sustaining channel orthogonality and channel spacing to reduce CCI (Co-Channel Interference) and ACI (Adjacent Channel Interference) for inter flow of an intra-flow link...
Effect of Intercritical Heat Treatment on Mechanical Properties of Plain Carbon Dual Phase Steel
Mechanical properties of DP (Dual Phase) steels are greatly influenced by the microstructural features such as grain size, morphology and martensite volume fraction (Vm%). These microstructural features can be altered by...
Flood Management Current State, Challenges and Prospects in Pakistan: A Review
Flooding is globally a major natural hazard. Floods result in property and life loss and poor economic development. Though it is not possible to prevent the occurrence of floods, but their negative impacts could be minim...