Image Interpolation by Adaptive 2-D Autoregressive Modeling and Soft-Decision Estimation using image processing


ABSTRACT:

The challenge of image interpolation is to preserve spatial details. We propose a soft-decision interpolation technique that estimates missing pixels in groups rather than one at a time. The new technique learns and adapts to varying scene structures using a 2-D piecewise autoregressive model. The model parameters are estimated in a moving window in the input low-resolution image. The pixel structure dictated by the learnt model is enforced by the soft-decision estimation process onto a block of pixels, including both observed and estimated. The result is equivalent to that of a high-order adaptive no separable 2-D interpolation filter. This new image interpolation approach preserves spatial coherence of interpolated images better than the existing methods, and it produces the best results so far over a wide range of scenes in both PSNR measure and subjective visual quality. Edges and textures are well preserved and common interpolation artefacts (blurring, ringing, jaggiest, zippering, etc.) Are greatly reduced.

EXISTING SYSTEM:

The existing system uses the bicubic interpolation method ,which results image interpolation from lower resolution to higher resolution image.

DISADVANTAGES:

1. PSNR is low
2. Poor  SSIM 


PROPOSED SYSTEM:

A novel soft-decision approach is proposed for adaptive image interpolation. When coupled with a piecewise autoregressive image model, the soft-decision approach estimates a block of missing pixels jointly by imposing an adaptively learnt spatial sample relation not only between known pixels and missing pixels but also between missing pixels themselves. This new image interpolation technique outperforms the existing methods in both PSNR measure and subjective visual quality over a wide range of scenes, by preserving the spacial coherence of the reconstructed HR image on features of large and small scales alike.

ADVANTAGES:

1. Good PSNR as compared to the existing system
2. SSIM is better
3. Error rate is very less.

BLOCK DIAGRAM:

 ALGORITHM:

1. 2D Autoregressive 
2. SAI

SYSTEM REQUIREMENTS:

HARDWARE REQUIREMENTS:

Processor Type : Pentium -IV
Speed : 2.4 GHZ
Ram : 128 MB RAM
Hard disk                                : 20 GB HD

SOFTWARE REQUIREMENTS

Operating System             : Windows 7 
Software Programming Package : Matlab R2014a

REFERENCES:

R. G. Keys, “Cubic convolution interpolation for digital image processing,”B IEEE TranS. Acoust., Speech, Signal Process., vol. ASSP-29, no. 6, pp. 1153–1160, Dec. 1981


12:48 AM 1 Crore Projects
Latest Post