A computationally efficient context based switched image interpolation algorithm for natural images
10 May 2011-pp 1-4
TL;DR: In this article, the authors proposed a new computationally efficient interpolation algorithm for natural images, in which unknown pixels are divided into few bins and the categorization of these unknown pixels into bins is based upon the characteristics of the neighboring pixels.
Abstract: In this paper we proposed a new computationally efficient interpolation algorithm for natural images in which unknown pixels are divided into few bins. The categorization of these unknown pixels into bins is based upon the characteristics of the neighboring pixels. These characteristics are obtained by taking difference of two slopes which are in orthogonal direction and these slopes are calculated from a set of neighboring pixels. We used the Least-Squares (LS) based approach to find optimal predictors for pixels belonging to various slope bins. We also presented a simplified proposed algorithm in which we used bilinear interpolation algorithm instead of estimating LS based predictor for some bins and it results into further reduction in computational complexity without sacrificing the much performance. Our proposed algorithm gives better interpolation quality with significantly lower computational complexity as compared to recently reported interpolation algorithms.
Citations
More filters
13 May 2012
TL;DR: This work has presented different set of fixed predictors for both smooth type and edgy type of images and proposed a modified algorithm in which selection of prediction parameter is done on block by block basis instead of image basis.
Abstract: Recently a lot of interpolation algorithms are proposed, but these interpolation algorithms are highly computationally expensive. Hence these algorithms cannot be implemented and used in real time applications. In view of real time applications we have proposed a computationally simple interpolation algorithm. In our proposed algorithm the unknown pixels are categorized into various bins depending upon the characteristic of the neighboring pixels (activity level) and for each bin fixed prediction parameters are used for prediction. We have presented different set of fixed predictors for both smooth type and edgy type of images. We have also proposed a modified algorithm in which selection of prediction parameter is done on block by block basis instead of image basis. Our proposed algorithm gives much better qualitative and quantitative performance as compared to other computationally simple interpolation algorithms.
20 citations
Cites background or methods from "A computationally efficient context..."
...Section II discuss the review of existing algorithm [3]....
[...]
...Both the proposed algorithms follow the same procedure of classifying the unknown pixels into several bins as in CBI [3] but we define a fixed set of prediction parameters for interpolation of unknown pixels for both smooth and edgy blocks/images....
[...]
...A context based switching interpolation algorithm [3] was designed in which unknown pixels are divided into several classes depending on the characteristics of neighboring pixels....
[...]
...In this phase, slope (SH ) is calculated and similar bin boundary values of CBI [3] are used....
[...]
...We follow the same procedure of CBI [3] while categorizing the unknown pixels into several classes....
[...]
01 Dec 2012
TL;DR: From the simulation results, it is found that the adaptive interpolation technique results in better subjective and objective (PSNR) quality in comparision to some of the recent works in literature.
Abstract: In this paper, we propose a new adaptive image interpolation algorithm for enhancement of natural images. The proposed method uses different algorithms namely SAI, SPIA and Context-Based Image Interpolation Algorithm (CBIA) techniques, for both edgy and smooth type of images. The detailed part of smooth type image is interpolated by SAI, while we propose to use SPIA method for detailed part of edgy image. The rest of the pixels for either type of images are interpolated by CBIA. From the simulation results, we found that our adaptive interpolation technique results in better subjective and objective (PSNR) quality in comparision to some of the recent works in literature.
2 citations
01 Dec 2012
TL;DR: Experimental results indicates that the proposed algorithm gives better quantitative performance as compared to other conventional interpolation techniques.
Abstract: This paper proposes a new interpolation approach for obtaining high resolution (HR) images from its low resolution (LR) images. We are using the Least Squared based block by block prediction scheme to estimate the predictors using Jacobian iteration method. In spite of Jacobian's Iterative property of convergence for diagonally dominant matrices only, our proposed method uses this property effectively for all types of matrices, and found a set of prediction coefficients using a small number of iterative steps. Due to its lesser computational cost it can be used in real time applications too. Use of iterative methods like Jacobi gives an advantage of its application over images which gives singular matrices during operation. Experimental results indicates that the proposed algorithm gives better quantitative performance as compared to other conventional interpolation techniques.
1 citations
02 Dec 2013
TL;DR: This paper proposes a generic two phase image interpolation algorithm based upon error feedback mechanism that plays a significant role in improving prediction accuracy of those algorithms which have inherently poor prediction capability for certain types of images.
Abstract: Many image interpolation algorithms have been developed in the recent past aiming for high prediction accuracy. But these algorithms are focused only towards better predictor design. In this paper, we propose a generic two phase image interpolation algorithm based upon error feedback mechanism. In the first phase, we learn error pattern occurred during interpolation of down sampled version of original Low Resolution (LR) image. It is assumed that similar error pattern also occurrs during the interpolation of original LR image. Hence, error pattern learnt in first phase, is employed during the interpolation of original LR image (second phase). From extensive experiments, we found that our algorithm gives a significant improvement in prediction accuracy of existing interpolation algorithms. In particular, our algorithm plays a significant role in improving prediction accuracy of those algorithms which have inherently poor prediction capability for certain types of images.
01 Sep 2013
TL;DR: A new generic algorithm for image interpolation as well as lossless image coding is presented that gives insignificant loss in terms of compression ratio as compared with some of the previous works reported in literature.
Abstract: This paper presents a new generic algorithm for image interpolation as well as lossless image coding. Main motivation behind the work is to reduce computational complexity involved in using Least Square Error Minimization (LS). The proposed method down samples the given image to its quarter size and then to its (1/16)th size. For each downsampled image, the least Square predictors are then obtained corresponding to pixels belonging to each bin. Thus, these predictors are used to synthetically generate a set of optimal predictors corresponding to each bin of the original image. Our proposed algorithm thus reduces 60% to 70% of computational complexity. We also observed that proposed algorithm gives insignificant loss in terms of compression ratio as compared with some of the previous works reported in literature.
Cites background or methods from "A computationally efficient context..."
...[11] http://decsai.ugr.es/cvg/CG/base.htm Image Processing Image and Video Coding Techniques 250...
[...]
...It works as follows: 1) We downsample the given image to (1/4)th of its original size and then, classified the existing pixels of the given image into different classes called bins....
[...]
...[5] X. Li and M.T. Orchard ”Edge-Directed Prediction of Lossless Compression of Natural Images,” in IEEE Transaction On Image Processing, Vol. 10, Issue 6, pp. 813 - 817 June 2001....
[...]
...Jakhetiya and Tiwari [2] had proposed a block based interpolation technique SPIA (single pass Interpolation algorithm)....
[...]
...REVIEW OF EXISTING METHOD...
[...]
References
More filters
TL;DR: Simulation results demonstrate that the new interpolation algorithm substantially improves the subjective quality of the interpolated images over conventional linear interpolation.
Abstract: This paper proposes an edge-directed interpolation algorithm for natural images. The basic idea is to first estimate local covariance coefficients from a low-resolution image and then use these covariance estimates to adapt the interpolation at a higher resolution based on the geometric duality between the low-resolution covariance and the high-resolution covariance. The edge-directed property of covariance-based adaptation attributes to its capability of tuning the interpolation coefficients to match an arbitrarily oriented step edge. A hybrid approach of switching between bilinear interpolation and covariance-based adaptive interpolation is proposed to reduce the overall computational complexity. Two important applications of the new interpolation algorithm are studied: resolution enhancement of grayscale images and reconstruction of color images from CCD samples. Simulation results demonstrate that our new interpolation algorithm substantially improves the subjective quality of the interpolated images over conventional linear interpolation.
1,933 citations
"A computationally efficient context..." refers methods in this paper
...To preserve edge structures in interpolation, Li and Orchard proposed to estimate the covariance of high-resolution (HR) image from the covariance of the low-resolution (LR) image, and then interpolate the missing pixels based on the estimated covariance (NEDI) [ 1 ]....
[...]
...The NEDI [ 1 ] method is pixel by pixel interpolation method....
[...]
TL;DR: A new edge-guided nonlinear interpolation technique is proposed through directional filtering and data fusion that can preserve edge sharpness and reduce ringing artifacts in image interpolation algorithms.
Abstract: Preserving edge structures is a challenge to image interpolation algorithms that reconstruct a high-resolution image from a low-resolution counterpart. We propose a new edge-guided nonlinear interpolation technique through directional filtering and data fusion. For a pixel to be interpolated, two observation sets are defined in two orthogonal directions, and each set produces an estimate of the pixel value. These directional estimates, modeled as different noisy measurements of the missing pixel are fused by the linear minimum mean square-error estimation (LMMSE) technique into a more robust estimate, using the statistics of the two observation sets. We also present a simplified version of the LMMSE-based interpolation algorithm to reduce computational cost without sacrificing much the interpolation performance. Experiments show that the new interpolation techniques can preserve edge sharpness and reduce ringing artifacts
971 citations
"A computationally efficient context..." refers background in this paper
...Alternatively, Zhang and Wu proposed to interpolate a missing pixel in multiple directions, and then fuse the directional interpolation results by minimum mean square-error estimation [3]....
[...]
TL;DR: A soft-decision interpolation technique that estimates missing pixels in groups rather than one at a time, which preserves spatial coherence of interpolated images better than the existing methods and produces the best results so far over a wide range of scenes in both PSNR measure and subjective visual quality.
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 nonseparable 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 artifacts (blurring, ringing, jaggies, zippering, etc.) are greatly reduced.
588 citations
"A computationally efficient context..." refers methods in this paper
...Zhang and Wu proposed an Image Interpolation algorithm based on the Adaptive 2-D Autoregressive Modeling and Soft-Decision Estimation (SAI) [4]....
[...]
...D Autoregressive Modeling and Soft-Decision Estimation (SAI) [4]....
[...]
...On an average our proposed algorithmm gives 0.17, 0.04 and 0.1 db better PSNR than NEDI7, SPIA and SAI respectively....
[...]
TL;DR: The underlying computational foundations of all these algorithms and their implementation techniques are described and some experimental results are presented to show the impact of these algorithms in terms of image quality metrics and computational requirements for implementation.
Abstract: Image interpolation is an important image processing operation applied in diverse areas ranging from computer graphics, rendering, editing, medical image reconstruction, to online image viewing. Image interpolation techniques are referred in literature by many terminologies, such as image resizing, image resampling, digital zooming, image magnification or enhancement, etc. Basically, an image interpolation algorithm is used to convert an image from one resolution (dimension) to another resolution without loosing the visual content in the picture. Image interpolation algorithms can be grouped in two categories, non-adaptive and adaptive. The computational logic of an adaptive image interpolation technique is mostly dependent upon the intrinsic image features and contents of the input image whereas computational logic of a non-adaptive image interpolation technique is fixed irrespective of the input image features. In this paper, we review the progress of both non-adaptive and adaptive image interpolation techniques. We also proposed a new algorithm for image interpolation in discrete wavelet transform domain and shown its efficacy. We describe the underlying computational foundations of all these algorithms and their implementation techniques. We present some experimental results to show the impact of these algorithms in terms of image quality metrics and computational requirements for implementation.
73 citations
"A computationally efficient context..." refers methods in this paper
...Conventional interpolation methods include linear, cubic and spline [2,5] interpolation algorithms belief that missing...
[...]
26 Feb 2010
TL;DR: The algorithm uses a piece-wise autoregressive (PAR) model to predict the unknown pixels of high resolution image and it is shown that subjective as well as objective quality of the high resolution (HR) images is same, on an average, as that of the competitive such method reported in literature.
Abstract: This paper presents a new interpolation algorithm based on the adaptive 2-D autoregressive modeling. The
algorithm uses a piece-wise autoregressive (PAR) model to predict the unknown pixels of high resolution
image. For this purpose, we used a block-based prediction model to predict the unknown pixels. The
unknown pixels are categorized into three categories and they are predicted using predictors of different
structure and order. Prediction accuracy and the visual quality of the interpolated image depend on the size of
the window. We experimentally found an appropriate window size and have shown that subjective as well as
objective (PSNR) quality of the high resolution (HR) images is same, on an average, as that of the
competitive such method reported in literature and also the method is a single pass.
16 citations
"A computationally efficient context..." refers methods in this paper
...Jakhetiya and Tiwari proposed a single pass interpolation algorithm (SPIA) [6] based on least square estimation....
[...]
...Hence, our proposed simplified algorithm saves a lot of computation power as compared to NEDI and SPIA....
[...]
...In order to interpolate low resolution image of size 256×256, SPIA requires 3×256 (256 corresponding to fourth order and 256×2 corresponding to sixth order) number of least square estimation....
[...]
...In this section we compared proposed algorithm with New edge directed interpolation (NEDI) algorithm and single pass interpolation algorithm (SPIA) in terms of number of multiplications and number of matrix inversions....
[...]
...Single pass interpolation [6] algorithm (SPIA) requires three type of predictors of fourth and sixth order per block (16×16)....
[...]