Perception-based Image Interpolation

Image interpolation is used widely in the computer vision. Holding edge information is main problem in the image interpolation. By using bilinear and bicubic B-spline interpolation methods, a novel image interpolation approach was proposed in this paper. Firstly, inverse distance weighted average method was used to reduce image’s noise. Secondly, edge detection operator was used to extract image's edges information. It can help us to select different interpolation methods in the image interpolation process. Finally, we selected bilinear interpolation approach at non-edge regions, and bicubic B-spline interpolation method was used near edges regions. Further more, control vertexes were computed from pixels with calculation formula which has been simplified in the B-spline interpolation process. Experiments showed the interpolated image by the proposed method had good vision results for it could hold image's edge information effectively.

Area-based matching is a fundamental image processing operation to obtain the displacement between images. Also, the similarity interpolation method to estimate subpixel displacement is commonly used to enhance resolution. Conventionally, similarity interpolation estimation is performed by assuming that the horizontal and vertical displacements are independent. Almost no investigations of estimation error over the conventional method have been made, but it is inferred experientially that subpixel estimation with image interpolation or gradient-based methods is more precise than the similarity interpolation method. This paper proposes a novel 2D subpixel displacement estimation method based on similarity interpolation through modeling of 2D self-similarity. The proposed method requires no “a priori” knowledge of 2D similarity and no images at all. It adopts no iteration. Furthermore, the proposed method entails only slightly higher calculation costs than the conventional similarity interpolation method. The proposed method can obtain more precise estimation than both the conventional similarity interpolation method and the image interpolation method using comparison of subpixel estimation accuracy. An experiment using actual images demonstrates the effectiveness of the proposed method. © 2005 Wiley Periodicals, Inc. Syst Comp Jpn, 36(2): 1–11, 2005; Published online in Wiley InterScience (). DOI 10.1002sscj.20221

Edge-based image interpolation often leads to an image with good quality because of the importance of sharp edges and smooth contours to the human vision. The wavelet-based image interpolation approach has good potential in producing interpolated images with high quality edges. Using the wavelet multiresolution analysis theory, such method is computationally demanding. In this paper, a new edge-based image interpolation method that uses symmetric biorthogonal wavelet transform is proposed. We form a list of ideal step edges and study the relationships between the wavelet approximation sub-image of each edge and its wavelet detail sub-images. Based on these relationships, a simple and efficient algorithm that predicts the edge information of high resolution images is proposed. For this method, the 9/7-M inverse wavelet transform is shown, experimentally, to yield better image interpolation performance compared to traditional image interpolation approaches

This paper presents a novel real-time super-resolution (SR) method using directionally adaptive image interpolation and image restoration. The proposed interpolation method estimates the edge orientation using steerable filters and performs edge refinement along the estimated edge orientation. Bi-linear and bi-cubic interpolation filters are then selectively used according to the estimated edge orientation for reducing jagging artifacts in slanting edge regions. The proposed restoration method can effectively remove image degradation caused by interpolation using the directionally adaptive truncated constrained least-squares (TCLS) filter. The proposed method provides high-quality magnified images which are similar to or better than the result of advanced interpolation or SR methods without high computational load. Experimental results indicate that the proposed system gives higher peak-to-peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) values than the state-of-the-art image interpolation methods.

Latent Embedded Graphs for Image and Shape Interpolation

PDE (Partial differential equation) is an image interpolation method which interpolates based on local geometry property. It can not preserve texture pattern and can only process natural image. NL (Non Local)-means is an interpolation method that uses global information of image. Entire texture pattern in image can be well preserved because of the high replication property of NL-means, while the problem is that blur is preserved as well. In this paper a novel image interpolation method which combines PDE and NL-means is proposed. Image interpolated by the novel method is clear and smooth, and preserves texture pattern. The new method enhances edges using shock filter PDE which does not strengthen jaggies of block contour in interpolated image; the PDE used in this method to smooth image diffuses along level curve. Divided gray regions caused by PDE are smoothed by NL-means; the broken texture pattern is recovered well. Lastly, it is proved that even noisy image can be directly interpolated to the required size using this method. Both theoretical analysis and experiments have been used to verify the benefits of the novel interpolation method.

This work presents a new image interpolation technique for image cracking such as telop character occlusion or picture deterioration. The landscape picture and texture pattern or other natural scenes contain the behavior of the autocorrelation pattern, and a method of image interpolation based on the autocorrelation pattern has been established. This method extracts many local regions from a piece of image and generates a subspace by the image vectors. The subspace limits the freedom of the image description at the local region by the hyperplane restriction in the image vector space. This paper explains for an image interpolation method based on eigen-space and explains the expansion using kernel non-linear projection.

A nonlinear method for image interpolation is presented based on spatial domain directional interpolation. Existing directional interpolation algorithms, which only consider edge regions, are extended to the whole image by interpolating in multiple directions. The interpolated values along various directions are combined using directional weights, which depend on the variation in that direction. The interpolation value for each direction is assigned based on the magnitude of its directional derivative.

An efficient general data hiding scheme based on image interpolation

Image interpolation is widely used for the field of medical image processing. In this paper, interpolation methods are divided into three groups: filter interpolation, ordinary interpolation and ge...

We consider the problem of image interpolation from an adaptive optimal recovery point of view. Many different standard interpolation approaches may be viewed through the prism of optimal recovery. We review some standard image interpolation methods and how they relate to optimal recovery as well as introduce a broader, more general and systematic approach to image interpolation using adaptive optimal recovery.

Low complexity image interpolation method based on path selection

An magnified image enhancement algorithm is presented in this study. Image interpolation is an important image magnification tool, but the magnified image has not been changed by the traditional image interpolation methods even if the magnified image is not satisfaction. Basically, the interpolating surface is determined uniquely for the given interpolating data. Namely the interpolating surface (magnified image) is fixed when the interpolating data (gray value of original image) is given. If the magnified image needs to be enhanced, another enhancement method must be chosen after image magnifying. The image magnification and enhancement are separated. The image natural attribute will be effected. To overcome the disadvantages of the traditional methods, a new method which combined the image magnification and enhancement is proposed. A bivariate rational interpolation with parameters is used in the algorithm. The value of the interpolating function at any point in the interpolating region can be modified under the condition that the interpolating data are not changed by selecting the suitable parameters. Using the surface control, the enlarged image enhancement is implemented. The experiment shows that the algorithm is efficient.

Computer-assisted surveillance of complex environments is becoming more and more interesting, thanks to significant improvements in real-time signal processing. In the surveillance research field applied to public areas, crowd monitoring is very useful but presents particularly complex problems. Recognizing human bodies and tracking their movements in complex real scenes by using a sequence of images are among the most difficult tasks in computer vision. The main difficulties arise both from the high level of shape variability associated with moving human bodies, and from the complexity of environmental real scenes. A method for tracking human motion in 3D real scenes by means of Kalman filtering is presented It is based on the introduction of a suitable mathematical model for a human body moving in a 3D scene and interacting with the surrounding environment. The developed refined static and dynamic models allow the system to be accurate and robust. Due to its real-time functioning, accuracy and robustness, the method can be used in surveillance systems devoted to assure public safety.

Roussos and Maragos proposed a method for image interpolation in "Reversible interpolation of vectorial images by an anisotropic diffusion-projection PDE." An earlier version was also published in conference paper (Roussos and Maragos, "Vector-Valued Image Interpolation by an Anisotropic Diffusion-Projection PDE," 2007). Given a discretely sampled image v, the method finds an image u such that v(n) = (h * u)(n), for all n in Z2, where h is the (assumed known) point spread function and * denotes convolution. The method is inspired by tensor-driven diffusion works of Tschumperlé and Weickert. Roussos and Maragos propose interpolation by evolving a diffusion equation to steady state, dt u = P0(div(T gradient(u)), where T is a tensor determined from image structure tensor and the diffusion is orthogonally projected to agree with the observed data. This diffusion is based on the general anisotropic diffusion model proposed by Weickert. The method can be applied to grayscale, color, or general vector-valued images.