Ketan Tang

Antialiasing Filter Design for Subpixel Downsampling via Frequency-Domain Analysis

In this paper, we are concerned with image downsampling using subpixel techniques to achieve superior sharpness for small liquid crystal displays (LCDs). Such a problem exists when a high-resolution image or video is to be displayed on low-resolution display terminals. Limited by the low-resolution display, we have to shrink the image. Signal-processing theory tells us that optimal decimation requires low-pass filtering with a suitable cutoff frequency, followed by downsampling. In doing so, we need to remove many useful image details causing blurring. Subpixel-based downsampling, taking advantage of the fact that each pixel on a color LCD is actually composed of individual red, green, and blue subpixel stripes, can provide apparent higher resolution. In this paper, we use frequency-domain analysis to explain what happens in subpixel-based downsampling and why it is possible to achieve a higher apparent resolution. According to our frequency-domain analysis and observation, the cutoff frequency of the low-pass filter for subpixel-based decimation can be effectively extended beyond the Nyquist frequency using a novel antialiasing filter. Applying the proposed filters to two existing subpixel downsampling schemes called direct subpixel-based downsampling (DSD) and diagonal DSD (DDSD), we obtain two improved schemes, i.e., DSD based on frequency-domain analysis (DSD-FA) and DDSD based on frequency-domain analysis (DDSD-FA). Experimental results verify that the proposed DSD-FA and DDSD-FA can provide superior results, compared with existing subpixel or pixel-based downsampling methods.

Novel 2-D MMSE Subpixel-Based Image Down-Sampling

Subpixel-based down-sampling is a method that can potentially improve apparent resolution of a down-scaled image on LCD by controlling individual subpixels rather than pixels. However, the increased luminance resolution comes at price of chrominance distortion. A major challenge is to suppress color fringing artifacts while maintaining sharpness. We propose a new subpixel-based down-sampling pattern called diagonal direct subpixel-based down-sampling (DDSD) for which we design a 2-D image reconstruction model. Then, we formulate subpixel-based down-sampling as a MMSE problem and derive the optimal solution called minimum mean square error for subpixel-based down-sampling (MMSE-SD). Unfortunately, straightforward implementation of MMSE-SD is computational intensive. We thus prove that the solution is equivalent to a 2-D linear filter followed by DDSD, which is much simpler. We further reduce computational complexity using a small k × k filter to approximate the much larger MMSE-SD filter. To compare the performances of pixel and subpixel-based down-sampling methods, we propose two novel objective measures: normalized l1 high frequency energy for apparent luminance sharpness and PSNRU(V) for chrominance distortion. Simulation results show that both MMSE-SD and MMSE-SD(k) can give sharper images compared with conventional down-sampling methods, with little color fringing artifacts.

Compressing similar image sets using low frequency template

In advance of the imaging capturing technology, large amount of similar images are created. Instead of compressing each similar image individually, removing the inter-image redundancy would reduce the storage and transmission time. However, only a few set redundancy methods are proposed to deal with the problem. In this paper, a new method was derived from a theoretical model by extracting the low frequency in an image set. For the similar images, the values of their low frequency components are very close to that of their neighboring pixel in the spatial domain. In our model, a low frequency template is created and used as a prediction for each image to compute its residue. This model proves the reduction in the entropy and hence the bit rates. Experiments were conducted and proved there were up to 30% gains over the existing methods.

Color clustering matting

Natural image matting refers to the problem of extracting regions of interest such as foreground object from an image based on user inputs like scribbles or trimap. More specifically, we need to estimate the color information of background, foreground and the corresponding opacity, which is an ill-posed problem inherently. Inspired by closed-form matting and KNN matting, in this paper, we extend the local color line model which is based on the assumption of linear color clustering within a small local window, to nonlocal feature space neighborhood. New affinity matrix is defined to achieve better clustering. Further, we demonstrate that good clustering ensures better prediction of alpha matte. Experimental evaluations on benchmark datasets and comparisons show that our matting algorithm is of higher accuracy and better visual quality than some state-of-the-art matting algorithms.

Image colorization using sparse representation

Image colorization is the task to color a grayscale image with limited color cues. In this work, we present a novel method to perform image colorization using sparse representation. Our method first trains an over-complete dictionary in YUV color space. Then taking a grayscale image and a small subset of color pixels as inputs, our method colorizes overlapping image patches via sparse representation; it is achieved by seeking sparse representations of patches that are consistent with both the grayscale image and the color pixels. After that, we aggregate the colorized patches with weights to get an intermediate result. This process iterates until the image is properly colorized. Experimental results show that our method leads to high-quality colorizations with small number of given color pixels. To demonstrate one of the applications of the proposed method, we apply it to transfer the color of one image onto another to obtain a visually pleasing image.

Image Interpolation Using Autoregressive Model and Gauss-Seidel Optimization

In this paper we propose a simple yet effective image interpolation algorithm based on autoregressive model. Unlike existing algorithms which rely on low resolution pixels to estimate interpolation coefficients, we optimize the interpolation coefficients and high resolution pixel values jointly from one optimization problem. Although the two sets of variables are coupled in the cost function, the problem can be effectively solved using Gauss-Seidel method. We prove the iterations are guaranteed to converge. Experiments show that on average we have over 3dB gain compared to bicubic interpolation and over 0.1dB gain compared to SAI.

From 2D Extrapolation to 1D Interpolation: Content Adaptive Image Bit-Depth Expansion

In this paper, we address the problem of image bit-depth expansion and present a novel method to generate high bit-depth (HBD) images from a single low bit-depth (LBD) image. We expand image bit-depth by reconstructing the least significant bits (LSBs) for the LBD image after it is rescaled to high bit-depth. For image regions whose intensities are neither locally maximum nor minimum, neighborhood flooding is applied to convert 2D interpolation problem into 1D interpolation, for local maxima/minima (LMM) regions where interpolation is not applicable, a virtual skeleton marking algorithm is proposed to convert problematic 2D extrapolation problem into 1D interpolation. At last, a content-adaptive reconstruction model is proposed to obtain the output HBD image. The experimental results show that proposed method significantly outperforms existing methods in PSNR and SSIM without contouring artifacts.

Nonparametric density estimation on a graph: Learning framework, fast approximation and application in image segmentation

We present a novel framework for tree-structure embedded density estimation and its fast approximation for mode seeking. The proposed method could find diverse applications in computer vision and feature space analysis. Given any undirected, connected and weighted graph, the density function is defined as a joint representation of the feature space and the distance domain on the graphs spanning tree. Since the distance domain of a tree is a constrained one, mode seeking can not be directly achieved by traditional mean shift in both domain. we address this problem by introducing node shifting with force competition and its fast approximation. Our work is closely related to the previous literature of nonparametric methods. One shall see, however, that the new formulation of this problem can lead to many advantages and new characteristics in its application, as will be illustrated later in this paper.

Halftone image watermarking via optimization

Although halftone image watermarking technologies have been rapidly developing in the 21st century, the existing techniques lack a theoretical basis. In this paper, we tackle halftone image watermarking problems from a theoretical perspective. First, we propose a general optimization framework for Halftone Visual Watermarking (HVW), which is a certain category of halftone image watermarking techniques. Then two specific HVW problems, Single-sided Embedding Error Diffusion (SEED) and Double-sided Embedding Error Diffusion (DEED) are presented and solved by applying the proposed framework. With SEED and DEED obtained, both the theoretical solutions and experimental results indicate that our previous heuristic methods, Data Hiding by Conjugate Error Diffusion (DHCED) and Data Hiding by Dual Conjugate Error Diffusion (DHDCED), are special cases of SEED and DEED, respectively. We also demonstrate that DEED can achieve outstanding performance compared to DHDCED and other previous methods by selecting different parameters. With this paper, we essentially build a bridge between the theory and practical implementations of HVW problems.

Making 3D Eyeglasses Try-on practical

In this paper, we propose a virtual 3D Eyeglasses Try-on (3DET) system, with efficient, realistic and real-time augmented performance. The 3DET system captures users performance with the help of depth camera and renders the glasses properly on the video stream immediately after users selection. The virtual eye-glasses follow with the motion (movement or rotation) of users head simultaneously. The high efficiency of our 3DET system is achieved by simplifying the eyeglasses matching procedure, making use of the active appearance model (AAM) based face tracking algorithm. This is completely different from existing methods, which usually relies on eye detection. In addition, due to the exploiting of a generic 3D face model during tracking and displaying, the 3DET system can handle occlusion problem easily and render realistic glasses in videos effectively. Experimental results demonstrate that the proposed 3DET system is able to produce superior natural and smooth visual results with virtual glasses fitted on the users face at 30 fps with a high level of accuracy on common hardware.