Matting Technique Research Articles

Motion Regularization for Matting Motion Blurred Objects

This paper addresses the problem of matting motion blurred objects from a single image. Existing single image matting methods are designed to extract static objects that have fractional pixel occupancy. This arises because the physical scene object has a finer resolution than the discrete image pixel and therefore only occupies a fraction of the pixel. For a motion blurred object, however, fractional pixel occupancy is attributed to the object’s motion over the exposure period. While conventional matting techniques can be used to matte motion blurred objects, they are not formulated in a manner that considers the object’s motion and tend to work only when the object is on a homogeneous background. We show how to obtain better alpha mattes by introducing a regularization term in the matting formulation to account for the object’s motion. In addition, we outline a method for estimating local object motion based on local gradient statistics from the original image. For the sake of completeness, we also discuss how user markup can be used to denote the local direction in lieu of motion estimation. Improvements to alpha mattes computed with our regularization are demonstrated on a variety of examples.

Image Forgery Using An Enhanced Bayesian Matting Algorithm

Abstract The development of forgery techniques for multimedia has recently become an important research topic This paper proposes a new method to construct a tampered image based on the matting approach. Most previous matting techniques focus on the alpha estimation of the source image, since an accurate alpha matte can help with compositing the selected object into a new scene. However, the lighting conditions are inherently assumed to be coherent between the source image and the new scene. We propose an enhanced Bayesian matting method that adopts a new nearest-neighbor sampling method to extract color information. It can produce a more accurate alpha matte than previous methods, especially on the fuzzy boundaries. Furthermore, the paper deals with the lighting consistency problem. The proposed approach analyzes the color variations and shading effect and then adjusts the extracted foreground object to combine with the new background. Experimental results demonstrate the effectiveness of our method by s...

Static Measure of Foot Loading

Static and dynamic loading of the foot are important characteristics for understanding human walking in both health and disease. The goal of this investigation was to determine whether an objective measure of normal midstance loading of the foot could reliably be recorded using readily available disposable qualitative recording devices. Ten randomly selected normal volunteers were trained to step on Harris mat and Pressure Stat recording devices during normal walking. Each of the recordings was divided into 5 weight-bearing regions by 2 separate examiners. After outlining each foot, the recordings were digitized and compared. Interobserver reliability ranged from 0.81 to 0.96 for the Harris mat technique and 0.94 to 0.97 for the Pressure Stat technique. Data from a linear regression plot indicate high precision of calculations of the foot masks between the 2 examiners based on an R(2) value of 0.966 using the Pressure Stat method. These data plus a linear regression plot suggest that both qualitative recording devices, when digitized using a standardized format, appear to obtain a reliable objective measure of midstance loading during normal gait. The Pressure Stat device may be slightly more reliable. It is planned to use this standardized experimental model to compare objectively patterns of midstance loading in patients with injury or disease that is capable of altering normal walking.

Video SnapCut

Although tremendous success has been achieved for interactive object cutout in still images, accurately extracting dynamic objects in video remains a very challenging problem. Previous video cutout systems present two major limitations: (1) reliance on global statistics, thus lacking the ability to deal with complex and diverse scenes; and (2) treating segmentation as a global optimization, thus lacking a practical workflow that can guarantee the convergence of the systems to the desired results. We present Video SnapCut , a robust video object cutout system that significantly advances the state-of-the-art. In our system segmentation is achieved by the collaboration of a set of local classifiers, each adaptively integrating multiple local image features. We show how this segmentation paradigm naturally supports local user editing and propagates them across time. The object cutout system is completed with a novel coherent video matting technique. A comprehensive evaluation and comparison is presented, demonstrating the effectiveness of the proposed system at achieving high quality results, as well as the robustness of the system against various types of inputs.

SoftCuts: A Soft Edge Smoothness Prior for Color Image Super-Resolution

Designing effective image priors is of great interest to image super-resolution (SR), which is a severely under-determined problem. An edge smoothness prior is favored since it is able to suppress the jagged edge artifact effectively. However, for soft image edges with gradual intensity transitions, it is generally difficult to obtain analytical forms for evaluating their smoothness. This paper characterizes soft edge smoothness based on a novel SoftCuts metric by generalizing the Geocuts method . The proposed soft edge smoothness measure can approximate the average length of all level lines in an intensity image. Thus, the total length of all level lines can be minimized effectively by integrating this new form of prior. In addition, this paper presents a novel combination of this soft edge smoothness prior and the alpha matting technique for color image SR, by adaptively normalizing image edges according to their alpha-channel description. This leads to the adaptive SoftCuts algorithm, which represents a unified treatment of edges with different contrasts and scales. Experimental results are presented which demonstrate the effectiveness of the proposed method.

On the Apparent Transparency of a Motion Blurred Object

An object which moves during the exposure time results in a blurred smear in the image. We consider the smear as if it was the image of a semitransparent object, and we retrieve its alpha matte by means of known techniques. The alpha value at a pixel is meaningfully interpreted as the fraction of the exposure time during which the object projection overlapped that pixel. Basing on this fact, our work highlights interesting qualitative and quantitative properties of the alpha matte, which can be used to derive constraints on the object’s apparent contour, and its motion during the exposure time, from a single motion-blurred image; we also show that some of these properties hold on the original image. The theory is validated with experimental results both on synthetic and real images, highlighting strengths and limitations; we point out a range of possible applications, including blurred image interpretation, temporal superresolution of object contours, model-based reconstruction of nontrivial motion, and improvements of alpha matting techniques.

Alternative formulation of Bayesian-based digital matting technique

An alternative formulation to the original Bayesian-based digital matting technique is described. With the new formulation, a user does not need to choose an image-dependent noise variance parameter, as in the original method. An iterative algorithm that avoids exhaustive search is provided. Performance comparison with the original method is given.

Poisson matting

In this paper, we formulate the problem of natural image matting as one of solving Poisson equations with the matte gradient field. Our approach, which we call Poisson matting , has the following advantages. First, the matte is directly reconstructed from a continuous matte gradient field by solving Poisson equations using boundary information from a user-supplied trimap. Second, by interactively manipulating the matte gradient field using a number of filtering tools, the user can further improve Poisson matting results locally until he or she is satisfied. The modified local result is seamlessly integrated into the final result. Experiments on many complex natural images demonstrate that Poisson matting can generate good matting results that are not possible using existing matting techniques.

Coastal Systems: A Pre-Vegetated Mat Technique for the Restoration of Submersed Aquatic Vegetation

Coastal Systems: A Pre-Vegetated Mat Technique for the Restoration of Submersed Aquatic Vegetation

Video matting of complex scenes

This paper describes a new framework for video matting, the process of pulling a high-quality alpha matte and foreground from a video sequence. The framework builds upon techniques in natural image matting, optical flow computation, and background estimation. User interaction is comprised of garbage matte specification if background estimation is needed, and hand-drawn keyframe segmentations into "foreground," "background" and "unknown". The segmentations, called trimaps, are interpolated across the video volume using forward and backward optical flow. Competing flow estimates are combined based on information about where flow is likely to be accurate. A Bayesian matting technique uses the flowed trimaps to yield high-quality mattes of moving foreground elements with complex boundaries filmed by a moving camera. A novel technique for smoke matte extraction is also demonstrated.

Free musculocutaneous and muscle flaps for foot reconstruction: a clinical and gait analysis study

Between 1986 and 1995, 48 microvascular flaps (14 fasciocutaneous, 13 muscle, and 21 musculocutaneous) were performed on 47 patients with foot defects. The study group consisted of 19 patients who successfully underwent weightbearing surface reconstruction with free musculocutaneous flaps or muscle flaps with a skin graft. The groups were identified on the basis of the free flap used. Group 1: Latissimus dorsi musculocutaneous flaps (11 patients); group 2: Skin grafted muscle flaps (8 patients: latissimus dorsi - 6, gracilis - 1, rectus abdominis - 1). The follow-up period was 1–11 years (average: 8.3 years). Follow-up included documentation of foot pain, presence of ulceration, sensory recovery, the ability to wear normal shoes, and the need for a second operation. In group 1, debulking operations were necessary (8 patients, 72.7%). Debulking was not required in group 2. Ulceration occurred in four (36.4%) group 1 patients and in one (12.5%) group 2 patient. All patients had good deep pressure sensation. All the group 2 patients could wear normal shoes. Four (36.4%) of the group 1 patients had to wear special orthopedic shoes. The gait analysis consisted of two parts: footprint analysis with the Harris mat technique and plantogram of Parotec system by Kraemer. Foot analysis with the Harris mat showed that the pressure on the muscle flap is less than the pressure on the musculocutaneous flap. Gait analysis by the Parotec system showed that in patients with musculocutaneous flaps, static load distribution on the reconstructed bare foot is nearly normal, but dynamic load distribution is pathological. In patients with muscle flaps, both static and dynamic load distribution were close to normal.

Outgrowing trends in the lower extremities of children

The authors present an overview of the changing biomechanical values in the growing child. They discuss a technique of evaluating total genu varum and genu valgus. A simple tread mat technique is presented.