Hock Soon Seah

Complex Object Correspondence Construction in Two-Dimensional Animation

Correspondence construction of objects in key frames is the precondition for inbetweening and coloring in 2-D computer-assisted animation production. Since each frame of an animation consists of multiple layers, objects are complex in terms of shape and structure. Therefore, existing shape-matching algorithms specifically designed for simple structures such as a single closed contour cannot perform well on objects constructed by multiple contours with an open shape. This paper introduces a semisupervised patch alignment framework for complex object correspondence construction. In particular, the new framework constructs local patches for each point on an object and aligns these patches in a new feature space, in which correspondences between objects can be detected by the subsequent clustering. For local patch construction, pairwise constraints, which indicate the corresponding points (must link) or unfitting points (cannot link), are introduced by users to improve the performance of correspondence construction. This kind of input is convenient for animation software users via user-friendly interfaces. A dozen of experimental results on our cartoon data set that is built on industrial production suggest the effectiveness of the proposed framework for constructing correspondences of complex objects. As an extension of our framework, additional shape retrieval experiments on MPEG-7 data set show that its performance is comparable with that of a prominent algorithm published in T-PAMI 2009.

On Combining Multiple Features for Cartoon Character Retrieval and Clip Synthesis

How do we retrieve cartoon characters accurately? Or how to synthesize new cartoon clips smoothly and efficiently from the cartoon library? Both questions are important for animators and cartoon enthusiasts to design and create new cartoons by utilizing existing cartoon materials. The first key issue to answer those questions is to find a proper representation that describes the cartoon character effectively. In this paper, we consider multiple features from different views, i.e., color histogram, Hausdorff edge feature, and skeleton feature, to represent cartoon characters with different colors, shapes, and gestures. Each visual feature reflects a unique characteristic of a cartoon character, and they are complementary to each other for retrieval and synthesis. However, how to combine the three visual features is the second key issue of our application. By simply concatenating them into a long vector, it will end up with the so-called “curse of dimensionality,” let alone their heterogeneity embedded in different visual feature spaces. Here, we introduce a semisupervised multiview subspace learning (semi-MSL) algorithm, to encode different features in a unified space. Specifically, under the patch alignment framework, semi-MSL uses the discriminative information from labeled cartoon characters in the construction of local patches where the manifold structure revealed by unlabeled cartoon characters is utilized to capture the geometric distribution. The experimental evaluations based on both cartoon character retrieval and clip synthesis demonstrate the effectiveness of the proposed method for cartoon application. Moreover, additional results of content-based image retrieval on benchmark data suggest the generality of semi-MSL for other applications.

Fringe pattern denoising using coherence-enhancing diffusion

Electronic speckle pattern interferometry is one of the methods measuring the displacement on object surfaces in which fringe patterns need to be evaluated. Noise is one of the key problems affecting further processing and reducing measurement quality. We propose an application of coherence-enhancing diffusion to fringe-pattern denoising. It smoothes a fringe pattern along directions both parallel and perpendicular to fringe orientation with suitable diffusion speeds to more effectively reduce noise and improve fringe-pattern quality. It is a generalized work of Tangs et al.s [Opt. Lett.33, 2179 (2008)] model that only smoothes a fringe pattern along fringe orientation. Since our model diffuses a fringe pattern with an additional direction, it is able to denoise low-density fringes as well as improve denoising effectiveness for high-density fringes. Theoretical analysis as well as simulation and experimental verifications are addressed.

Adaptive T-spline surface fitting to z-map models

Surface fitting refers to the process of constructing a smooth representation for an object surface from a fairly large number of measured 3D data points. This paper presents an automatic algorithm to construct smooth parametric surfaces using T-splines from z-map data. The algorithm begins with a rough surface approximation and then progressively refines it in the regions where the approximation accuracy does not meet the requirement. The topology of the resulting T-spline surface is determined adaptively based on the local geometric character of the input data and the geometry of the control points is obtained by a least squares procedure. The advantage of the approach is that the resulting surface is C2 continuous and the refinement is essentially local, resulting in a small number of control points for the surface.

GPU-Accelerated Real-Time Tracking of Full-Body Motion With Multi-Layer Search

Compared to monocular pose tracking, 3D articulated body pose tracking from multiple cameras can better deal with self-occlusions and meet less ambiguities. Though considerable advances have been made, pose tracking from multiple images has not been extensively studied: very seldom existing work can produce a solution comparable to that of a marker-based system which generally can recover accurate 3D full-body motion in real-time. In this paper, we present a multi-view approach to 3D body pose tracking. We propose a pose search method by introducing a new generative sampling algorithm with a refinement step of local optimization. This multi-layer search method does not rely on strong motion priors and generalizes well to general human motions. Physical constraints are incorporated in a novel way and 3D distance transform is employed for speedup. A voxel subject-specific 3D body model is created automatically at the initial frame to fit the subject to be tracked. We design and develop the optimized parallel implementations of time-consuming algorithms on GPU (Graphics Processing Unit) using CUDA (Compute Unified Device Architecture), which significantly accelerates the pose tracking process, making our method capable of tracking full body movements with a maximum speed of 9 fps. Experiments on various 8-camera datasets and benchmark datasets (HumanEva-II) captured by 4 cameras demonstrate the robustness and accuracy of our method.

Rendering fireworks displays

A particle system technique to model, render, and animate realistic fireworks displays is presented. The attributes of the fireworks display that the particle system models are color, brightness, shape, trial, size, particle dynamics, blinking, mousing, star effect, spinning, and elasticity. A rendering engine that consists of various modules which individually handle a particular property of the particle is described. >

Computer-assisted coloring by matching line drawings

An approach to automatically color line drawings based on feature matching is proposed. The motivation is that coloring 2D animation is still a labor-intensive process in current cartoon film production. The objective of our work is to investigate how to automatically color an image in a cartoon sequence on the basis of the previous frame. Our method first establishes the matching relationship of two images, after which it automatically paints one of them with the color information of the other using a region-matching algorithm. The region-matching algorithm is based on feature correspondences. The results show that the proposed algorithm can straightforwardly and robustly realize our objective and has a promising future for our next step to further automate conventional animation.

Algorithm for directly retrieving the phase difference: a generalization

Determination of phase difference is important in many applications of optical metrology. Algorithms for temporal phase difference measurement using the Fourier transform and phase shifting methods are available. These algorithms are first shown to be equivalent and then are generalized for spatial phase difference measurements and a spatial carrier phase shifting method. The efficiency of the algorithm is verified by two examples for slope and curvature determination.

Fault detection by interferometric fringe pattern analysis using windowed Fourier transform

Windowed Fourier transform (WFT), a tool of spatial-frequency analysis, is able to characterize the local frequency at any location in a fringe pattern. Changes in fringe frequency characterize defects in optical interferometric-based systems. Hence, the WFT is suitable for fault detection and condition monitoring in optical NDT. In this paper, a WFT-based algorithm is described and theoretically analysed for fault detection. This is followed by demonstrations using both simulated and real fringe patterns. Comparisons with the traditional Fourier transform approach and normalized cross correlation approaches are also carried out.

Binary SIPPER plankton image classification using random subspace

Plankton recognition plays an important role in the ocean environmental research. In this paper, we propose a random subspace based algorithm to classify the plankton images detected in real time by the Shadowed Image Particle Profiling and Evaluation Recorder. The difficulty of such classification is multifold because the data sets are not only much noisier but the plankton are deformable, projection-variant, and often in partial occlusion. In addition, the images in our experiments are binary, thus are lack of texture information. Using random sampling, we construct a set of stable classifiers to take full advantage of nearly all the discriminative information in the feature space of plankton images. The combination of multiple stable classifiers is better than a single classifier. We achieve over 93% classification accuracy on a collection of more than 3000 images, making it comparable with what a trained biologist can achieve by using conventional manual techniques.