Extracting a polyhedron from a single-view sketch: Topological construction of a wireframe sketch with minimal hidden elements

An essential prerequisite to construct a manifold trihedral polyhedron from a given natural (or partial-view) sketch is solution of the “wireframe sketch from a single natural sketch (WSS)” problem, which is the subject of this paper. Published solutions view WSS as an “image-processing”/“computer vision” problem where emphasis is placed on analyzing the given input (natural sketch) using various heuristics. This paper proposes a new WSS method based on robust tools from graph theory, solid modeling and Euclidean geometry. Focus is placed on producing a minimal wireframe sketch that corresponds to a topologically correct polyhedron.     

Using evolutionary design to interactively sketch car silhouettes and stimulate designer's creativity

An Interactive Genetic Algorithm is proposed to progressively sketch the desired side-view of a car profile. It adopts a Fourier decomposition of a 2D profile as the genotype, and proposes a cross-over mechanism. In addition, a formula function of two genes' discrepancies is fitted to the perceived dissimilarity between two car profiles. This similarity index is intensively used, throughout a series of user tests, to highlight the added value of the IGA compared to a systematic car shape exploration, to prove its ability to create superior satisfactory designs and to stimulate designer's creativity. These tests have involved six designers with a design goal defined by a semantic attribute. The results reveal that if “friendly” is diversely interpreted in terms of car shapes, “sportive” denotes a very conventional representation which may be a limitation for shape renewal.     

结合图元与感知哈希的手写输入简笔画识别

目的 为了克服手写输入中随意性强和自由度大的缺陷,同时兼顾简笔画的整体属性和局部特征,提出一种基于图元识别与感知哈希技术相结合的手写输入简笔画二级识别算法。方法 首先提取笔画的几何特征、笔序特征及结构特征且进行识别,然后查找由图元信息、笔画结构信息和笔序信息构成的简笔画语义库,完成由规则的几何图元构成的简笔画识别;若未被识别,则生成简笔画图像,利用感知哈希技术完成简笔画图像的识别。结果 基于本文提出的简笔画识别方法,实现了对样本库中150种简笔画对象的识别,平均识别率为82.6%。结论 实验结果表明,对于不同用户手写输入的任意样本库中的简笔画,该方法具有较高的识别率,此外,还可以通过在简笔画语义库和样本库中增加简笔画的种类等方式实现对更多种类简笔画的扩展识别。     

Pencil-like sketch rendering of 3D scenes using trajectory planning and dynamic tracking

Objective: We present a new non-photorealistic rendering method to render 3D scenes in the form of pencil-like sketches.Methods: This work is based on the observation that the dynamic feedback mechanism involving the human visual system and the motor control of the hand collectively generates the visual characteristics unique to hand-drawn sketches. At the heart of our approach is a trajectory planning and tracking algorithm that generate the sketch in multiple layers using a dynamic pen model. On each layer, a set of target strokes are generated from the silhouette lines, edges, and shaded regions which serve as the target trajectory for a closed-loop dynamic pen model. The pen model then produces the rendered sketch, whose characteristics can be adjusted with a set of trajectory and tracking parameters. This process continues in several layers until the tonal difference between the sketch and the original 3D render is minimized.Results: We demonstrate our approach with examples that are created by controlling the parameters of our sketch rendering algorithms.Conclusion: The examples not only show typical sketching artifacts that are common to human-drawn sketches but also demonstrate that it is capable of producing multiple sketching styles.     

The eternal sunshine of the sketch data structure

In the past years there has been significant research on developing compact data structures for summarizing large data streams. A family of such data structures is the so-called sketches. Sketches bear similarities to the well-known Bloom filters [B.H. Bloom, Space/time trade-offs in hash coding with allowable errors, Communications of ACM, 13 (7) (1970), 422–426] and employ hashing techniques to approximate the count associated with an arbitrary key in a data stream using fixed memory resources. One limitation of sketches is that when used for summarizing long data streams, they gradually saturate, resulting in a potentially large error on estimated key counts. In this work, we introduce two techniques to address this problem based on the observation that real-world data streams often have many transient keys that appear for short time periods and do not re-appear later on. After entering the data structure, these keys contribute to hashing collisions and thus reduce the estimation accuracy of sketches. Our techniques use a limited amount of additional memory to detect transient keys and to periodically remove their hashed values from the sketch. In this manner the number of keys hashed into a sketch decreases, and as a result the frequency of hashing collisions and the estimation error are reduced. Our first technique in effect slows down the saturation process of a sketch, whereas our second technique completely prevents a sketch from saturating.¹ We demonstrate the performance improvements of our techniques analytically as well as experimentally. Our evaluation results using real network traffic traces show a reduction in the collision rate ranging between 26.1% and 98.2% and even higher savings in terms of estimation accuracy compared to a state-of-the-art sketch data structure. To our knowledge this is the first work to look into the problem of improving the accuracy of sketches by mitigating their saturation process.     

Interactive sketch generation

In this paper, we propose an interactive system for generating artistic sketches from images, based on the stylized multiresolution B-spline curve model and the livewire contour tracing paradigm. Our multiresolution B-spline stroke model allows interactive and continuous control of style and shape of the stroke at any level of details. Especially, we introduce a novel mathematical paradigm called the wavelet frame to provide essential properties for multiresolution stroke editing, such as feature point preservation, locality, time-efficiency, good approximation, etc. The livewire stroke map construction leads the user-guided stroke to automatically lock on to the target contour, allowing fast and accurate sketch drawing. We classify the target contours as outlines and interior flow, and develop two respective livewire techniques based on extended graph formulation and vector flow field. Experimental results show that the proposed system facilitates quick and easy generation of artistic sketches of various styles.     

LAMPS: A sketch recognition-based teaching tool for Mandarin Phonetic Symbols I

The non-Romanized Mandarin Phonetic Symbols I (MPS1) system is a highly advantageous phonetic system for native English users studying Chinese Mandarin to learn, yet its steep initial learning curve discourages language programs to instead adopt Romanized phonetic systems. Computer-assisted language instruction (CALI) can greatly reduce this learning curve, in order to enable students to sooner benefit from the long-term advantages presented in MPS1 usage during the course of Chinese Mandarin study. Unfortunately, the technologies surrounding existing online handwriting recognition algorithms and CALI applications are insufficient in providing a “dynamic” counterpart to traditional paper-based workbooks employed in the classroom setting. In this paper, we describe our sketch recognition-based LAMPS system for teaching MPS1 by emulating the naturalness and realism of paper-based workbooks, while extending their functionality with human instructor-level critique and assessment at an automated level.     

AAM Based Face Sketch Synthesis

Face sketch synthesis has many practical applications, such as law enforcement and digital entertainment. Existing face sketch synthesis methods focus on neighbor selection and/or weight reconstruction. However, these approaches did not take “interpretation through synthesis” into consideration obviously. Active appearance model (AAM) is one of “interpretation through synthesis” approaches. In this paper, we introduce AAM to “explain” face photos by generating synthetic images that are as similar as possible. Then AAM provides a compact set of parameters that are useful for face sketch synthesis. Extensive experiments on public face sketch databases demonstrate the superiority of the proposed method in comparison to state-of-the-art methods.     

On the geodesic voronoi diagram of point sites in a simple polygon

Given a simple polygon withn sides in the plane and a set ofk point “sites” in its interior or on the boundary, compute the Voronoi diagram of the set of sites using the internal “geodesic” distance inside the polygon as the metric. We describe anO((n + k) log(n + k) logn)-time algorithm for solving this problem and sketch a fasterO((n + k) log(n + k)) algorithm for the case when the set of sites includes all reflex vertices of the polygon in question.     

Virtual indexing based methods for estimating node connection degrees

It is difficult to accurately measure node connection degrees for a high speed network, since there is a massive amount of traffic to be processed. In this paper, we present a new virtual indexing method for estimating node connection degrees for high speed links. It is based on the virtual connection degree sketch (VCDS) where a compact sketch of network traffic is built by generating multiple virtual bitmaps for each network node. Each virtual bitmap consists of a fixed number of bits selected randomly from a shared bit array by a new method for recording the traffic flows of the corresponding node. The shared bit array is efficiently utilized by all nodes since every bit is shared by the virtual bitmaps of multiple nodes. To reduce the “noise” contaminated in a node’s virtual bitmaps due to sharing, we propose a new method to generate the “filtered” bitmap used to estimate node connection degree. Furthermore, we apply VCDS to detect super nodes often associated with traffic anomalies. Since VCDS need a large amount of extra memory to store node addresses, we also propose a new data structure, the reversible virtual connection degree sketch, which identifies super node addresses analytically without the need of extra memory space but at a small increase in estimation error. Furthermore we combine the VCDS and RVCDS based methods with a uniform flow sampling technique to reduce memory complexities. Experiments are performed based on the actual network traffic and testing results show that the new methods are more memory efficient and more accurate than existing methods.