Scale-dependent and example-based grayscale stippling

We present an example-based approach to synthesizing stipple illustrations for static 2D images that produces scale-dependent results appropriate for an intended spatial output size and resolution. We show how treating stippling as a grayscale process allows us to both produce on-screen output and to achieve stipple merging at medium tonal ranges. At the same time we can also produce images with high spatial and low color resolution for print reproduction. In addition, we discuss how to incorporate high-level illustration considerations into the stippling process based on discussions with and observations of a stipple artist. Also, certain features such as edges can be extracted and used to control the placement of dots to improve the result. The implementation of the technique is based on a fast method for distributing dots using halftoning and can be used to create stipple images interactively. We describe both a GPU implementation of the basic algorithm that creates stipple images in real-time for large images and an extended CPU method that allows a finer control of the output at interactive rates.     

EXTRA: a system for example-based translation assistance

In this paper we present EXTRA (EXample-based TRanslation Assistant), a translation memory (TM) system. EXTRA is able to propose effective translation suggestions by relying on syntactic analysis of the text and on a rigorous, language-independent measure; the search is performed efficiently in large amounts of bilingual texts thanks to its advanced retrieval techniques. EXTRA does not use external knowledge requiring the intervention of users and is completely customizable and portable as it has been implemented on top of a standard DataBase Management System. The paper provides a thorough evaluation of both the effectiveness and the efficiency of our system. In particular, in order to quantify the benefits offered by EXTRA assisted translation over manual translation, we introduce a simulator implementing specifically devised statistical, process-oriented, discrete-event models. As far as we know, this is the first time statistical simulation experiments have been used to face the nontrivial problem of evaluating TM systems, particularly for comparing the time that could be saved by performing assisted translation versus “manual” translation and for optimally tuning the system behaviour with respect to differently skilled users. In our experiments, we considered three scenarios, manual translation with one or two translators and assisted translation with one translator. The time needed for one translator to do an assisted translation is significantly closer to that of a team of two translators than to that of the single translator. The mean sentence translation time is by far the lowest for this scenario, corresponding to the highest per translator productivity. We also estimate the total translation time when the number of query sentences, the maximum number of suggestions to be read, and the probability of look up are varied: the best trade-off is given by reading (and presenting) four or five suggestions at the most.     

Fast example-based surface texture synthesis via discrete optimization

We synthesize and animate general texture patterns over arbitrary 3D mesh surfaces. The animation is controlled by flow fields over the target mesh, and the texture can be arbitrary user input as long it satisfies the Markov-Random-Field assumptions. We achieve this by extending the texture optimization framework over 3D mesh surfaces. We propose an efficient discrete solver inspired by k-coherence search, allowing interactive flow texture animation while avoiding the blurry blending problem for the least square solver in previous work. Our technique has potential applications ranging from simulation, visualization, and special effects.     

Computer-supported example-based learning: When instructional explanations reduce self-explanations

We investigated whether the findings from worked-out example research on the effects of self-explanation prompts and on instructional explanations can be generalized to other example types – in this case: solved example problems. Whereas worked-out examples consist of a problem formulation, solution steps, and the final solution, solved example problems merely provide the problem formulation and the solution. We employed a first module of a computer-based environment for student teachers presenting solved example problems from which they learned how to select and to design worked-out examples for high school students. The participants (47 student teachers for German low- and medium-track schools and 33 student teachers for high-track schools) were randomly assigned to the cells of our 2 × 2 design (with vs. without self-explanation prompts; with vs. without instructional explanations). The effects of the different program versions on objective and subjective learning outcomes, on the perceived helpfulness of the program, and on the learning time were analyzed. As learning process data, the written and spoken self-explanations were assessed. The following main results were obtained: Particularly self-explanation prompts had favorable effects on learning outcomes, whereas instructional explanations can reduce the student teacher’s self-explanation activities and thereby the learning outcomes. Whereas “objectively” the most favorable learning outcomes were obtained when only self-explanation prompts were employed, the student teachers perceived their learning outcome best when only instructional explanations were provided. It can be concluded that the status of self-explanation prompts and of instructional explanations is comparable irrespective of the example type presented for learning.     

Evaluating multimedia features and fusion for example-based event detection

Multimedia event detection (MED) is a challenging problem because of the heterogeneous content and variable quality found in large collections of Internet videos. To study the value of multimedia features and fusion for representing and learning events from a set of example video clips, we created SESAME, a system for video SEarch with Speed and Accuracy for Multimedia Events. SESAME includes multiple bag-of-words event classifiers based on single data types: low-level visual, motion, and audio features; high-level semantic visual concepts; and automatic speech recognition. Event detection performance was evaluated for each event classifier. The performance of low-level visual and motion features was improved by the use of difference coding. The accuracy of the visual concepts was nearly as strong as that of the low-level visual features. Experiments with a number of fusion methods for combining the event detection scores from these classifiers revealed that simple fusion methods, such as arithmetic mean, perform as well as or better than other, more complex fusion methods. SESAME’s performance in the 2012 TRECVID MED evaluation was one of the best reported.     

Robust 3D face capture using example-based photometric stereo

We show that using example-based photometric stereo, it is possible to achieve realistic reconstructions of the human face. The method can handle non-Lambertian reflectance and attached shadows after a simple calibration step. We use spherical harmonics to model and de-noise the illumination functions from images of a reference object with known shape, and a fast grid technique to invert those functions and recover the surface normal for each point of the target object. The depth coordinate is obtained by weighted multi-scale integration of these normals, using an integration weight mask obtained automatically from the images themselves. We have applied these techniques to improve the PhotoFace system of Hansen et al. (2010).     

Purest ever example-based machine translation: Detailed presentation and assessment

We have designed, implemented and assessed an EBMT system that can be dubbed the “purest ever built”: it strictly does not make any use of variables, templates or patterns, does not have any explicit transfer component, and does not require any preprocessing or training of the aligned examples. It uses only a specific operation, proportional analogy, that implicitly neutralizes divergences between languages and captures lexical and syntactic variations along the paradigmatic and syntagmatic axes without explicitly decomposing sentences into fragments. Exactly the same genuine implementation of such a core engine was evaluated on different tasks and language pairs. To begin with, we compared our system on two tasks of a previous MT evaluation campaign to rank it among other current state-of-the-art systems. Then, we illustrated the “universality” of our system by participating in a recent MT evaluation campaign, with exactly the same core engine, for a wide variety of language pairs. Finally, we studied the influence of extra data like dictionaries and paraphrases on the system performance.     

Efficient example-based painting and synthesis of 2D directional texture

We present a new method for converting a photo or image to a synthesized painting following the painting style of an example painting. Treating painting styles of brush strokes as sample textures, we reduce the problem of learning an example painting to a texture synthesis problem. The proposed method uses a hierarchical patch-based approach to the synthesis of directional textures. The key features of our method are: 1) Painting styles are represented as one or more blocks of sample textures selected by the user from the example painting; 2) image segmentation and brush stroke directions defined by the medial axis are used to better represent and communicate shapes and objects present in the synthesized painting; 3) image masks and a hierarchy of texture patches are used to efficiently synthesize high-quality directional textures. The synthesis process is further accelerated through texture direction quantization and the use of Gaussian pyramids. Our method has the following advantages: First, the synthesized stroke textures can follow a direction field determined by the shapes of regions to be painted. Second, the method is very efficient; the generation time of a synthesized painting ranges from a few seconds to about one minute, rather than hours, as required by other existing methods, on a commodity PC. Furthermore, the technique presented here provides a new and efficient solution to the problem of synthesizing a 2D directional texture. We use a number of test examples to demonstrate the efficiency of the proposed method and the high quality of results produced by the method.     

UHD TV image enhancement using example-based spatially adaptive image restoration filter

This paper presents a novel image restoration algorithm using examples and truncated constrained least squares (TCLS) filter for ultra-high definition (UHD) television systems. The proposed approach consists of three steps: (i) generation of the patch dictionary using multiple-step image blurring, (ii) selection of the optimum patch based on the orientation and the amount of blurring, and (iii) combination of the selected patch in the dictionary and its filtered version by the TCLS restoration filter for reducing the patch mismatch error. In the proposed algorithm, a complicated point-spread-function (PSF) estimation process is replaced with the generation of multiple, differently blurred patches. Furthermore, the patch dictionary is made by orientation-based classification to reduce the time to search the optimum patch. Experimental results show that the proposed algorithm can restore more natural images with less synthetic artifacts than existing methods. The proposed method provides a significantly improved restoration performance over existing methods in the sense of both subjective and objective measures including peak-to-peak signal-to-noise ratio (PSNR) and structural similarity measure (SSIM).     

MT model space: statistical versus compositional versus example-based machine translation

We offer a perspective on EBMT from a statistical MT standpoint, by developing a three-dimensional MT model space based on three pairs of definitions: (1) logical versus statistical MT, (2) schema-based versus example-based MT, and (3) lexical versus compositional MT. Within this space we consider the interplay of three key ideas in the evolution of transfer, example-based, and statistical approaches to MT. We depict how all translation models face these issues in one way or another, regardless of the school of thought, and suggest where the real questions for the future may lie.     

Dependency treelet translation: the convergence of statistical and example-based machine-translation?

We describe a novel approach to MT that combines the strengths of the two leading corpus-based approaches: Phrasal SMT and EBMT. We use a syntactically informed decoder and reordering model based on the source dependency tree, in combination with conventional SMT models to incorporate the power of phrasal SMT with the linguistic generality available in a parser. We show that this approach significantly outperforms a leading string-based Phrasal SMT decoder and an EBMT system. We present results from two radically different language pairs, and investigate the sensitivity of this approach to parse quality by using two distinct parsers and oracle experiments. We also validate our automated bleu scores with a small human evaluation.     

Calculation of co-ordinates for optimal hatching

The paper discusses details of a structured program which calculates co-ordinate values for optimal hatching of planar shapes. The problem arises when there is a need for NC control of light spot plotters in manufacturing linear circuit printing.     

Interactive documentation

Documents are increasingly often read from computer screens rather than from paper. This paper describes a tool, called GUIDE, which allows readers of computer-based documents to peruse these documents at any desired level of detail. GUIDE covers any kind of textual document, and is designed for environments where both author and readers are lay users.     

Interactive networking

The Primenet software supports communication via local ring networks, point-to-point synchronous networks, and X.25 packet-switched networks. The paper outlines use of the networking software and its software modules — the interprogram communication facility, interactive terminal support facility and the file access manager. The manufacturer's own data-communications network, which links its installations in the USA, Canada and the UK, is described.