The problem of matching a forensic sketch to a gallery of mug shot images is addressed in this paper. Previous research in sketch matching only offered solutions to matching highly accurate sketches that were drawn while looking at the subject (viewed sketches). Forensic sketches differ from viewed sketches in that they are drawn by a police sketch artist using the description of the subject provided by an eyewitness. To identify forensic sketches, we present a framework called local feature-based discriminant analysis (LFDA). In LFDA, we individually represent both sketches and photos using SIFT feature descriptors and multiscale local binary patterns (MLBP). Multiple discriminant projections are then used on partitioned vectors of the feature-based representation for minimum distance matching. We apply this method to match a data set of 159 forensic sketches against a mug shot gallery containing 10,159 images. Compared to a leading commercial face recognition system, LFDA offers substantial improvements in matching forensic sketches to the corresponding face images. We were able to further improve the matching performance using race and gender information to reduce the target gallery size. Additional experiments demonstrate that the proposed framework leads to state-of-the-art accuracys when matching viewed sketches.
Vinod Goel argues that the cognitive computational conception of the world requires our thought processes to be precise, rigid, discrete, and unambiguous; yet there are dense, ambiguous, and amorphous symbol systems, like sketching, painting, and poetry, found in the arts and much of everyday discourse that have an important, nontrivial place in cognition. Much of the cognitive lies beyond articulate, discursive thought, beyond the reach of current computational notions. In Sketches of Thought, Vinod Goel argues that the cognitive computational conception of the world requires our thought processes to be precise, rigid, discrete, and unambiguous; yet there are dense, ambiguous, and amorphous symbol systems, like sketching, painting, and poetry, found in the arts and much of everyday discourse that have an important, nontrivial place in cognition. Goel maintains that while on occasion our thoughts do conform to the current computational theory of mind, they often are—indeed must be—vague, fluid, ambiguous, and amorphous. He argues that if cognitive science takes the classical computational story seriously, it must deny or ignore these processes, or at least relegate them to the realm of the nonmental. As a cognitive scientist with a design background, Goel is in a unique position to challenge cognitive science on its own territory. He introduces design problem solving as a domain of cognition that illustrates these inarticulate, nondiscursive thought processes at work through the symbol system of sketching. He argues not that such thoughts must remain noncomputational but that our current notions of computation and representation are not rich enough to capture them. Along the way, Goel makes a number of significant and controversial interim points. He shows that there is a principled distinction between design and nondesign problems, that there are standard stages in the solution of design problems, that these stages correlate with the use of different types of external symbol systems; that these symbol systems are usefully individuated in Nelson Goodman's syntactic and semantic terms, and that different cognitive processes are facilitated by different types of symbol systems. Bradford Books imprint
Methods for Approximate Query Processing (AQP) are essential for dealing with massive data. They are often the only means of providing interactive response times when exploring massive datasets, and are also needed to handle high speed data streams. These methods proceed by computing a lossy, compact synopsis of the data, and then executing the query of interest against the synopsis rather than the entire dataset. We describe basic principles and recent developments in AQP. We focus on four key synopses: random samples, histograms, wavelets, and sketches. We consider issues such as accuracy, space and time efficiency, optimality, practicality, range of applicability, error bounds on query answers, and incremental maintenance. We also discuss the tradeoffs between the different synopsis types.
暂无摘要（点击查看原文获取完整内容）
Of our spritual strivings.--Of the dawn of freedom.--Of Mr. Booker T. Washington and others.--Of the meaning of progress.--Of the wings of Atlanta.--Of the training of black men.--Of the black belt.--Of the quest of the golden fleece.--Of the sons of master and man.--Of the faith of the fathers.--Of the passing of the first-born.--Of Alexander Crummell.--Of the comimg of John.--The sorrow songs.
Abstract Topos Theory is a subject that stands at the junction of geometry, mathematical logic and theoretical computer science, and it derives much of its power from the interplay of ideas drawn from these different areas. Because of this, an account of topos theory which approaches the subject from one particular direction can only hope to give a partial picture; the aim of this compendium is to present as comprehensive an account as possible of all the main approaches and thereby to demonstrate the overall unity of the subject. The material is organized in such a way that readers interested in following a particular line of approach may do so by starting at an appropriate point in the text.
暂无摘要（点击查看原文获取完整内容）
Book digitized by Google from the library of Harvard University and uploaded to the Internet Archive by user tpb.
暂无摘要（点击查看原文获取完整内容）
Effective image retrieval by content from database requires that visual image properties are used instead of textual labels to properly index and recover pictorial data. Retrieval by shape similarity, given a user-sketched template is particularly challenging, owing to the difficulty to derive a similarity measure that closely conforms to the common perception of similarity by humans. In this paper, we present a technique which is based on elastic matching of sketched templates over the shapes in the images to evaluate similarity ranks. The degree of matching achieved and the elastic deformation energy spent by the sketch to achieve such a match are used to derive a measure of similarity between the sketch and the images in the database and to rank images to be displayed. The elastic matching is integrated with arrangements to provide scale invariance and take into account spatial relationships between objects in multi-object queries. Examples from a prototype system are expounded with considerations about the effectiveness of the approach and comparative performance analysis.
This survey highlights the recent advances in algorithms for numerical linear algebra that have come from the technique of linear sketching, whereby given a matrix, one first compresses it to a much smaller matrix by multiplying it by a (usually) random matrix with certain properties. Much of the expensive computation can then be performed on the smaller matrix, thereby accelerating the solution for the original problem. In this survey we consider least squares as well as robust regression problems, low rank approximation, and graph sparsification. We also discuss a number of variants of these problems. Finally, we discuss the limitations of sketching methods.
We present sketch-rnn, a recurrent neural network (RNN) able to construct stroke-based drawings of common objects. The model is trained on thousands of crude human-drawn images representing hundreds of classes. We outline a framework for conditional and unconditional sketch generation, and describe new robust training methods for generating coherent sketch drawings in a vector format.
Humans have used sketching to depict our visual world since prehistoric times. Even today, sketching is possibly the only rendering technique readily available to all humans. This paper is the first large scale exploration of human sketches. We analyze the distribution of non-expert sketches of everyday objects such as 'teapot' or 'car'. We ask humans to sketch objects of a given category and gather 20,000 unique sketches evenly distributed over 250 object categories. With this dataset we perform a perceptual study and find that humans can correctly identify the object category of a sketch 73% of the time. We compare human performance against computational recognition methods. We develop a bag-of-features sketch representation and use multi-class support vector machines, trained on our sketch dataset, to classify sketches. The resulting recognition method is able to identify unknown sketches with 56% accuracy (chance is 0.4%). Based on the computational model, we demonstrate an interactive sketch recognition system. We release the complete crowd-sourced dataset of sketches to the community.
Free-hand sketch-based image retrieval (SBIR) is a specific cross-view retrieval task, in which queries are abstract and ambiguous sketches while the retrieval database is formed with natural images. Work in this area mainly focuses on extracting representative and shared features for sketches and natural images. However, these can neither cope well with the geometric distortion between sketches and images nor be feasible for large-scale SBIR due to the heavy continuous-valued distance computation. In this paper, we speed up SBIR by introducing a novel binary coding method, named Deep Sketch Hashing (DSH), where a semi-heterogeneous deep architecture is proposed and incorporated into an end-to-end binary coding framework. Specifically, three convolutional neural networks are utilized to encode free-hand sketches, natural images and, especially, the auxiliary sketch-tokens which are adopted as bridges to mitigate the sketch-image geometric distortion. The learned DSH codes can effectively capture the cross-view similarities as well as the intrinsic semantic correlations between different categories. To the best of our knowledge, DSH is the first hashing work specifically designed for category-level SBIR with an end-to-end deep architecture. The proposed DSH is comprehensively evaluated on two large-scale datasets of TU-Berlin Extension and Sketchy, and the experiments consistently show DSHs superior SBIR accuracies over several state-of-the-art methods, while achieving significantly reduced retrieval time and memory footprint.
Summary A broadly applicable algorithm for computing maximum likelihood estimates from incomplete data is presented at various levels of generality. Theory showing the monotone behaviour of the likelihood and convergence of the algorithm is derived. Many examples are sketched, including missing value situations, applications to grouped, censored or truncated data, finite mixture models, variance component estimation, hyperparameter estimation, iteratively reweighted least squares and factor analysis.
Tree boosting is a highly effective and widely used machine learning method. In this paper, we describe a scalable end-to-end tree boosting system called XGBoost, which is used widely by data scientists to achieve state-of-the-art results on many machine learning challenges. We propose a novel sparsity-aware algorithm for sparse data and weighted quantile sketch for approximate tree learning. More importantly, we provide insights on cache access patterns, data compression and sharding to build a scalable tree boosting system. By combining these insights, XGBoost scales beyond billions of examples using far fewer resources than existing systems.
Sketching is a software synthesis approach where the programmer develops a partial implementation - a sketch - and a separate specification of the desired functionality. The synthesizer then completes the sketch to behave like the specification. The correctness of the synthesized implementation is guaranteed by the compiler, which allows, among other benefits, rapid development of highly tuned implementations without the fear of introducing bugs.We develop SKETCH, a language for finite programs with linguistic support for sketching. Finite programs include many highperformance kernels, including cryptocodes. In contrast to prior synthesizers, which had to be equipped with domain-specific rules, SKETCH completes sketches by means of a combinatorial search based on generalized boolean satisfiability. Consequently, our combinatorial synthesizer is complete for the class of finite programs: it is guaranteed to complete any sketch in theory, and in practice has scaled to realistic programming problems.Freed from domain rules, we can now write sketches as simpleto-understand partial programs, which are regular programs in which difficult code fragments are replaced with holes to be filled by the synthesizer. Holes may stand for index expressions, lookup tables, or bitmasks, but the programmer can easily define new kinds of holes using a single versatile synthesis operator.We have used SKETCH to synthesize an efficient implementation of the AES cipher standard. The synthesizer produces the most complex part of the implementation and runs in about an hour.
We investigate the problem of fine-grained sketch-based image retrieval (SBIR), where free-hand human sketches are used as queries to perform instance-level retrieval of images. This is an extremely challenging task because (i) visual comparisons not only need to be fine-grained but also executed cross-domain, (ii) free-hand (finger) sketches are highly abstract, making fine-grained matching harder, and most importantly (iii) annotated cross-domain sketch-photo datasets required for training are scarce, challenging many state-of-the-art machine learning techniques. In this paper, for the first time, we address all these challenges, providing a step towards the capabilities that would underpin a commercial sketch-based image retrieval application. We introduce a new database of 1,432 sketchphoto pairs from two categories with 32,000 fine-grained triplet ranking annotations. We then develop a deep tripletranking model for instance-level SBIR with a novel data augmentation and staged pre-training strategy to alleviate the issue of insufficient fine-grained training data. Extensive experiments are carried out to contribute a variety of insights into the challenges of data sufficiency and over-fitting avoidance when training deep networks for finegrained cross-domain ranking tasks.
The Sketch Engine is a leading corpus tool, widely used in lexicography. Now, at 10 years old, it is mature software. The Sketch Engine website offers many ready-to-use corpora, and tools for users to build, upload and install their own corpora. The paper describes the core functions (word sketches, concordancing, thesaurus). It outlines the different kinds of users, and the approach taken to working with many different languages. It then reviews the kinds of corpora available in the Sketch Engine, gives a brief tour of some of the innovations fromthe last few years, and surveys other corpus tools and websites.
Most face recognition systems focus on photo-based face recognition. In this paper, we present a face recognition system based on face sketches. The proposed system contains two elements: pseudo-sketch synthesis and sketch recognition. The pseudo-sketch generation method is based on local linear preserving of geometry between photo and sketch images, which is inspired by the idea of locally linear embedding. The nonlinear discriminate analysis is used to recognize the probe sketch from the synthesized pseudo-sketches. Experimental results on over 600 photo-sketch pairs show that the performance of the proposed method is encouraging.