There is, I think, something ethereal about i —the square root of minus one. I remember first hearing about it at school. It seemed an odd beast at that time—an intruder hovering on the edge of reality.

Usually familiarity dulls this sense of the bizarre, but in the case of i it was the reverse: over the years the sense of its surreal nature intensified. It seemed that it was impossible to write mathematics that described the real world in …

I and i

Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

Presents a review of 200 references in content-based image retrieval. The paper starts with discussing the working conditions of content-based retrieval: patterns of use, types of pictures, the role of semantics, and the sensory gap. Subsequent sections discuss computational steps for image retrieval systems. Step one of the review is image processing for retrieval sorted by color, texture, and local geometry. Features for retrieval are discussed next, sorted by: accumulative and global features, salient points, object and shape features, signs, and structural combinations thereof. Similarity of pictures and objects in pictures is reviewed for each of the feature types, in close connection to the types and means of feedback the user of the systems is capable of giving by interaction. We briefly discuss aspects of system engineering: databases, system architecture, and evaluation. In the concluding section, we present our view on: the driving force of the field, the heritage from computer vision, the influence on computer vision, the role of similarity and of interaction, the need for databases, the problem of evaluation, and the role of the semantic gap.

/pdf/content-based-image-retrieval-at-the-end-of-the-early-years-q45iy9ejai.pdf

Content-based image retrieval at the end of the early years

http://cvssp-data.eps.surrey.ac.uk/Personal/AdrianHilton/Publications_files/survey_techrep.pdf

A survey of advances in vision-based human motion capture and analysis

Extending beyond the boundaries of science, art, and culture, content-based multimedia information retrieval provides new paradigms and methods for searching through the myriad variety of media all over the world. This survey reviews 100p recent articles on content-based multimedia information retrieval and discusses their role in current research directions which include browsing and search paradigms, user studies, affective computing, learning, semantic queries, new features and media types, high performance indexing, and evaluation techniques. Based on the current state of the art, we discuss the major challenges for the future.

/pdf/content-based-multimedia-information-retrieval-state-of-the-41z647ll8w.pdf

Content-based multimedia information retrieval: State of the art and challenges

Syriac (a dialect of Aramaic) was the primary language spoken in the late ancient Middle East between the second and eighth centuries AD, and continues to be a language of Christian scholarship and liturgy up to the present day. There are approximately 20,000 known surviving Syriac manuscripts. Among early manuscripts, only around 10% include a scribal note that provides information regarding when, where, and by whom a given manuscript was written. For the remaining 90%, close examination of subtle differences in the handwritten script remains the primary tool for determining provenance. Prior to this study, scholars classified early Syriac manuscripts into two divergent script styles: Estrangela and Serto. In this paper, we present a case study of historians’ analysis of this collection of manuscripts supported by visual analytic tools. This approach uncovered major inaccuracies in this dichotomous model, resulting in profound disruption to the dominant understanding of the development of these texts.

/pdf/scalable-syriac-paleography-using-interactive-visualization-1lpm03rujc.pdf

Scalable Syriac Paleography using Interactive Visualization

Humans beings can easily make abstract judgments of similarity, but current techniques for algorithmically measuring the similarity between two images do so at a very concrete level, measuring simple statistics computed from the raw image pixels. This dissertation develops and evaluates an evolvable framework for computing image similarity that moves toward more abstract forms of similarity, particularly by allowing the comparison of images based only upon certain significant portions. We begin by formulating and stating the area-matching assumption for concrete visual similarity: Two images are likely to be similar to the extent that they comprise equally matched areas of visually similar materials. We develop an infrastructure to test and explore this approach, and extend it to applications such as classification, image retrieval, and object retrieval. The infrastructure extends from early phases of image processing and analysis, through to multiple-image comparisons and frameworks for applying sophisticated learning algorithms. Throughout we apply the best available tests to evaluate the new techniques and compare them to existing methods. 
We begin with basic image processing tools that contribute to successful image comparisons. A multi-tiered model-based segmentation algorithm identifies regions of uniform visual properties. The models used in the segmentation also lead to precise measurements of region properties such as texture and color. A flexible vector representation system forms the core of the image comparison infrastructure, recording in a uniform framework the characteristic feature co-occurrences identified within the image. Combined with a smoothing mechanism that allows closely related but non-identical feature matches to be recorded and scored, this representation forms the basis of a new similarity metric on images. We compare this similarity metric to other techniques on multiple tests, and find that in many circumstances, although not all, it performs on par with or better than existing methods. 
Further variations on the original metric allow searches that match only the significant portions of images, as defined by a user's query. These extensions require no additional stored data structures, and compare well with existing methods. One variation proves at least as powerful as any of the other current algorithms implemented for comparison. 
Finally, we look farther afield and draw connections between this work and the field of machine learning. First we show that the infrastructure developed here has broad applicability to other machine learning problems. Conversely, we also demonstrate that a popular machine learning approach (boosting) can significantly improve the performance of our image infrastructure on a large-scale classification task.

/pdf/analysis-and-representations-for-automatic-comparison-cdhzq6glqy.pdf

Analysis and representations for automatic comparison, classification and retrieval of digital images

Libraries are digitizing their collections of maps from all eras, generating increasingly large online collections of historical cartographic resources. Aligning such maps to a modern geographic coordinate system greatly increases their utility. This work presents a method for such automatic georeferencing, matching raster image content to GIS vector coordinate data. Given an approximate initial alignment that has already been projected from a spherical geographic coordinate system to a Cartesian map coordinate system, a probabilistic shape-matching scheme determines an optimized match between the GIS contours and ink in the binarized map image. Using an evaluation set of 20 historical maps from states and regions of the U.S., the method reduces average alignment RMSE by 12%.

/pdf/details-of-deformable-part-models-for-automatically-2t7ws1eczb.pdf

Details of Deformable Part Models for Automatically Georeferencing Historical Map Images

This paper describes a set of hand-isolated character samples selected from securely dated manuscripts written in Syriac between 300 and 1300 C.E., which are being made available for research purposes. The collection can be used for a number of applications, including ground truth for character segmentation and form analysis for paleographical dating. Several applications based upon convolutional neural networks demonstrate the possibilities of the data set.

/pdf/isolated-character-forms-from-dated-syriac-manuscripts-5f2xt4ah54.pdf

Isolated Character Forms from Dated Syriac Manuscripts

Inkball models provide a tool for matching and comparison of spatially structured markings such as handwritten characters and words. Hidden Markov models offer a framework for decoding a stream of text in terms of the most likely sequence of causal states. Prior work with HMM has relied on observation of features that are correlated with underlying characters, without modeling them directly. This paper proposes to use the results of inkball-based character matching as a feature set input directly to the HMM. Experiments indicate that this technique outperforms other tested methods at handwritten word recognition on a common benchmark when applied without normalization or text deslanting.

/pdf/inkball-models-as-features-for-handwriting-recognition-2z4jy6pwxb.pdf

Nicholas R. Howe

Papers

Scalable Syriac Paleography using Interactive Visualization

Analysis and representations for automatic comparison, classification and retrieval of digital images

Details of Deformable Part Models for Automatically Georeferencing Historical Map Images

Isolated Character Forms from Dated Syriac Manuscripts

Inkball Models as Features for Handwriting Recognition