Clustering is the unsupervised classification of patterns (observations, data items, or feature vectors) into groups (clusters). The clustering problem has been addressed in many contexts and by researchers in many disciplines; this reflects its broad appeal and usefulness as one of the steps in exploratory data analysis. However, clustering is a difficult problem combinatorially, and differences in assumptions and contexts in different communities has made the transfer of useful generic concepts and methodologies slow to occur. This paper presents an overview of pattern clustering methods from a statistical pattern recognition perspective, with a goal of providing useful advice and references to fundamental concepts accessible to the broad community of clustering practitioners. We present a taxonomy of clustering techniques, and identify cross-cutting themes and recent advances. We also describe some important applications of clustering algorithms such as image segmentation, object recognition, and information retrieval.

/pdf/data-clustering-a-review-4c452f5cab.pdf

Data clustering: a review

“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

From the Publisher: 
The accessible presentation of this book gives both a general view of the entire computer vision enterprise and also offers sufficient detail to be able to build useful applications. Users learn techniques that have proven to be useful by first-hand experience and a wide range of mathematical methods. A CD-ROM with every copy of the text contains source code for programming practice, color images, and illustrative movies. Comprehensive and up-to-date, this book includes essential topics that either reflect practical significance or are of theoretical importance. Topics are discussed in substantial and increasing depth. Application surveys describe numerous important application areas such as image based rendering and digital libraries. Many important algorithms broken down and illustrated in pseudo code. Appropriate for use by engineers as a comprehensive reference to the computer vision enterprise.

Computer vision : a modern approach = 计算机视觉 : 一种现代的方法

Handwriting has continued to persist as a means of communication and recording information in day-to-day life even with the introduction of new technologies. Given its ubiquity in human transactions, machine recognition of handwriting has practical significance, as in reading handwritten notes in a PDA, in postal addresses on envelopes, in amounts in bank checks, in handwritten fields in forms, etc. This overview describes the nature of handwritten language, how it is transduced into electronic data, and the basic concepts behind written language recognition algorithms. Both the online case (which pertains to the availability of trajectory data during writing) and the off-line case (which pertains to scanned images) are considered. Algorithms for preprocessing, character and word recognition, and performance with practical systems are indicated. Other fields of application, like signature verification, writer authentification, handwriting learning tools are also considered.

/pdf/online-and-off-line-handwriting-recognition-a-comprehensive-4qmt9ty596.pdf

Online and off-line handwriting recognition: a comprehensive survey

IEEE Transactions on Pattern Analysis and Machine Intelligence

Ultrasound (US) image despeckling is a problem of high clinical importance. Machine learning solutions to the problem are considered impractical due to the unavailability of speckle-free US image dataset. On the other hand, the classical approaches, which are able to provide the desired outputs, have limitations like input dependent parameter tuning. In this work, a convolutional neural network (CNN) is developed which learns to remove speckle from US images using the outputs of these classical approaches. It is observed that the existing approaches can be combined in a complementary manner to generate an output better than their individual outputs. Thus, the CNN is trained using the individual outputs as well as the output ensembles. It eliminates the cumbersome process of parameter tuning required by the existing approaches for every new input. Further, the proposed CNN is able to outperform the state-of-the-art despeckling approaches and produces the outputs even better than the ensembles for certain images.

Despeckling CNN with Ensembles of Classical Outputs

This paper is concerned with the development of techniques for the recognition of ornamental characters motivated by the perceptual processes involved in humans. To understand the perceptual process, we have performed the eye-tracking experiment to recognize the special set of characters, with artistic variations in character structure and form. The novelty of this paper is the use of human visual fixations to supervise the intermediate layers of the convolutional neural network. From the results obtained, we found that the network performs better when trained with the assistance of fixation information compared to the network trained without eye fixations.

Intelligent Identification of Ornamental Devanagari Characters Inspired by Visual Fixations

First, we describe how 360°-rotational symmetry may be used for three dimensional reconstruction of repeated cylinders from a single perspective image. In our experiments, we consider translational and affine repetition of cylinders with vertical and random orientations. Later, we create a virtual camera configuration for retrieving pose and location of repeated cylinders. The combination of 360°-rotational symmetry and camera center is used to identify two orthogonal planes called axis plane and orthogonal axis plane. These two planes are the basis for the proposed reconstruction framework and virtual camera configuration. Furthermore, we discuss possible extension of our method in vision tasks based on motion analysis.

/pdf/symmetry-based-3d-reconstruction-of-repeated-cylinders-cv6iz47nyf.pdf

Symmetry based 3D reconstruction of repeated cylinders

We present a framework for classification of text document images based on their script. We deal with the domain of Indian scripts which has high inter script similarities. Indian scripts have characteristic curvature distributions which help in visual discrimination of scripts. We use edge direction based features to capture the distribution of curvature. We also use a recently proposed feature selection algorithm to obtain the most discriminating curvature features. We form hierarchy (automatically) based on statistical distances between the script models. Hierarchy allows us to group similar scripts at one level and then focus on the classification between the similar scripts at the next level leading to improvement in accuracy. We show experiments and results on a large set of about 3400 images.

Curvature feature distribution based classification of Indian scripts from document images

Multi-view stereo, novel view synthesis and high dynamic range (HDR) imaging are three pertinent areas of concern for high quality 3D view generation. This paper presents a novel parameterized variety based model that integrates these different domains into one common framework with an envisioned goal, to accommodate multi-view stereo for multiple exposure input views and to render photo-realistic HDR images from arbitrary virtual viewpoints for high quality 3D reconstruction. We extend the parameterized variety approach for rendering presented earlier by Genc and Ponce [1] to handle full perspective cameras. An efficient algebraic framework is proposed to construct an explicit parameterization of the space of all multi-view multi-exposed images. This characterization of differently exposed views allow to simultaneously recover artifacts free HDR images, and reliable depth maps from arbitrary camera viewpoints. High quality, HDR textured 3D model of the scene is obtained using these images and recovered geometry information.

Santanu Chaudhury

Papers

Despeckling CNN with Ensembles of Classical Outputs

Intelligent Identification of Ornamental Devanagari Characters Inspired by Visual Fixations

Symmetry based 3D reconstruction of repeated cylinders

Curvature feature distribution based classification of Indian scripts from document images

Parameterized variety for multi-view multi-exposure image synthesis and high dynamic range stereo reconstruction