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

Recent advances in swarm inspired optimization algorithms have shown its extensive acceptance in solving a wide range of different real-world problems. Particle Swarm Optimization (PSO) is one of the most explored nature-inspired population-based stochastic optimization algorithm. In this paper, a Multi-level Particle Swarm Optimization (MPSO) algorithm is proposed to find the architecture and hyperparameters of the Convolutional Neural Network (CNN) simultaneously. This automated learning will reduce the overhead of human experts to find these parameters through manual analysis and experiments. The proposed solution uses multiple swarms at two levels. The initial swarm at level-1 optimizes architecture and multiple swarms at level-2 optimize hyperparameters. The proposed method has used sigmoid like inertia weight to adjust the exploration and exploitation property of particles and avoid the PSO algorithm to prematurely converge into a local optimum solution. In this paper, we have explored an approach to suggest the best well-conditioned CNN architecture and its hyperparameters using MPSO in a specified search space. The complexity and performance of MPSO-CNN will depend on the dimension of the search space. The experimental results on 5 benchmark datasets of MNIST, CIFAR-10, CIFAR-100, Convex Sets, and MDRBI have demonstrated one more effective application of PSO in learning a deep neural architecture.

Hybrid MPSO-CNN: Multi-level Particle Swarm optimized hyperparameters of Convolutional Neural Network

Preservation of intangible cultural heritage, such as music and dance, requires encoding of background knowledge together with digitized records of the performances. We present an ontology-based approach for designing a cultural heritage repository for that purpose. Since dance and music are recorded in multimedia format, we use Multimedia Web Ontology Language (MOWL) to encode the domain knowledge. We propose an architectural framework that includes a method to construct the ontology with a labeled set of training data and use of the ontology to automatically annotate new instances of digital heritage artifacts. The annotations enable creation of a semantic navigation environment in a cultural heritage repository. We have demonstrated the efficacy of our approach by constructing an ontology for the cultural heritage domain of Indian classical dance, and have developed a browsing application for semantic access to the heritage collection of Indian dance videos.

Nrityakosha: Preserving the intangible heritage of Indian classical dance

We propose a novel biometrics cryptosystem where one can send and receive secure information using just the fingerprints. This cryptosystem is a judicious blend of the asymmetric cryptosystem like RSA and the symmetric fuzzy vault scheme having the advantages of both the aforementioned crypto systems. We have proposed a modification of the fuzzy vault scheme to make it more robust against variations in the values of biometric features. Finally, we propose the use of invariant features as a key to producing a hierarchical security system where the same key (fingerprint) can be used to generate encrypted messages at different levels of security

Biometrics based Asymmetric Cryptosystem Design Using Modified Fuzzy Vault Scheme

This paper presents a Deep Bidirectional Long Short Term Memory (LSTM) based Recurrent Neural Network architecture for text recognition. This architecture uses Connectionist Temporal Classification (CTC) for training to learn the labels of an unsegmented sequence with unknown alignment. This work is motivated by the results of Deep Neural Networks for isolated numeral recognition and improved speech recognition using Deep BLSTM based approaches. Deep BLSTM architecture is chosen due to its ability to access long range context, learn sequence alignment and work without the need of segmented data. Due to the use of CTC and forward backward algorithms for alignment of output labels, there are no unicode re-ordering issues, thus no need of lexicon or postprocessing schemes. This is a script independent and segmentation free approach. This system has been implemented for the recognition of unsegmented words of printed Oriya text. This system achieves 4.18% character level error and 12.11% word error rate on printed Oriya text.

Text recognition using deep BLSTM networks

A video compression framework based on parametric object and background compression is proposed. At the encoder, an object is detected and frames are segmented into regions corresponding to the foreground object and the background. The encoder generates object motion and appearance parameters. The motion or warping parameters may include at least two parameters for object translation; two parameters for object scaling in two primary axes and one object orientation parameter indicating a rotation of the object. Particle filtering may be employed to generate the object motion parameters. The proposed methodology is the formalization of the concept and usability for perceptual quality scalability layer for Region(s) of Interest. A coded video sequence format is proposed which aims at “network friendly” video representation supporting appearance and generalized motion of object(s).

Santanu Chaudhury

Papers

Hybrid MPSO-CNN: Multi-level Particle Swarm optimized hyperparameters of Convolutional Neural Network

Nrityakosha: Preserving the intangible heritage of Indian classical dance

Biometrics based Asymmetric Cryptosystem Design Using Modified Fuzzy Vault Scheme

Text recognition using deep BLSTM networks

Advance video coding with perceptual quality scalability for regions of interest