Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

http://library.utia.cas.cz/prace/20030125.pdf

Image registration methods: a survey

Humans perceive the three-dimensional structure of the world with apparent ease. However, despite all of the recent advances in computer vision research, the dream of having a computer interpret an image at the same level as a two-year old remains elusive. Why is computer vision such a challenging problem and what is the current state of the art? Computer Vision: Algorithms and Applications explores the variety of techniques commonly used to analyze and interpret images. It also describes challenging real-world applications where vision is being successfully used, both for specialized applications such as medical imaging, and for fun, consumer-level tasks such as image editing and stitching, which students can apply to their own personal photos and videos. More than just a source of recipes, this exceptionally authoritative and comprehensive textbook/reference also takes a scientific approach to basic vision problems, formulating physical models of the imaging process before inverting them to produce descriptions of a scene. These problems are also analyzed using statistical models and solved using rigorous engineering techniques Topics and features: structured to support active curricula and project-oriented courses, with tips in the Introduction for using the book in a variety of customized courses; presents exercises at the end of each chapter with a heavy emphasis on testing algorithms and containing numerous suggestions for small mid-term projects; provides additional material and more detailed mathematical topics in the Appendices, which cover linear algebra, numerical techniques, and Bayesian estimation theory; suggests additional reading at the end of each chapter, including the latest research in each sub-field, in addition to a full Bibliography at the end of the book; supplies supplementary course material for students at the associated website, http://szeliski.org/Book/. Suitable for an upper-level undergraduate or graduate-level course in computer science or engineering, this textbook focuses on basic techniques that work under real-world conditions and encourages students to push their creative boundaries. Its design and exposition also make it eminently suitable as a unique reference to the fundamental techniques and current research literature in computer vision.

/pdf/computer-vision-algorithms-and-applications-25dn6wu83j.pdf

Computer Vision: Algorithms and Applications

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

Images containing faces are essential to intelligent vision-based human-computer interaction, and research efforts in face processing include face recognition, face tracking, pose estimation and expression recognition. However, many reported methods assume that the faces in an image or an image sequence have been identified and localized. To build fully automated systems that analyze the information contained in face images, robust and efficient face detection algorithms are required. Given a single image, the goal of face detection is to identify all image regions which contain a face, regardless of its 3D position, orientation and lighting conditions. Such a problem is challenging because faces are non-rigid and have a high degree of variability in size, shape, color and texture. Numerous techniques have been developed to detect faces in a single image, and the purpose of this paper is to categorize and evaluate these algorithms. We also discuss relevant issues such as data collection, evaluation metrics and benchmarking. After analyzing these algorithms and identifying their limitations, we conclude with several promising directions for future research.

/pdf/detecting-faces-in-images-a-survey-4yhbbns6mr.pdf

Detecting faces in images: a survey

We propose a simple technique for content-based image retrieval (CBIR) using contourlets that possess not only the multi-resolution time frequency localization properties of wavelets but are also good at capturing the directional information. Statistical features extracted from contourlet coefficients on each subband of the decomposed image, capturing the textural properties, are combined with the color feature while doing the CBIR. The retrieval performance on a large image database shows that the proposed technique provides a better accuracy compared to other multi-resolution based approaches.

/pdf/use-of-contourlets-for-image-retrieval-5fi0qsv612.pdf

Use of contourlets for image retrieval

The image retrieval problem in the presence of possible foreground disturbances is considered. The foreground may be irrelevant for the retrieval purposes but it occludes the background and hence reduces the retrieval accuracy. The accrued inaccuracy is quantified in terms of cardinality of the occluding region. The use of the sprite generated from a video clip is proposed as a query, so that the effect of moving foreground can be eliminated. The segmented foreground region is filled in by constructing the background sprite to increase the retrieval accuracy. The performance of a retrieval scheme under foreground disturbance is presented here.

Content-based image retrieval in presence of foreground disturbances

Image co-segmentation is jointly segmenting two or more images sharing common foreground objects. In this paper, we propose a novel graph convolution neural network (graph CNN) based end-to-end model for performing co-segmentation. At the beginning, each input image is over-segmented into a set of superpixels. Next, a weighted graph is formed using the over-segmented images exploiting spatial adjacency and both intra-image and inter-image feature similarities among the image superpixels (nodes). Subsequently, the proposed network, consisting of graph convolution layers followed by node classification layers, classifies each superpixel either into the common foreground or its complement. During training, along with the co-segmentation network, an additional network is introduced to exploit the corresponding semantic labels, and the two networks share the same weights in graph convolution layers. The whole model is learned in an end-to-end fashion using a novel cost function comprised of a superpixel wise binary cross entropy and a multi-label cross entropy. We also use empirical class probabilities in the loss function to deal with class imbalance. Experimental results reflect that the proposed technique is very competitive with the state-of-the-art methods on two challenging datasets, Internet and Pascal-VOC.

Image Co-segmentation using Graph Convolution Neural Network

In 1887, Augustus D. Waller published the _rst human electrocardiogram (ECG) recorded with a capillary electrometer. Subsequently, Willem Einthoven invented a more sensitive galvanometer for producing ECG using a _ne quartz string coated in silver. He invented the lead system for ECG recording and identi_ed the _ve deection points in the cardiac cycle by naming them P, Q, R, S and T which are still being used in the present standards (see Fig. 1.2). Einthoven also started transmission of ECG from hospital to his laboratory on telephone lines [33]. Since then a huge knowledge base has been generated covering clinical and engineering aspects of electrocardiography. Since last few decades electronic recorders have been developed for digital recording of the ECG signal. In recent years the ECG recorders are available in a much compact form so that the user can wear it for ECG recording without much of obstruction in the routine activities. Recently, the wearable ECG recorders (W-ECG) are becoming very popular because of their low cost, long term recording capability and ease of use.

Review of ECG Analysis

Analysis of human interaction in a social gathering is of high interest in security and surveillance applications. It is also of psychological interest to study the interaction to get a better understanding of the participant behavior. This paper is an attempt to explore and analyze interactions among the individuals from a single calibrated camera. We are particularly interested in trajectory prediction. These predicted trajectories of individuals are then used in predicting personal space violation. Each individual, represented by a feature point in a 2.5D coordinate system, is tracked using Lucas-Kanade tracking algorithm. We use the linear cyclic pursuit framework to model this point motion. This model is used for short-term prediction of individual trajectory. We demonstrate these ideas on different types of datasets.

Subhasis Chaudhuri

Papers

Use of contourlets for image retrieval

Content-based image retrieval in presence of foreground disturbances

Image Co-segmentation using Graph Convolution Neural Network

Review of ECG Analysis

Linear cyclic pursuit based prediction of personal space violation in surveillance video