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

In the literature on psychophysics, it is reported that during a psychophysical experiment when a user is subjected to many trials in succession, the perception of the current trial is observed to be overly similar to the previous trial (assimilation effect), and is observed to be dissimilar to distantly past trials (contrast effect). Overall, this behavior is called the sequential effect and is a very well-established phenomenon in psychophysics. In the literature, the sequential effect has been demonstrated on loudness of sound, and has been further assumed for other perceptual modalities like haptics and vision. However, to the best of our knowledge, we have not found any experimental study either claiming its existence for kinesthetic perception or for quantifying the effect. This motivates us to study the sequential effect on kinesthetic perception. In this chapter, we take up this study and find out whether or not the sequential effect exists, and how to quantify the effect. In order to study the presence of sequential effect for kinesthetic perception, we design an experimental setup where a user is subjected to a series of random force stimuli. We record the responses for several users. Thereafter, a logistic regression model is employed to observe how much the recorded responses are affected by the past stimuli. Based on the results of the logistic regression model, we demonstrate the presence of sequential effect for the kinesthetic stimuli. We also explain how to quantify the duration over which the sequential effect persists.

Sequential Effect on Kinesthetic Perception

We present an unsupervised approach to analyze crowd at various levels of granularity $-$ individual, group and collective. We also propose a motion model to represent the collective motion of the crowd. The model captures the spatio-temporal interaction pattern of the crowd from the trajectory data captured over a time period. Furthermore, we also propose an effective group detection algorithm that utilizes the eigenvectors of the interaction matrix of the model. We also show that the eigenvalues of the interaction matrix characterize various group activities such as being stationary, walking, splitting and approaching. The algorithm is also extended trivially to recognize individual activity. Finally, we discover the overall crowd behavior by classifying a crowd video in one of the eight categories. Since the crowd behavior is determined by its constituent groups, we demonstrate the usefulness of group level features during classification. Extensive experimentation on various datasets demonstrates a superlative performance of our algorithms over the state-of-the-art methods.

Spatio-temporal interaction model for crowd video analysis.

Haptic rendering of a point cloud data without a precomputed mesh structure is always a difficult problem. This paper tries to solve the problem of real time rendering a variable density 3D point cloud data as an optimization problem with a local kernel bandwidth estimation. In order to avoid the ambiguity of deciding the direction of reaction force while rendering the data we prefer a proxy based renderer. To avoid the proxy sinking into the object during collision the proxy point is always kept at minimum distance away from the object surface approximated by the point cloud. This minimum distance is computed during the rendering process depending on the local density of the points in the data using the kernel bandwidth estimation. Once collision is detected, we minimize a cost function depending on the current haptic interaction point (HIP) and proxy positions and find a new goal position for the proxy corresponding to the local minimum of the cost function. We validate the proposed technique by comparing the rendered force with the reaction force computed using a known spherical object.

Haptic rendering of variable density point cloud through local kernel bandwidth estimation

In this paper we attempt to solve the problem of synthesizing a novel view corresponding to a virtual camera given the scene description in the form of images captured from other view points We project each line of sight emerging from the virtual camera on each of the given views, align them geometrically and assign a color that is photo consistent as per the radiance model This being ill-conditioned, a smooth variation of depth in the scene is utilized as the regularizing constraint It leads to development of an algorithm which is computationally fast and generates visually realistic images with negligible artifacts even with a limited number of input views The proposed approach puts no restriction on the view points from which the input images are captured

Novel view synthesis using locally adaptive depth regularization

In this paper, we present a novel proxy-based method of the adaptive haptic rendering of a variable density 3D point cloud data at different levels of detail without pre-computing the mesh structure. We also incorporate features like rotation, translation, and friction to provide a better realistic experience to the user. A proxy-based rendering technique is used to avoid the pop-through problem while rendering thin parts of the object. Instead of a point proxy, a spherical proxy of a variable radius is used, which avoids the sinking of proxy during the haptic interaction of sparse data. The radius of the proxy is adaptively varied depending upon the local density of the point data using kernel bandwidth estimation. During the interaction, the proxy moves in small steps tangentially over the point cloud such that the new position always minimizes the distance between the proxy and the haptic interaction point (HIP). The raw point cloud data re-sampled in a regular 3D lattice of voxels are loaded to the haptic space after proper smoothing to avoid aliasing effects. The rendering technique is validated with several subjects, and it is observed that this functionality supplements the user's experience by allowing the user to interact with an object at multiple resolutions.

Subhasis Chaudhuri

Papers

Sequential Effect on Kinesthetic Perception

Spatio-temporal interaction model for crowd video analysis.

Haptic rendering of variable density point cloud through local kernel bandwidth estimation

Novel view synthesis using locally adaptive depth regularization

Scalable Rendering of Variable Density Point Cloud Data.