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

The recovery of depth from defocus involves calculating the depth of various points in a scene by modeling the effect that the focal parameters of the camera have on images acquired with a small depth of field. We propose a method that, instead of analyzing an image region in isolation, uses a block shift-variant interactive blur model to account for the interaction among neighboring subimages. Simulation results are presented on the performance of the model.

A block shift-variant blur model for recovering depth from defocused images

This work is aimed at rendering an object described by a dense point cloud data without a pre-computed polygonal mesh and surface normal information. We use a proxy based rendering technique with proxy collocated with the HIP in free space. To avoid sinking of proxy into the object during collision a sphere of sufficiently large radius is selected as the proxy so as to avoid it going through the point cloud. Once collision is detected, we minimize a cost function depending on the current HIP and proxy positions and find a new goal position for the proxy corresponding to the local minimum of the cost function. Our rendering algorithm continuously evaluates a tangential vector for the proxy to move over the object surface during collision. The penetration depth is calculated from the proxy to the HIP and is used to calculate the reaction force for the haptic device. We used our technique to render several dense point cloud based models. We also use the surface normal evaluated at the point of contact to shade the object surface when shown visually.

Haptic rendering of dense 3D point cloud data

An algorithm is presented to obtain the total least squares (TLS) estimates of the motion parameters of an object from range/stereo data or perspective views in a closed form. TLS estimates are suitable when data in both time frames are corrupted by noise, which is an appropriate model for motion analysis in practice. The robustness of different linear least squares methods is analyzed for the estimation of motion parameters against the sensor noise and possible mismatches in establishing object feature point correspondence. As the errors in point correspondence increase, the performance of an ordinary least squares (LS) estimator was found to deteriorate much faster than that of the TLS estimator. The Cramer-Rao lower bound (CRLB) of the error covariance matrix was derived for the TLS model under the assumption of uncorrelated additive Gaussian noise. The CRLB for the TLS model is shown to be always higher than that for the LS model. >

Performance analysis of total least squares methods in three-dimensional motion estimation

Electronic noses (E-Nose) are devices used to substitute human or canine olfactory systems in detecting gases or chemical substances. The success of an E-Nose in detecting a set of target gases depends on how optimal is the choice of the gas sensors. This paper proposes a novel algorithm for selection of an optimal set of surface acoustic wave (SAW) sensors for an E-Nose from a given set of available gas sensors. The sensor performance is quantified in terms of separability of data obtained from them. A similarity measure specifying how similar the responses of sensors are when exposed to a set of gases, is also defined. The sensor selection algorithm is then specified as an optimization problem in terms of separability of target gases and similarity of sensor responses. The advantage of the proposed method lies in its performance being independent of the choice of the pattern recognition engine.

Optimal selection of SAW sensors for E-Nose applications

Weber's law suggests a logarithmic relationship between perceptual stimuli and human perception. The Weber sampler is an adaptive, nonuniform sampling mechanism that exploits Weber's law to sample the signal at a minimum rate without significant perceptual degradation. In this paper, we introduce and analyze a regularized Weber sampler for smooth deterministic signals as well as smooth random processes. While analysis for a fixed Weber constant δ is analytically intractable except for some special cases, we exploit the fact that the Weber constant is usually small. Under suitable assumptions, for deterministic signals, we provide analytical approximations to the number of samples in a unit time interval and the intersample times. For a random signal, we give analytical approximations to the expectation and probability distribution function of the respective quantities. Our class of deterministic as well as random signals is quite wide, and in particular covers bandlimited signals and signals satisfying second order ordinary differential equations. We also present a number of simulations to demonstrate that our approximations are good up to a Weber constant of 0.2, which is the regime of practical interest. Our results provide a source model for the Weber sampler, which can be used in the study of transmission of perceptual stimuli signals over communication links.

Subhasis Chaudhuri

Papers

A block shift-variant blur model for recovering depth from defocused images

Haptic rendering of dense 3D point cloud data

Performance analysis of total least squares methods in three-dimensional motion estimation

Optimal selection of SAW sensors for E-Nose applications

Analysis of an Adaptive Sampler Based on Weber's Law