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

A fast-Fourier-transform method of topography and interferometry is proposed. By computer processing of a noncontour type of fringe pattern, automatic discrimination is achieved between elevation and depression of the object or wave-front form, which has not been possible by the fringe-contour-generation techniques. The method has advantages over moire topography and conventional fringe-contour interferometry in both accuracy and sensitivity. Unlike fringe-scanning techniques, the method is easy to apply because it uses no moving components.

Fourier-transform method of fringe-pattern analysis for computer-based topography and interferometry

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

Measurement of visual quality is of fundamental importance to numerous image and video processing applications. The goal of quality assessment (QA) research is to design algorithms that can automatically assess the quality of images or videos in a perceptually consistent manner. Image QA algorithms generally interpret image quality as fidelity or similarity with a "reference" or "perfect" image in some perceptual space. Such "full-reference" QA methods attempt to achieve consistency in quality prediction by modeling salient physiological and psychovisual features of the human visual system (HVS), or by signal fidelity measures. In this paper, we approach the image QA problem as an information fidelity problem. Specifically, we propose to quantify the loss of image information to the distortion process and explore the relationship between image information and visual quality. QA systems are invariably involved with judging the visual quality of "natural" images and videos that are meant for "human consumption." Researchers have developed sophisticated models to capture the statistics of such natural signals. Using these models, we previously presented an information fidelity criterion for image QA that related image quality with the amount of information shared between a reference and a distorted image. In this paper, we propose an image information measure that quantifies the information that is present in the reference image and how much of this reference information can be extracted from the distorted image. Combining these two quantities, we propose a visual information fidelity measure for image QA. We validate the performance of our algorithm with an extensive subjective study involving 779 images and show that our method outperforms recent state-of-the-art image QA algorithms by a sizeable margin in our simulations. The code and the data from the subjective study are available at the LIVE website.

Image information and visual quality

The objective of this paper is to give a comprehensive introduction to applied cryptography with an engineer or computer scientist in mind. The emphasis is on the knowledge needed to create practical systems which supports integrity, confidentiality, or authenticity. Topics covered includes an introduction to the concepts in cryptography, attacks against cryptographic systems, key use and handling, random bit generation, encryption modes, and message authentication codes. Recommendations on algorithms and further reading is given in the end of the paper. This paper should make the reader able to build, understand and evaluate system descriptions and designs based on the cryptographic components described in the paper.

[서평]「Applied Cryptography」

Over the past two decades, there have been various studies on the distributions of the DCT coefficients for images. However, they have concentrated only on fitting the empirical data from some standard pictures with a variety of well-known statistical distributions, and then comparing their goodness of fit. The Laplacian distribution is the dominant choice balancing simplicity of the model and fidelity to the empirical data. Yet, to the best of our knowledge, there has been no mathematical justification as to what gives rise to this distribution. We offer a rigorous mathematical analysis using a doubly stochastic model of the images, which not only provides the theoretical explanations necessary, but also leads to insights about various other observations from the literature. This model also allows us to investigate how certain changes in the image statistics could affect the DCT coefficient distributions.

A mathematical analysis of the DCT coefficient distributions for images

Super-resolution (SR) reconstruction technique is capable of producing a high-resolution image from a sequence of low-resolution images. In this paper, we study an efficient SR algorithm for digital video. To effectively deal with the intractable problems in SR video reconstruction, such as inevitable motion estimation errors, noise, blurring, missing regions, and compression artifacts, the total variation (TV) regularization is employed in the reconstruction model. We use the fixed-point iteration method and preconditioning techniques to efficiently solve the associated nonlinear Euler-Lagrange equations of the corresponding variational problem in SR. The proposed algorithm has been tested in several cases of motion and degradation. It is also compared with the Laplacian regularization-based SR algorithm and other TV-based SR algorithms. Experimental results are presented to illustrate the effectiveness of the proposed algorithm.

/pdf/a-total-variation-regularization-based-super-resolution-5er3fv1bwp.pdf

A Total Variation Regularization Based Super-Resolution Reconstruction Algorithm for Digital Video

In digital holography, it is crucial to extract the object distance from a hologram in order to reconstruct its amplitude and phase. This is known as autofocusing, which is conventionally solved by first reconstructing a stack of images, and then the sharpness of each reconstructed image is computed using a focus metric such as entropy or variance. The distance corresponding to the sharpest image is considered the focal position. This approach, while effective, is computationally demanding and time-consuming. To cope with this problem, we turn to machine learning, where we cast the autofocusing as a regression problem, with the focal distance being a continuous response corresponding to each hologram. Therefore, distance estimation is converted to hologram prediction, which we solve by designing a powerful convolutional neural network trained by a set of holograms acquired a priori. Experimental results show that this allows fast autofocusing without reconstructing an image stack, even when the physical parameters of the optical setup are unknown.

Learning-based nonparametric autofocusing for digital holography

Source camera identification is the process of discerning which camera has been used to capture a particular image. In this paper, we consider the more fundamental problem of trying to classify images captured by a limited number of camera models. Inspired by the previous work that uses sensor imperfection, we propose to use the intrinsic lens aberration as features in the classification. In particular, we focus on lens radial distortion as the primary distinctive feature. For each image under investigation, parameters from pixel intensities and aberration measurements are obtained. We then employ a classifier to identify the source camera of an image. Simulation is carried out to evaluate the success rate of our method. The results show that this is a viable procedure in source camera identification with a high probability of accuracy. Comparing with the procedures using only image intensities, our approach improves the accuracy from 87% to 91%.

Source camera identification using footprints from lens aberration

The practicability and methodology of applying regularly placed contacts on layout design of standard cells are studied. The regular placement enables more effective use of resolution enhancement technologies, which in turn allows for a reduction of critical dimensions. Although placing contacts on a grid adds restrictions during cell layout, overall circuit area can be made smaller by a careful selection of the grid pitch, allowing slight contact offset, applying double exposure, and shrinking the minimum size and pitch. The contact level of 250 nm standard cells was shrunk by 10%, resulting in an area change ranging from -20% to +25% with an average decrease of 5% for the 84 cells studied. The areas of two circuits, a finite-impulse-response (FIR) filter and an add-compare-select (ACS) unit in the Viterbi decoder, decrease by 4% and 2%, respectively.

/pdf/standard-cell-layout-with-regular-contact-placement-3fmgkq0jp0.pdf

Edmund Y. Lam

Papers

A mathematical analysis of the DCT coefficient distributions for images

A Total Variation Regularization Based Super-Resolution Reconstruction Algorithm for Digital Video

Learning-based nonparametric autofocusing for digital holography

Source camera identification using footprints from lens aberration

Standard cell layout with regular contact placement