Objective methods for assessing perceptual image quality traditionally attempted to quantify the visibility of errors (differences) between a distorted image and a reference image using a variety of known properties of the human visual system. Under the assumption that human visual perception is highly adapted for extracting structural information from a scene, we introduce an alternative complementary framework for quality assessment based on the degradation of structural information. As a specific example of this concept, we develop a structural similarity index and demonstrate its promise through a set of intuitive examples, as well as comparison to both subjective ratings and state-of-the-art objective methods on a database of images compressed with JPEG and JPEG2000. A MATLAB implementation of the proposed algorithm is available online at http://www.cns.nyu.edu//spl sim/lcv/ssim/.

/pdf/image-quality-assessment-from-error-visibility-to-structural-1rlwcqe34t.pdf

Image quality assessment: from error visibility to structural similarity

다중혈관 관상동맥 환자에서 y-문합을 이용하여 양쪽 내흉동맥만을 사용한 우회술의 조기 성적

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 general non-parametric technique is proposed for the analysis of a complex multimodal feature space and to delineate arbitrarily shaped clusters in it. The basic computational module of the technique is an old pattern recognition procedure: the mean shift. For discrete data, we prove the convergence of a recursive mean shift procedure to the nearest stationary point of the underlying density function and, thus, its utility in detecting the modes of the density. The relation of the mean shift procedure to the Nadaraya-Watson estimator from kernel regression and the robust M-estimators; of location is also established. Algorithms for two low-level vision tasks discontinuity-preserving smoothing and image segmentation - are described as applications. In these algorithms, the only user-set parameter is the resolution of the analysis, and either gray-level or color images are accepted as input. Extensive experimental results illustrate their excellent performance.

Mean shift: a robust approach toward feature space analysis

Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

Information and communication technologies (ICT) have become more mature after its development for more than half a century. We are in a new era in which ICT research has shifted its focus from technology development to novel applications. For example, digital technologies have been widely applied to speech, audio, video and graphics in various commercial applications today. Furthermore, the availability of the broadband wired/wireless Internet infrastructure and the cloud computing facilities has changed the way of web-based services. This lecture will address the following four major paradigm shifts in this modern IT era: • From the analog implementation to the digital implementation • From PC-centric to cloud/network-centric • From one-way broadcasting to two-way interaction • From HW/SW/infra-structure provision to contents and value-added services

Paradigm shifts in modern ICT era and future trends

A new color feature obtained from the pruned octree color representation of an image for interactive image retrieval is proposed in this work. The pruned octree is constructed based on a natural color clustering of a given image rather than the fixed bucket color quantization of the entire database. In this new framework, we integrate commonly used features such as color width, color depth, average colore and multi-resolution colore distributions. As a result, it supports flexible filtering, in which the similarity matching procedure can be gradually refined. Examples are given to illustrate the query image analysis and sequential filtering strategy based on the octree color feature.© (1997) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.

Pruned octree feature for interactive retrieval

Supervised and unsupervised deep trackers that rely on deep learning technologies are popular in recent years. Yet, they demand high computational complexity and a high memory cost. A green unsupervised single-object tracker, called GUSOT, that aims at object tracking for long videos under a resource-constrained environment is proposed in this work. Built upon a baseline tracker, UHP-SOT++, which works well for short-term tracking, GUSOT contains two additional new modules: 1) lost object recovery, and 2) color-saliency-based shape proposal. They help resolve the tracking loss problem and offer a more flexible object proposal, respectively. Thus, they enable GUSOT to achieve higher tracking accuracy in the long run. We conduct experiments on the large-scale dataset LaSOT with long video sequences, and show that GUSOT offers a lightweight high-performance tracking solution that finds applications in mobile and edge computing platforms.

GUSOT: Green and Unsupervised Single Object Tracking for Long Video Sequences

Textured images are generally difficult to compress because they contain a large number of high frequency components which are difficult to capture with traditional compression schemes such as transform coding, especially at high compression ratios. Since many textures possess a high degree of self-similarity at different scales, the fractal compression technique can be applied to effectively encode such textured images by exploiting this self-similar property. The main drawback of fractal compression is that the fractal encoding procedure is very time consuming. In this research, we focus on the speed up of this procedure by introducing three schemes: dimensionality reduction, energy-based classification, and tree search. We have developed an algorithm that combines these three schemes together and achieves a speed-up factor of 177 at the expense of only 0.4 dB degradation in PSNR relative to the unmodified exhaustive search for a typical textured image encoded with 0.44 bpp.

Fractal-based method for textured-image compression

A 2D intra prediction with geometrical manipulations (2DIP) was proposed in [1] to enhance the intra coding performance of H.264/AVC. However, the complexity of 2DIP is high if the full search scheme is used. In this work, we investigate ways to speed up the intra prediction mode decision for 2DIP. To achieve this, we first conduct a block correlation analysis that reveals the unique characteristics of 2DIP. Based on the analysis, a fast 2DIP search scheme is proposed to reduce the encoder complexity, where a block classification method is used to identify blocks using LIP only, a good initial search position is predicted and a block pruning technique is introduced. It is shown by experimental results that the fast 2DIP search can reduce the complexity of the full search significantly with little loss in the RD performance.

C.-C. Jay Kuo

Papers

Paradigm shifts in modern ICT era and future trends

Pruned octree feature for interactive retrieval

GUSOT: Green and Unsupervised Single Object Tracking for Long Video Sequences

Fractal-based method for textured-image compression

Fast 2D intra prediction (2DIP) mode decision for image and video coding