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

Image compression has experienced a new revolution with the success of deep learning, which yields superior rate-distortion (RD) performance against traditional codecs. Yet, high computational complexity and energy consumption are the main bottlenecks that hinder the practical applicability of deep-learning-based (DL-based) codecs. Inspired by the neural network’s hierarchic structure yet with lower complexity, we propose a new lightweight image coding framework and name it the ”Green Image Codec” (GIC) in this work. First, GIC down-samples an input image into several spatial resolutions from fine-to-coarse grids and computes image residuals between two adjacent grids. Then, it encodes the coarsest content, interpolates content from coarse-tofine grids, encodes residuals, and adds residuals to interpolated images for reconstruction. All coding steps are implemented by vector quantization while all interpolation steps are conducted by the Lanczos interpolation. To facilitate VQ codebook training, the Saab transform is applied for energy compaction and, thus, dimension reduction. A simple rate-distortion optimization (RDO) is developed to help select the coding parameters. GIC yields an RD performance that is comparable with BPG at significantly lower complexity. 

Green image codec: a lightweight learning-based image coding method

The transmission of animated 2D graphics via the wireless link of the personal digital assistant (PDA) system is investigated in this work. An animated graphic sequence is often stored in the animated GIF format and transmitted via wired networks. Due to the much narrower bandwidth requirement of a wireless channel, the same approach cannot be properly used in the wireless environment. This paper presents a new approach to wireless transmission of animated sequences. Basic elements of 2D graphics include points, lines, polygons and different color filling commands. Furthermore, to achieve the animation effect, a reference frame is often used to reduce the redundancy between adjacent frames. All these can be considered as rendering commands. The major different between 2D graphics and the GIF image is that the former is on structure level while the latter is on pixel level (i.e. bitmap). By exploiting this unique feature, we are able to obtain a more efficient coding method for the component frame. That is, instead of transmitting the rendered bitmap as done with animated GIF, rendering commands are encoded and transmitted to client's PDA while the rendering process is actually performed at the client side. With the proposed scheme, the compression standard is built upon a common set of rendering commands. The final integration involves buffer control and error protection. It is demonstrated by experiments that animated sequences can be transmitted within a channel of bandwidth less than 1 Kbps while maintaining excellent image quality.© (1998) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.

Wireless transmission of animated 2D graphics for personal digital assistant (PDA) systems

In this work, we propose a new data visualization and clustering technique for discovering discriminative structures in high-dimensional data. This technique, referred to as cPCA++, utilizes the fact that the interesting features of a "target" dataset may be obscured by high variance components during traditional PCA. By analyzing what is referred to as a "background" dataset (i.e., one that exhibits the high variance principal components but not the interesting structures), our technique is capable of efficiently highlighting the structure that is unique to the "target" dataset. Similar to another recently proposed algorithm called "contrastive PCA" (cPCA), the proposed cPCA++ method identifies important dataset specific patterns that are not detected by traditional PCA in a wide variety of settings. However, the proposed cPCA++ method is significantly more efficient than cPCA, because it does not require the parameter sweep in the latter approach. We applied the cPCA++ method to the problem of image splicing localization. In this application, we utilize authentic edges as the background dataset and the spliced edges as the target dataset. The proposed method is significantly more efficient than state-of-the-art methods, as the former does not require iterative updates of filter weights via stochastic gradient descent and backpropagation, nor the training of a classifier. Furthermore, the cPCA++ method is shown to provide performance scores comparable to the state-of-the-art Multi-task Fully Convolutional Network (MFCN).

Efficient Image Splicing Localization via Contrastive Feature Extraction.

A new rate adaptation mechanism called SFRAM is developed based on the TCP-throughput equation in this research to facilitate end-to-end Internet video transmission. The proposed scheme not only achieves TCP-friendliness but also provides a smooth and fast rate adaptation for Internet video delivery. By adaptively averaging measurements such as the round trip time (RTT) and the packet loss rate over a suitable window, SFRAM mitigates unnecessary fluctuation that is undesirable for video transmission. The adopted weighting scheme enables the response in a fast manner only for distinct network variations so that the overall network utilization is improved and end-to-end video quality is sustained. When integrated with active routing support such as RED (random early detection) and ECN (explicit congestion notification), SFRAM provides the best possible performance. Additionally, this property is utilized to select an interactive error control scheme so that the video encoder can choose the most effective error recovery option based on the network status. Extensive experiments by using the ns-2 network simulator and the real Internet are performed to test the dynamic behavior of SFRAM. The seamless integration of an interactively linked ns-2 network simulator and the ITU-T H.263+ video encoder is demonstrated for network-aware error control as well as rate adaptation of Internet video.

C.-C. Jay Kuo

Papers

Green image codec: a lightweight learning-based image coding method

Wireless transmission of animated 2D graphics for personal digital assistant (PDA) systems

Efficient Image Splicing Localization via Contrastive Feature Extraction.

Smooth and Fast Rate Adaptation and Network-Aware Error Control for TCP-friendly Internet Video Transmission

Precoding Techniques for MIMO Channels