A standard approach to describe an image for classification and retrieval purposes is to extract a set of local patch descriptors, encode them into a high dimensional vector and pool them into an image-level signature The most common patch encoding strategy consists in quantizing the local descriptors into a finite set of prototypical elements This leads to the popular Bag-of-Visual words representation In this work, we propose to use the Fisher Kernel framework as an alternative patch encoding strategy: we describe patches by their deviation from an "universal" generative Gaussian mixture model This representation, which we call Fisher vector has many advantages: it is efficient to compute, it leads to excellent results even with efficient linear classifiers, and it can be compressed with a minimal loss of accuracy using product quantization We report experimental results on five standard datasets--PASCAL VOC 2007, Caltech 256, SUN 397, ILSVRC 2010 and ImageNet10K--with up to 9M images and 10K classes, showing that the FV framework is a state-of-the-art patch encoding technique

/pdf/image-classification-with-the-fisher-vector-theory-and-4a0lxo3dta.pdf

Image Classification with the Fisher Vector: Theory and Practice

Sparse representation has attracted much attention from researchers in fields of signal processing, image processing, computer vision, and pattern recognition. Sparse representation also has a good reputation in both theoretical research and practical applications. Many different algorithms have been proposed for sparse representation. The main purpose of this paper is to provide a comprehensive study and an updated review on sparse representation and to supply guidance for researchers. The taxonomy of sparse representation methods can be studied from various viewpoints. For example, in terms of different norm minimizations used in sparsity constraints, the methods can be roughly categorized into five groups: 1) sparse representation with $l_{0}$ -norm minimization; 2) sparse representation with $l_{p}$ -norm ( $0 ) minimization; 3) sparse representation with $l_{1}$ -norm minimization; 4) sparse representation with $l_{2,1}$ -norm minimization; and 5) sparse representation with $l_{2}$ -norm minimization. In this paper, a comprehensive overview of sparse representation is provided. The available sparse representation algorithms can also be empirically categorized into four groups: 1) greedy strategy approximation; 2) constrained optimization; 3) proximity algorithm-based optimization; and 4) homotopy algorithm-based sparse representation. The rationales of different algorithms in each category are analyzed and a wide range of sparse representation applications are summarized, which could sufficiently reveal the potential nature of the sparse representation theory. In particular, an experimentally comparative study of these sparse representation algorithms was presented.

A Survey of Sparse Representation: Algorithms and Applications

Super-resolution, the process of obtaining one or more high-resolution images from one or more low-resolution observations, has been a very attractive research topic over the last two decades. It has found practical applications in many real-world problems in different fields, from satellite and aerial imaging to medical image processing, to facial image analysis, text image analysis, sign and number plates reading, and biometrics recognition, to name a few. This has resulted in many research papers, each developing a new super-resolution algorithm for a specific purpose. The current comprehensive survey provides an overview of most of these published works by grouping them in a broad taxonomy. For each of the groups in the taxonomy, the basic concepts of the algorithms are first explained and then the paths through which each of these groups have evolved are given in detail, by mentioning the contributions of different authors to the basic concepts of each group. Furthermore, common issues in super-resolution algorithms, such as imaging models and registration algorithms, optimization of the cost functions employed, dealing with color information, improvement factors, assessment of super-resolution algorithms, and the most commonly employed databases are discussed.

/pdf/super-resolution-a-comprehensive-survey-xjl42yt9nt.pdf

Super-resolution: a comprehensive survey

Image classification is a hot topic in computer vision and pattern recognition. Feature coding, as a key component of image classification, has been widely studied over the past several years, and a number of coding algorithms have been proposed. However, there is no comprehensive study concerning the connections between different coding methods, especially how they have evolved. In this paper, we first make a survey on various feature coding methods, including their motivations and mathematical representations, and then exploit their relations, based on which a taxonomy is proposed to reveal their evolution. Further, we summarize the main characteristics of current algorithms, each of which is shared by several coding strategies. Finally, we choose several representatives from different kinds of coding approaches and empirically evaluate them with respect to the size of the codebook and the number of training samples on several widely used databases (15-Scenes, Caltech-256, PASCAL VOC07, and SUN397). Experimental findings firmly justify our theoretical analysis, which is expected to benefit both practical applications and future research.

Feature Coding in Image Classification: A Comprehensive Study

In this paper, we present dictionary learning methods for sparse signal representations in a high dimensional feature space. Using the kernel method, we describe how the well known dictionary learning approaches, such as the method of optimal directions and KSVD, can be made nonlinear. We analyze their kernel constructions and demonstrate their effectiveness through several experiments on classification problems. It is shown that nonlinear dictionary learning approaches can provide significantly better performance compared with their linear counterparts and kernel principal component analysis, especially when the data is corrupted by different types of degradations.

Design of Non-Linear Kernel Dictionaries for Object Recognition

Service oriented architecture (SOA) is an approach for building distributed systems that deliver application functionality as a set of self-contained business-aligned services with well-defined and discoverable interfaces. This paper presents a systematic and architecture-centric framework, named service oriented architecture framework (SOAF), to ease the definition, the design and the realization of SOA in order to achieve a better business and IT alignment. The proposed framework is business-process centric and comprises a set of structured activities grouped in five phases. It incorporates a range of techniques and guidelines for systematically identifying services, deciding service granularity and modeling services while integrating existing operational/legacy systems. The results from a pilot validation of SOAF for SOA enablement of a realistic securities trading application are presented. Best practices and lessons learned are also discussed

SOAF: An Architectural Framework for Service Definition and Realization

This paper presents the case study of a leading US financial Institution International Financial and Brokerage Services (IFBS), which faced SOA realization issues while it followed an inappropriate SOA design strategy. While riding on the SOA hype wave, it implemented thousands of fine grained Web-services without paying much heed to issues like governance, and usage within its business processes. IFBSpsilas service portfolio comprises of a gamut of services which although on paper looked good, but presented a lot of challenges in their usage and maintenance. We address some of these issues in this paper and present our framework for SOA adoption (called INSOAP) which can be effective in a similar end- to-end SOA adoption exercise in an enterprise.

http://www.einsten.net/pdf/10210258078.pdf

The Role of Service Granularity in a Successful SOA Realization A Case Study

Images in general are captured under a diverse set of conditions. An image of the same object can be captured with varied poses, illuminations, scales, backgrounds and probably different camera parameters. The task of image classification then lies in forming features of the input images in a representational space where classifiers can be better supported in spite of the above variations. Existing methods have mostly focused on obtaining features which are invariant to scale and translation, and thus they generally suffer from performance degradation on datasets which consist of images with varied poses or camera orientations. In this paper we present a new framework for image classification, which is built upon a novel way of feature extraction that generates largely affine-invariant features called affine sparse codes. This is achieved through learning a compact dictionary of features from affine-transformed input images. Analysis and experiments indicate that this novel feature is highly discriminative in addition to being largely affine-invariant. A classifier using AdaBoost is then designed using the affine sparse codes as the input. Extensive experiments with standard databases demonstrate that the proposed approach can obtain the state-of-the-art results, outperforming existing leading approaches in the literature.

Discriminative affine sparse codes for image classification

Recently, compressive sensing (CS) has emerged as a powerful tool for solving a class of inverse/underdetermined problems in computer vision and image processing. In this paper, we investigate the application of CS paradigms on single image super-resolution (SR) problems that are considered to be the most challenging in this class. In light of recent promising results, we propose novel tools for analyzing sparse representation-based inverse problems using redundant dictionary basis. Further, we provide novel results establishing tighter correspondence between SR and CS. As such, we gain insights into questions concerning regularizing the solution to the underdetermined problem, such as follows. 1) Is sparsity prior alone sufficient? 2) What is a good dictionary? 3) What is the practical implication of noncompliance with theoretical CS hypothesis? Unlike in other underdetermined problems that assume random down-projections, the low-resolution image formation model employed in CS-based SR is a deterministic down-projection that may not necessarily satisfy some critical assumptions of CS. We further investigate the impact of such projections in concern to the above questions.

Understanding Compressive Sensing and Sparse Representation-Based Super-Resolution

The raison dpsilaetre for Web-services is that they could be used to compose new services. As in process centric systems, wherein blocks of software implement a functional domain through a set of linked activities, a SOA based system modeled through Web-services, requires business services (of low granularity) which implement various business functions. Such business services could not only ensure a high degree of re-use but could also help in realizing service oriented architecture in its true sense. Although today quite a few approaches for the problem exist, but most of them are bottom up solutions, or mainly focus on domain decomposition and composite service formation. Not many of them have yet utilized the full potential of business processes, which form the backbone of any enterprise. In this work we define what a business service would be like, vis-a-vis its corresponding business function, and how it could be realized through data, utility, information and other services. We present our service identification approach which utilizes process maps and service hierarchies and towards the end we discuss some of our current work in building an automation tool (named SQUID) for service identification.

Naveen Kulkarni

Papers

SOAF: An Architectural Framework for Service Definition and Realization

The Role of Service Granularity in a Successful SOA Realization A Case Study

Discriminative affine sparse codes for image classification

Understanding Compressive Sensing and Sparse Representation-Based Super-Resolution

A Model Driven Service Identification Approach for Process Centric Systems