基于完整LBP特征的人脸识别*

提出一种基于完整局部二值模式(CLBP)进行人脸识别的方法,CLBP算子包括三个部分:中心像素的LBP(CLBP_C)、符号部分的LBP(CLBP_S)、数值部分的LBP(CLBP_M)。该方法首先采用CLBP算子提取人脸灰度图像的直方图;然后融合成CLBP直方图,进行直方图相似性比较;最后根据最近邻原则进行识别。在ORL和YALE标准人脸数据库上的实验表明,该方法得到的结果比LBP效果更好,鲁棒性更高。     

Generic model abstraction from examples

The recognition community has typically avoided bridging the representational gap between traditional, low-level image features and generic models. Instead, the gap has been artificially eliminated by either bringing the image closer to the models using simple scenes containing idealized, textureless objects or by bringing the models closer to the images using 3D CAD model templates or 2D appearance model templates. In this paper, we attempt to bridge the representational gap for the domain of model acquisition. Specifically, we address the problem of automatically acquiring a generic 2D view-based class model from a set of images, each containing an exemplar object belonging to that class. We introduce a novel graph-theoretical formulation of the problem in which we search for the lowest common abstraction among a set of lattices, each representing the space of all possible region groupings in a region adjacency graph representation of an input image. The problem is intractable and we present a shortest path-based approximation algorithm to yield an efficient solution. We demonstrate the approach on real imagery.     

Face recognition using elastic local reconstruction based on a single face image

In this paper, we propose a new face recognition algorithm based on a single frontal-view image for each face subject, which considers the effect of the face manifold structure. To compare two near-frontal face images, each face is considered a combination of a sequence of local image blocks. Each of the image blocks of one image can be reconstructed according to the corresponding local image block of the other face image. Then an elastic local reconstruction (ELR) method is proposed to measure the similarities between the image block pairs in order to measure the difference between the two face images. Our algorithm not only benefits from the face manifold structure, in terms of being robust to various image variations, but also is computationally simple because there is no need to build the face manifold. We evaluate the performance of our proposed face recognition algorithm with the use of different databases, which are produced under various conditions, e.g. lightings, expressions, perspectives, with/without glasses and occlusions. Consistent and promising experimental results were obtained, which show that our algorithm can greatly improve the recognition rates under all the different conditions.     

Algebraic and PDE Approaches for Lattice Scale-Spaces with Global Constraints

This paper begins with analyzing the theoretical connections between levelings on lattices and scale-space erosions on reference semilattices. They both represent large classes of self-dual morphological operators that exhibit both local computation and global constraints. Such operators are useful in numerous image analysis and vision tasks including edge-preserving multiscale smoothing, image simplification, feature and object detection, segmentation, shape and motion analysis. Previous definitions and constructions of levelings were either discrete or continuous using a PDE. We bridge this gap by introducing generalized levelings based on triphase operators that switch among three phases, one of which is a global constraint. The triphase operators include as special cases useful classes of semilattice erosions. Algebraically, levelings are created as limits of iterated or multiscale triphase operators. The subclass of multiscale geodesic triphase operators obeys a semigroup, which we exploit to find PDEs that can generate geodesic levelings and continuous-scale semilattice erosions. We discuss theoretical aspects of these PDEs, propose discrete algorithms for their numerical solution which converge as iterations of triphase operators, and provide insights via image experiments.     

Robust reconstruction of low-resolution document images by exploiting repetitive character behaviour

In this paper, we present a new approach for reconstructing low-resolution document images. Unlike other conventional reconstruction methods, the unknown pixel values are not estimated based on their local surrounding neighbourhood, but on the whole image. In particular, we exploit the multiple occurrence of characters in the scanned document. In order to take advantage of this repetitive behaviour, we divide the image into character segments and match similar character segments to filter relevant information before the reconstruction. A great advantage of our proposed approach over conventional approaches is that we have more information at our disposal, which leads to a better reconstruction of the high-resolution (HR) image. Experimental results confirm the effectiveness of our proposed method, which is expressed in a better optical character recognition (OCR) accuracy and visual superiority to other traditional interpolation and restoration methods.     

Connectivity on Complete Lattices: New Results

The notion of connectivity is very important in image processing and analysis, and particularly in problems related to image segmentation. It is well understood, however, that classical notions of connectivity, including topological and graph-theoretic notions, are not compatible with each other. This motivated G. Matheron and J. Serra to develop a general framework of connectivity, which unifies most classical notions, circumvents incompatibility issues, and allows the construction of new types of connectivity for binary and grayscale images. In this paper, we enrich this theory of connectivity by providing several new theoretical results and examples that are useful in image processing and analysis. In particular, we provide new results on the semi-continuity behavior of connectivity openings, we study the reconstruction operator in a complete lattice framework, and we extend some known binary results regarding reconstruction to this framework. Moreover, we study connectivities constructed by expanding given connectivities by means of clustering operators and connectivities constructed by restricting given connectivities by means of contraction operators.     

Morphable model space based face super-resolution reconstruction and recognition

Super-resolution image reconstruction is the process of producing a high-resolution image from a set of low-resolution images of the same scene. For the applications of performing face evaluation and/or recognition from low-resolution video surveillance, in the past, super-resolution image reconstruction was mainly used as a separate preprocessing step to obtain a high-resolution image in the pixel domain that is later passed to a face feature extraction and recognition algorithm. Such three-stage approach suffers a high degree of computational complexity. A low-dimensional morphable model space based face super-resolution reconstruction and recognition algorithm is proposed in this paper. The approach tries to construct the high-resolution information both required by reconstruction and recognition directly in the low dimensional feature space. We show that comparing with generic pixel domain algorithms, the proposed approach is more robust and more computationally efficient.     

The illumination-invariant matching of deterministic localstructure in color images

The availability of multiple spectral measurements at each pixel in an image provides important additional information for recognition. Spectral information is of particular importance for applications where spatial information is limited. Such applications include the recognition of small objects or the recognition of small features on partially occluded objects. We introduce a feature matrix representation for deterministic local structure in color images. Although feature matrices are useful for recognition, this representation depends on the spectral properties of the scene illumination. Using a linear model for surface spectral reflectance with the same number of parameters as the number of color bands, we show that changes in the spectral content of the illumination correspond to linear transformations of the feature matrices, and that image plane rotations correspond to circular shifts of the matrices. From these relationships, we derive an algorithm for the recognition of local surface structure which is invariant to these scene transformations. We demonstrate the algorithm with a series of experiments on images of real objects     

图像场方向导数的局部区域重建

目的 目前图像修复的研究是以人眼不能察觉为目标,注重视觉效果而不追求重建的准确性。本文提出一种能准确重建图像缺损边缘的重建算法。方法 采用稳定场作为图像局部纹理的数学物理描述,提出基于点源影响函数的图像局部区域重建模型,该模型针对每一个缺损点,计算周围各已知点对它的影响,以期较为准确地重建该点;并根据该场中的方向导数,分析各已知点与缺损点的差异性及相似性,确定一种点源影响函数的计算方法,以实现该重建模型。结果 实验结果表明所提算法与传统修复算法相比,对图像边缘及纹理细节的重建更加清晰,同时保持了较好的整体视觉效果;且重建过程无迭代计算,具有较高的效率。结论 实验结果表明,该算法在重建效率和准确重建方面均取得了较好的成果。     

Seeking the user interface

User interface design and coding can be complex and messy. We describe a system that uses code search to simplify and automate the exploration of such code. We start with a simple sketch of the desired interface along with a set of keywords describing the application context. If necessary, we convert the sketch into a scalable vector graphics diagram. We then use existing code search engines to find results based on the keywords. We look for potential Java-based graphical user interface solutions within those results and apply a series of code transformations to the solutions to generate derivative solutions, aiming to get solutions that constitute only the user interface and that will compile and run. We run the resultant solutions and compare the generated interfaces to the user’s sketches. Finally, we let programmers interact with the matched solutions and return the running code for the solutions they choose. The system is useful for exploring alternative interfaces to the initial and for looking at graphical user interfaces in a code repository.     

基于梯度比率的SAR图像局部特征提取方法研究

本文研究了基于像素灰度差值计算的LBP算子和基于梯度比率的LGRP算子等局部二值模式。首先介绍了基本LBP算子和其他几种LBP算子的变形模式,并通过光学图像和实测SAR图像对LBP算子进行性能评估。针对LBP对SAR 图像乘性噪声敏感的问题,利用梯度比率计算的LGRP算子,并结合旋转不变LBP的抗旋转性,本文提出了一种改进的SAR 图像LGRP特征,获得了对SAR 图像的抗噪性和抗旋转性能。实验结果表明,由本文方法提取的SAR图像局部特征具有较好的不变性,可用于姿态角变化下的目标识别与图像纹理切片匹配。     

CONVERTING RUN CODE TO CHAIN CODE

Abstract

The run code is easy to generate on-line from a video signal but the chain code is often more useful. A simple, fast algorithm is presented for constructing chain code from run code. The algorithm defines the order of preference of the next move for a “bug,” given its most recent move. The task for this bug is to travel right around the outermost edge elements of the object whose silhouette appears in the binary image. It is assumed that there is only one such object which may contain holes, although these are not coded by this simple algorithm. The algorithm generates a 4-value code whereas it is more usual to use an 8-value chain code which can be created by a simple method described by Freeman in his definitive work on the chain code.     

Pattern recognition experiments in the mandala/cosine domain

The problem of recognition of objects in images is investigated from the simultaneous viewpoints of image bandwidth compression and automatic target recognition. A scenario is suggested in which recognition is implemented on features in the block cosine transform domain which is useful for data compression as well. While most image frames would be processed by the automatic recognition algorithms in the compressed domain without need for image reconstruction, this still allows for visual image classification of targets with poor recognition rates (by human viewing at the receiving terminal). It has been found that the Mandala sorting of the block cosine domain results in a more effective domain for selecting target identification parameters. Useful features from this Mandala/cosine domain are developed based upon correlation parameters and homogeneity measures which appear to successfully discriminate between natural and man-made objects. The Bhattacharyya feature discriminator is used to provide a 10:1 compression of the feature space for implementation of simple statistical decision surfaces (Gaussian and minimum distance classification). Imagery sensed in the visible spectra with a resolution of approximately 5-10 ft is used to illustrate the success of the technique on targets such as ships to be separated from clouds. A data set of 38 images is used for experimental verification with typical classification results ranging from the high 80's to low 90 percentile regions depending on the options choosen.     

Relative affine structure: canonical model for 3D from 2D geometryand applications

We propose an affine framework for perspective views, captured by a single extremely simple equation based on a viewer-centered invariant we call relative affine structure. Via a number of corollaries of our main results we show that our framework unifies previous work-including Euclidean, projective and affine-in a natural and simple way, and introduces new, extremely simple algorithms for the tasks of reconstruction from multiple views, recognition by alignment, and certain image coding applications     

Non-negativity and locality constrained Laplacian sparse coding for image classification

The traditional sparse coding (SC) method has achieved good results in image classification. However, one of its serious weaknesses is that it ignores the relationship between features thus losing spatial information. Moreover, in combinatorial optimisation problems, operations of addition and subtraction are involved, and the use of subtraction may cause features to be cancelled. In this paper, we propose a method called non-negativity and locality constrained Laplacian sparse coding (NLLSC) for image classification. Firstly, non-negative matrix factorisation (NMF) is used in the Laplacian sparse coding (LSC), which is applied to constrain the negativity of both codebook and code coefficient. Secondly, we introduce K-nearest neighbouring codewords for local features because locality is more important than sparseness. Finally, non-negativity and locality constrained operators are introduced to obtain a novel sparse coding for local features, and then in the pooling step, we use spatial pyramid division (SPD) and max pooling (MP) to represent the final images. As for image classification, multi-class linear SVM is adopted. Experiments on several standard image datasets have shown better performance than previous algorithms.     

Quantitative Static Analysis Over Semirings: Analysing Cache Behaviour for Java Card

We present a semantics-based technique for modeling and analysing resource usage behaviour of programs written in a simple object oriented language like Java Card byte code. The approach is based on the quantitative abstract interpretation framework of Di Pierro and Wiklicky where programs are represented as linear operators. We consider in particular linear operators over semi-rings (such as max-plus) that have proven useful for analysing cost properties of discrete event systems. We illustrate our technique through a cache behaviour analysis for Java Card.     

Face recognition with local steerable phase feature

In this paper, we propose a novel local steerable phase (LSP) feature extracted from the face image using steerable filters for face recognition. The new type of local feature is semi-invariant under common image deformations and distinctive enough to provide useful identity information. Phase information provided by steerable filters is locally stable with respect to scale changes, noise and brightness changes. Phase features from multiple scales and orientations are concatenated to an augmented feature vector which is used to evaluate similarity between face images. We use a nearest-neighbor classifier based on the local weighted phase-correlation for final classification. The experimental results on FERET dataset show an encouraging recognition performance.     

Orthogonal moments based on exponent functions: Exponent-Fourier moments

In this paper, we propose a new set of orthogonal moments based on Exponent functions, named Exponent-Fourier moments (EFMs), which are suitable for image analysis and rotation invariant pattern recognition. Compared with Zernike polynomials of the same degree, the new radial functions have more zeros, and these zeros are evenly distributed, this property make EFMs have strong ability in describing image. Unlike Zernike moments, the kernel of computation of EFMs is extremely simple. Theoretical and experimental results show that Exponent-Fourier moments perform very well in terms of image reconstruction capability and invariant recognition accuracy in noise-free, noisy and smooth distortion conditions. The Exponent-Fourier moments can be thought of as generalized orthogonal complex moments.