Search

In the domain of target recognition, the image complexity of target and background is used to describe the difficult degree of extracting and recognizing target from complex background, which has important guiding significance and widely application prospect in a lot of domains such as biological medical, information encrypt, image compression, meteorological analysis, automatic target recognition. This paper comprehensively took the innate characteristics of target and the target local background characteristic into consideration, which affected the algorithm performance of target extraction and recognition, then made generalizations of three classes of evaluation methods: methods based on the target characteristic, including the target shape characteristic, the gray standard deviation of target pixels, the target Local background entropy difference, etc; methods based on the target similitude, including the edge profile and structural characteristic similitude between target and phony target; methods based on the background characteristic, including texture characteristic edge ratio, etc. And on this basis, we made research on the relationship of structural features and evaluation parameters, and analyzed the foundation and properties of each method by contrast. Thoughts and foresights of this field are given at the end of this paper.

This paper presents a novel pattern recognition method based on Reeb graph representation. The main idea of this approach is to reinforce the topological consistency conditions of the graph-based description. This approach enfolds an off-line step and an on-line step. In the off-line one, 3D shape is represented by a Reeb graph associated with geometrical signatures based on parametrization approaches. The similarity estimation is performed in the on-line step. It consists to compute a global similarity measure which quantifies the similitude degree between any pair of 3D-models in the given dataset. The experimental results obtained on the SHREC 2012 database show the system effectiveness in 3D shape recognition.

We describe the automated application of an area based registration method to the surface inspection of steel industry products as a tool to solve an intermediate mosaicing problem. The main problem of area based methods is that there is high probability that the results of a matching process will be incorrect if a region of interest without any relevant detail is used. The selection of a region of interest with relevant content continues to be a problem nowadays. We propose a method to select a salient area when using a zero mean normalised cross correlation metric and a block as a region of interest. The selection of the size and the position of the block is focused on ensuring a smooth unimodal similarity surface around the maximum similitude point. Experiments show a correlation between the surface kurtosis of the block autocovariance and the same coefficient measured over the correlation surface around the maximum similitude point for the three different steel products analysed. We check that the maximum correlation value is reached abruptly, in a small range of pixels around the maximum similitude point, in correlation surfaces obtained from blocks containing non-relevant information. On the other hand, salient blocks usually lead to unimodal smooth similarity surfaces with small sensitivity to noise in contrast with the ones obtained from non-remarkable blocks. Also, the method proposed allows the application of fast search algorithms based on the unimodality of the correlation surface, obtaining high computational time reduction in comparison with full search strategies using fast normalised cross correlation algorithms.

The paper presents an image-oriented modality to functionally describe articially and biologically nanostruc- tured surfaces, which can be used for the characterization of the atom neighborhoods on the surface of proteins. The both properties,hydrophobicity and charge distribution on protein surface, are analyzed in this paper. The actual discrete hydrophobicity and charge distribution attached to the atoms that form a surface atom's vicinity is replaced by an approximately equivalent density distribution, computed in a standardized octagonal pattern around each atom. These representations of hydrophobicities and charges are used to compute the resemblance of surface atom neighborhoods belonging to a protein, dened as the sum of the products of hydrophobicity densities of the corresponding patches (the pattern's central circles or angular sectors having the same position). The similitude and the interaction of a pair of atom neighborhoods are dened as their resemblance for parallel, respectively, anti-parallel orientations of the normals on the molecular surfaces in the points where the central atoms are located. Surface atom neighborhoods have been classied in terms of both resemblance and vector description.© (2012) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.

The paper presents an image-oriented modality to functionally describe artificially and biologically nanostructured surfaces, which can be used for the characterization of the atom neighborhoods on the surface of proteins. The property which is mainly analyzed in this paper is the hydrophobicity distribution on protein surface, but the distributions of charges and mutual electrical potentials can also be considered. The actual discrete hydrophobicity distribution attached to the atoms that form a surface atom's vicinity is replaced by an approximately equivalent hydrophobicity density distribution, computed in a standardized octagonal pattern around each atom. These representation of hydrophobicities is used to compute the resemblance of surface atom neighborhoods belonging to a protein, defined as the sum of the products of hydrophobicity densities of the corresponding patches (the pattern's central circles or angular sectors having the same position). The similitude and the interaction of a pair of atom neighborhoods are defined as their resemblance for parallel, respectively, anti-parallel orientations of the normals on the molecular surfaces in the points where the central atoms are located. The purpose of this work is to create a database of selected protein surfaces that will be used for nanotechnology research and applications purposes.

Managing large document databases is an important task today. Being able to automatically com- pare document layouts and classify and search documents with respect to their visual appearance proves to be desirable in many applications. We measure single page documents' similarity with respect to distance functions between three document components: background, text, and saliency. Each document component is represented as a Gaussian mixture distribution; and distances between dierent documents' components are calculated as probabilistic similarities between corresponding distributions. The similarity measure between documents is represented as a weighted sum of the components' distances. Using this document similarity measure, we propose a browsing mechanism operating on a document dataset. For these purposes, we use a hierarchical browsing environment which we call the document similarity pyramid. It allows the user to browse a large document dataset and to search for documents in the dataset that are similar to the query. The user can browse the dataset on dierent levels of the pyramid, and zoom into the documents that are of interest.

A SemiBoost-based character recognition method is introduced in order to incorporate the information of unlabeled practical samples in training stage. One of the key problems in semi-supervised learning is the criteria of unlabeled sample selection. In this paper, a criteria based on pair-wise sample similarity is adopted to guide the SemiBoost learning process. At each time of iteration, unlabeled examples are selected and assigned labels. The selected samples are used along with the original labeled samples to train a new classifier. The trained classifiers are integrated to make the final classfier. An empirical study on several Arabic similar character pairs with different similarities shows that the proposed method improves the performance as unlabeled samples reveal the distribution of practical samples.

A large amount of handwritten historical documents are located in libraries around the world. The desire to access, search, and explore these documents paves the way for a new age of knowledge sharing and promotes collaboration and understanding between human societies. Currently, the indexes for these documents are generated manually, which is very tedious and time consuming. Results produced by state of the art techniques, for converting complete images of handwritten documents into textual representations, are not yet sufficient. Therefore, word-spotting methods have been developed to archive and index images of handwritten documents in order to enable efficient searching within documents. In this paper, we present a new matching algorithm to be used in word-spotting tasks for historical Arabic documents. We present a novel algorithm based on the Chamfer Distance to compute the similarity between shapes of word-parts. Matching results are used to cluster images of Arabic word-parts into different classes using the Nearest Neighbor rule. To compute the distance between two word-part images, the algorithm subdivides each image into equal-sized slices (windows). A modified version of the Chamfer Distance, incorporating geometric gradient features and distance transform data, is used as a similarity distance between the different slices. Finally, the Dynamic Time Warping (DTW) algorithm is used to measure the distance between two images of word-parts. By using the DTW we enabled our system to cluster similar word-parts, even though they are transformed non-linearly due to the nature of handwriting. We tested our implementation of the presented methods using various documents in different writing styles, taken from Juma'a Al Majid Center - Dubai, and obtained encouraging results.

In this work, we introduce EdgeMaps as a new method for integrating the visualization of explicit and implicit data relations. Explicit relations are specific connections between entities already present in a given dataset, while implicit relations are derived from multidimensional data based on shared properties and similarity measures. Many datasets include both types of relations, which are often difficult to represent together in information visualizations. Node-link diagrams typically focus on explicit data connections, while not incorporating implicit similarities between entities. Multi-dimensional scaling considers similarities between items, however, explicit links between nodes are not displayed. In contrast, EdgeMaps visualize both implicit and explicit relations by combining and complementing spatialization and graph drawing techniques. As a case study for this approach we chose a dataset of philosophers, their interests, influences, and birthdates. By introducing the limitation of activating only one node at a time, interesting visual patterns emerge that resemble the aesthetics of fireworks and waves. We argue that the interactive exploration of these patterns may allow the viewer to grasp the structure of a graph better than complex node-link visualizations.

With the advent of high resolution imaging through the atmosphere, turbulence distribution measurement has become a key issue. The possibility to measure C2n profile from Shack-Hartman data, slopes and intensities, acquired on a unique point source has recently been demonstrated numerically.1 This method, called SCOSLIDAR, is exploited here on experimental data. From slopes and intensities of a mid-infrared wavefront sensor, C2n profiles along an oblique line of sight are estimated and compared to local measurements. Time averaged profiles are confronted to a profile deduced from similitude law.

This paper presents a work-piece position correction equipment. In order to correct work-piece position, for using video signal, this paper illustrates the method of similarity rate of labelled images to carry on object location and to calculate work-piece's deviate angle. This method is proved to be useful and efficient in testing. This paper is new and original in three facts. First, using similarity rate of labelled image is more convenient for this purpose than the complex combination of sensors and machinery. Second, the algorithm of this method is easier to realize than other methods. Third, this equipment can fit a multi-purpose situation through flexible adjusting matching labelled image. This method in the paper can be widely used in other similar application.

Image fusion can integrate several images of the same scene captured by several different sensors with different features and resolutions at different time into one image. Research on quality assessment of fusion images is meaningful for image processing course in order to improve the registration technology and fusion algorithm. Structural similarity metric describes differences between two images by means of three variables, luminance, contrast, and spatial similarity, which show the better evaluating capability than others objective metrics. A new assessment method to fusion effect based on structural similarity comparison among fusion images is provided in paper. Fusion algorithms including weighing method, principal component analysis, different pyramid methods and multi-resolution wavelet filtering is used to create fusion images. Then the mutual structural similarity metric among fusion images obtained by different fusion algorithms is used to evaluate the fusion effect. In some extent, the low structural similarity comparison denotes the low quality fusion effect. Meanwhile, the experiment show also the fusion effect determined by structural similarity comparison is accordant with the subjective evaluation. Besides, the experiment explain the method based on different pyramid methods and multi-resolution wavelet filtering have the better fusion effect than weighing method and principal component analysis method. Furthermore, the experiment also prove the whole image fusion system should choose the different fusion algorithm to adjust to the different task requirement and applied circumstance in order to acquire the optimum scene interpreting effect.

Humans are the ultimate receivers of the visual information contained in an image, so the reasonable method of image quality assessment (IQA) should follow the properties of the human visual system (HVS). In recent years, IQA methods based on HVS-models are slowly replacing classical schemes, such as mean squared error (MSE) and Peak Signal-to-Noise Ratio (PSNR). IQA-structural similarity (SSIM) regarded as one of the most popular HVS-based methods of full reference IQA has apparent improvements in performance compared with traditional metrics in nature, however, it performs not very well when the images' structure is destroyed seriously or masked by noise. In this paper, a new efficient fovea based structure similarity image quality assessment (FSSIM) is proposed. It enlarges the distortions in the concerned positions adaptively and changes the importances of the three components in SSIM. FSSIM predicts the quality of an image through three steps. First, it computes the luminance, contrast and structure comparison terms; second, it computes the saliency map by extracting the fovea information from the reference image with the features of HVS; third, it pools the above three terms according to the processed saliency map. Finally, a commonly experimental database LIVE IQA is used for evaluating the performance of the FSSIM. Experimental results indicate that the consistency and relevance between FSSIM and mean opinion score (MOS) are both better than SSIM and PSNR clearly.

Atmospheric turbulence is an imaging phenomenon that introduces blur, distortion, and intensity fluctuations that corrupt image quality and can decrease target acquisition performance. The modeling of imaging sensors requires an accurate description of turbulence effects. We present two novel methodologies for the measurement of the turbulence MTF in infrared imagery. First, the structural similarity metric is used to compare pristine and degraded imagery. Second, contrast modulations of radial bar targets are analyzed to extract an equivalent blur. Human perception tests are compared against model predictions. The results show that complex turbulence effects can be measured and modeled with simple MTF blurs.

Computing the similarity between videos is a challenging problem in many applications of video processing such as video retrieval and video-based action recognition. The main difficulty in evaluating similarity between videos is the lack of an effective distance measure. In this paper, we propose a clustering based distance measure to solve this problem. In our approach, a video sequence is represented by a set of spatiotemporal descriptors. Therefore computing the similarity between two video sequences can be achieved by estimating the distance between two sets of descriptors extracted from the videos. To compute the distance measure, we use clustering to obtain distributions and "constrained distributions" of the two sets of descriptors, and use Kullback-Leibler (KL) divergence [6] with the distributions. We apply our distance measure to the problems of distinguishing different human actions and content-based video retrieval. Our experimental results show that the proposed distance measure is an effective metric for these applications.

This paper presents a local feature-based method for matching facial sketch images to face photographs, which is the first known feature-based method for performing such matching. Starting with a training set of sketch to photo correspondences (i.e. a set of sketch and photo images of the same subjects), we demonstrate the ability to match sketches to photos: (1) directly using SIFT feature descriptors, (2) in a "common representation" that measures the similarity between a sketch and photo by their distance from the training set of sketch/photo pairs, and (3) by fusing the previous two methods. For both matching methods, the first step is to sample SIFT feature descriptors uniformly across all the sketch and photo images. In direct matching, we simply measure the distance of the SIFT descriptors between sketches and photos. In common representation matching, the distance between the descriptor vectors of the probe sketches and gallery photos at each local sample point is measured. This results in a vector of distances across the sketch or photo image to each member of the training basis. Further recognition improvements are shown by score level fusion of the two sketch matchers. Compared with published sketch to photo matching algorithms, experimental results demonstrate improved matching performances using the presented feature-based methods.

A new face recognition algorithm has been proposed which is robust to variations in pose, expression, illumination and occlusions such as sunglasses. The algorithm is motivated by the Edit Distance used to determine the similarity between strings of one dimensional data such as DNA and text. The key to this approach is how to extend the concept of an Edit Distance on one-dimensional data to two-dimensional image data. The algorithm is based on mapping one image into another and using the characteristics of the mapping to determine a two-dimensional Pictorial-Edit Distance or P-Edit Distance. We show how the properties of the mapping are similar to insertion, deletion and substitution errors defined in an Edit Distance. This algorithm is particularly well suited for face recognition in uncontrolled environments such as stand-off and other surveillance applications. We will describe an entire system designed for face recognition at a distance including face detection, pose estimation, multi-sample fusion of video frames and identification. Here we describe how the algorithm is used for face recognition at a distance, present some initial results and describe future research directions.(

There is considerable research in the field of content-based image retrieval (CBIR); however, few of the current systems incorporate radiologists' visual impression of image similarity. Our objective is to bridge the semantic gap between radiologists' ratings and image features. We have been developing a conceptual-based similarity model derived from content-based similarity to improve CBIR. Previous work in our lab reduced the Lung Image Database Consortium (LIDC) data set into a selection of 149 images of unique nodules, each containing nine semantic ratings by four radiologists and 64 computed image features. After evaluating the similarity measures for both content-based and semantic-based features, we selected 116 nodule pairs with a high correlation between both similarities. These pairs were used to generate a linear regression model that predicts semantic similarity with content similarity input with an R 2 value of 0.871. The characteristics and features of nodules that were used for the model were also investigated.

The performance of image classification largely depends on both the discrimination power of the visual features for image content representation and the effectiveness of the kernels for diverse image similarity characterization. Different types of kernels have been developed for SVM image classifier training, and different research teams may use different types of visual features in their experiments. Thus there is an urgent need to provide benchmark work to assess the real performance of different types of visual features and kernels for various image classification tasks. In this paper, we have benchmarked multiple approaches for feature extraction and image similarity characterization, so that some useful guidelines can be provided for: (a) how to select more effective approach for feature extraction and enhance the discrimination power of various types of visual features; and (b) how to combine multiple types of visual features and their kernels to enhance the discrimination power of SVM image classifiers. Our experiments on large-scale image collections have also obtained very positive results.

To crawl large amounts of weakly-tagged images for computer vision tasks such as object detection and scene recognition, it is very important to develop new techniques for tag cleansing and word sense disambiguation (i.e., removing irrelevant images from the crawled results). Based on this observation, a topic network is first generated to characterize both the semantic similarity contexts and the visual similarity contexts between the image topics more sufficiently. The topic network is used to represent the classes of objects and scenes of interest. Second, both the visual similarity contexts between the images and the semantic similarity contexts between their tags are integrated for tag cleansing and word sense disambiguation. By addressing the issues of polysemes and synonyms more effectively, our word sense disambiguation algorithm can determine the relevance between the images and the associated tags more precisely, and thus it can allow us to crawl large-scale weakly-tagged images for computer vision tasks.

Detecting the correct orientation of document images is an important step in large scale digitization processes, as most subsequent document analysis and optical character recognition methods assume upright position of the document page. Many methods have been proposed to solve the problem, most of which base on ascender to descender ratio computation. Unfortunately, this cannot be used for scripts having no descenders nor ascenders. Therefore, we present a trainable method using character similarity to compute the correct orientation. A connected component based distance measure is computed to compare the characters of the document image to characters whose orientation is known. This allows to detect the orientation for which the distance is lowest as the correct orientation. Training is easily achieved by exchanging the reference characters by characters of the script to be analyzed. Evaluation of the proposed approach showed accuracy of above 99% for Latin and Japanese script from the public UW-III and UW-II datasets. An accuracy of 98.9% was obtained for Fraktur on a non-public dataset. Comparison of the proposed method to two methods using ascender / descender ratio based orientation detection shows a significant improvement.

Multiphase pumping is essentially a means of adding energy to the unprocessed effluent which enables the liquid and gas mixture to be transported over a long distances without prior separation. A reduction, consolidation, or elimination of the production infrastructure, such as separation equipments and offshore platforms can be developed more economically. Also it successfully lowed the backpressure of wells, revived dead wells and improved the production and efficiency of oilfield. This paper reviews the issues related to indoor performance test and an oilfield application of the helico-axial multiphase pump designed by China University of Petroleum (Beijing). Pump specification and its hydraulic design are given. Results of performance testing under different condition, such as operational speed and gas volume fraction (GVF) etc are presented. Experimental studies on combination of theoretical analysis showed the multiphase pump satisfies the similitude rule, which can be used in the development of new MPP design and performance prediction. Test results showed that rising the rotation speed and suction pressure could better its performance, pressure boost improved, high efficiency zone expanding and the flow rate related to the optimum working condition increased. The pump worked unstable as GVF increased to a certain extent and slip occurred between two phases in the pump, creating surging and gas lock at a high GVF. A case of application in Nanyang oilfield is also studied.

With a wide use of vector maps, the copyright issue is educing an increasing importance and attracting focus on the transmission and the exchange of the vector maps through a network environment. This paper discusses a feature nodes based watermarking method (FNBW) towards keeping robustness and high accuracy of digital map based on SVG and GML format. The digital map treats as a set of curves in the embedding algorithm, and each curve was divided up into several shorter curves under two given thresholds. And then a watermark bit combined with user certificate was embedded into each segment around the feature nodes with the maximum curvature in the segment series nodes. To extract the watermark, all watermark nodes were calculated and searched for in the watermarked map with the Watermark node Searching Algorithm by using the original map. Finally the method calculates the similarity between the original watermark bits and the extracted ones, and determines whether the watermark exists or not. As the experiment result shown, the method not only guarantees the accuracy of vector map but also possesses the good robustness, such as it gives 1.00 similarity under no attack or only geometric transformation with the map; And the anticopping ability is also good enough to give a more than 0.87 similarity for the map cropped 80%. In addition, the method has the full ability of anti-compression lossless methods and good ability to the loss approaches. And an experiment curve of the similarity threshold was given in the paper, which helped to control the anti-attack ability of the watermark and set parameters for an automatic procedure of watermark detection.

In this paper, we propose an ICA-based approach for assessing image quality. Independent component analysis (ICA), which is a kind of fundamental statistical model for natural images, could model images as linear superpositions of basis images. The features given by ICA are suitable for image quality assessment because they resemble the representation given by simple-cells in the mammalian primary visual cortex. The steps of the proposed approach are listed concisely as follows: estimation of basis images in the ICA model; image features extraction from reference images and their corresponding distorted images; calculation of image quality scores or scales. Our experimental results show that the proposed method could achieve competitive performance with other two typical models, Structure SIMilarity (SSIM) and Visual Information Fidelity (VIF) by being tested on LIVE Subjective database. Some factors that may influence the performance results, such as the size of sliding window, the total number of image patches, are also discussed.

A correlation algorithm for scene matching by using two intensity features, i.e., gray level and gradient magnitude, is proposed. The correlation surface produced by the algorithm is the simple summation of the two ones obtained by using gray level and gradient magnitude respectively with zero mean normalized cross correlation similarity measure. We show that theoretically the proposed method will give better matching performance compared to the correlation algorithm by either gray level or gradient magnitude only under some conditions. Experimental results with real images demonstrate that the new algorithm can even report better results than classical algorithms and some newly presented ones.

Although change detection of image objects has good future in military and civil area, effective application in fact is still a difficult problem. This paper denotes the course of change detection by a united structure in different areas firstly. At the same time, the author analyzes similarities and differences as well as bottleneck of several key steps under united structure detailedly on the basis of different backgrounds and applications, and puts forward resolved method and improved algorithms, which enhances understanding and application for kinds of change detection algorithms. Finally, the author prospects several advice of future research and application on change detection of image objects.

CBIR (Content-Based Image Retrieval), which includes feature selection, feature extraction, similarity measurement and user feedback parts, often uses feedback to improve the retrieval accuracy. But there are two problems of Feedback: 1) improving the retrieval accuracy, but also increasing the user's operation complexity; 2) it is not easy to confirm the weight values of each feature in similarity measurement. In this paper, a feedforward idea from Control Theory was used in CBIR system. The method is to select an obvious feature automatically from multi-features, and then give a higher weight value to the obvious feature in the similarity measurement. Experiment results show that the method presented is efficient in image retrieval based on feedforward idea.

A new image fusion method based on intuitionistic fuzzy clustering is proposed in this paper. In this method, two multisource images are decomposed firstly by multiwavelet filter groups. Secondly, intuitionistic fuzzy similarity is used to cluster the decomposing sub-images respectively. Thirdly, decomposition coefficients of fused image are formed according to the clustering results. The experimental results show that there is a noticeable improvement in the information and visual quality of the fused images.

Building recognition is an important field in computer vision. Building target line features which represent the target geometry information are stable features in infrared images. In this paper, the stable building line features are acquired by morphology filter algorithm and the number of the correctly obtained line features and the distance similarities of these features are used to measure the probability of the target emerge in the infrared image. From the recognition results, we can see that our algorithm can efficiently recognize this kind of targets.

Spatial similarity relations are put forward with the introduction of automated map generalization in the construction of multi-scale map databases; then the definition of spatial similarity relations is presented and the concept of spatial similarity degree is given. Finally a classification system for spatial similarity relations in multi-scale map spaces is discussed in detail. This research may be useful to automated map generalization, spatial similarity retrieval and spatial reasoning.

Agricultural regionalization, which is largly achieved according to the similarity within a certain area and the difference between this area and other ones, is the foundation of agricultural production. Due to the fact that clustering is much like regionalization, methods for clustering are also commonly used in regionalization. However, the clustering algorithms applied are usually for only numerical attributes and large amounts of categorical data with great values cannot be handled with traditional clustering methods, which largely limits the utilization of clustering in agricultural regionalization. In this paper, we propose a new spatial clustering algorithm which combines the ROCK algorithm with fuzzy mathematics, can handle both numerical and categorical data at the same time, to satisfy the actual needs of agriculture regionalization. The effectiveness of the new algorithm is tested on the agricultural regionalization of ZengCheng, GuangZhou, China. During the test, we test both the effectiveness of the new spatial clustering algorithm and some old algorithms. The final result shows that the new algorithm performs better in agricultural regionalization, and its result is also closer to the artificial agricultural regionalization.

In this paper we discuss a novel patch-based framework for image denoising through local geometric representations of an image. We learn local data adaptive bases that best capture the underlying geometric information from noisy image patches. To do so we first identify regions of similar structure in the given image and group them together. This is done by the use of meaningful features in the form of local kernels that capture similarities between pixels in a neighborhood. We then learn an informative basis (called a dictionary) for each cluster that best describes the patches in the cluster. Such a data representation can be achieved by performing a simple principal component analysis (PCA) on the member patches of each cluster. The number of principal components to consider in a particular cluster is dictated by the underlying geometry captured by the cluster and the strength of the corrupting noise. Once a dictionary is defined for a cluster, each patch in the cluster is denoised by expressing it as a linear combination of the dictionary elements. The coefficients of such a linear combination for any particular patch is determined in a regression framework using the local dictionary for the cluster. Each step of our method is well motivated and is shown to minimize some cost function. We then present an iterative extension of our algorithm that results in further performance gain. We validate our method through experiments with simulated as well as real noisy images. These indicate that our method is able to produce results that are quantitatively and qualitatively comparable to those obtained by some of the recently proposed state of the art denoising techniques.

A new approach is presented for obtaining feature matching based on the identified features from images. Features which are described by high-dimension vectors are first extracted from a set of reference images and stored in a database, then the correspondence between similar features from different images are established by introducing the notion of a Min-cost K-flow Problem (MKP), which consists in finding a min-cost flow subject to the constraint that the flow value is K. The similarity function, which characterizes these vector components, can avoid the errors that come from different metrics of vectors. Finally, the K-flow is checked to reject ambiguous correspondence bi-directionally and automatically in accordance with the ratio of the matching cost. Experiments on three image sets demonstrate encouraging results.

We are interested in the problem of curve identification, motivated by problems in handwriting recognition. Various geometric approaches have been proposed, with one of the most popular being "elastic matching." We examine the problem using distances defined by inner products on functional spaces. In particular we examine the Legendre and Legendre-Sobolev inner products. We show that both of these can be computed in online constant time. We compare both with elastic matching and conclude that the Legendre-Sobolev distance measure provides a competitive alternative to elastic matching, being almost as accurate and much faster.

The assessment of image quality is very important for numerous image processing applications, where the goal of image quality assessment (IQA) algorithms is to automatically assess the quality of images in a manner that is consistent with human visual judgment. Two prominent examples, the Structural Similarity Image Metric (SSIM) and Multi-scale Structural Similarity (MS-SSIM) operate under the assumption that human visual perception is highly adapted for extracting structural information from a scene. Results in large human studies have shown that these quality indices perform very well relative to other methods. However, the performance of SSIM and other IQA algorithms are less effective when used to rate amongst blurred and noisy images. We address this defect by considering a three-component image model, leading to the development of modified versions of SSIM and MS-SSIM, which we call three component SSIM (3-SSIM) and three component MS-SSIM (3-MS-SSIM). A three-component image model was proposed by Ran and Farvardin, [13] wherein an image was decomposed into edges, textures and smooth regions. Different image regions have different importance for vision perception, thus, we apply different weights to the SSIM scores according to the region where it is calculated. Thus, four steps are executed: (1) Calculate the SSIM (or MS-SSIM) map. (2) Segment the original (reference) image into three categories of regions (edges, textures and smooth regions). Edge regions are found where a gradient magnitude estimate is large, while smooth regions are determined where the gradient magnitude estimate is small. Textured regions are taken to fall between these two thresholds. (3) Apply non-uniform weights to the SSIM (or MS-SSIM) values over the three regions. The weight for edge regions was fixed at 0.5, for textured regions it was fixed at 0.25, and at 0.25 for smooth regions. (4) Pool the weighted SSIM (or MS-SSIM) values, typically by taking their weighted average, thus defining a single quality index for the image (3-SSIM or 3-MS-SSIM). Our experimental results show that 3-SSIM (or 3-MS-SSIM) provide results consistent with human subjectivity when finding the quality of blurred and noisy images, and also deliver better performance than SSIM (and MS-SSIM) on five types of distorted images from the LIVE Image Quality Assessment Database.

This work deals with a novel adaptive parcel-based method for change detection in long time series of SAR images. The proposed technique considers two temporal series of SAR images acquired over the same geographical area in different periods and is based on the following 3 steps: a) adaptive modeling of the geometry of multitemporal SAR sequences according to the generation of spatio-temporal homogeneous regions (i.e., spatio-temporal parcels); b) comparison of series according to a parcel-based similarity measure (e.g., the Kullback-Leibler distance); and c) change-detection map generation according to thresholding. Parcels result in a proper modeling of complex spatial-temporal phenomena in the scene as well as borders and details of the changed areas. The use of similarity measures between long temporal series allows one capturing the complexity of multitemporal data involving statistics of different order. Experiments carried out on two sequences of ERS-1/ERS-2 SAR data confirmed the effectiveness of the proposed approach.

Some non conventional methods of model identification based on data normalization are presented in the article. The method of Data Normalization can be effectively used in those fields of industry optical engineers and technology processing of optical signals, which suffer from factual difficulties while gathering experimental data. The named method helps to receive information about some tendencies and regularities in process and objects dynamics, identify similarities and differences of their structure, their quantitative estimations, to provide the statistical explanation of experimental data and real-time analysis.© (2008) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.

For multi-sensor registration, previous techniques typically use mutual information (MI) rather than the sum-of-the-squared difference (SSD) as the similarity measure. However, the optimization of MI is much less straightforward than is the case for SSD-based algorithms. A new technique for image registration has recently been proposed that uses an information theoretic measure called the Cross-Cumulative Residual Entropy (CCRE). In this paper we show that using CCRE for multi-sensor registration of remote sensing imagery provides an optimization strategy that converges to a global maximum with significantly less iterations than existing techniques and is much less sensitive to the initial geometric disparity between the two images to be registered.

Hyperspectral images provide scientists and engineers with the capability of precise material identification in remote sensing applications. One can leverage this data for precise track identification (ID) and incorporate the high-confidence ID in the tracking process. Our previous work demonstrates that hyperspectral-aided tracking outperforms kinematic-only tracking where multiple ambiguous situations exist. We develop a novel gating concept for hyperspectral measurements, similar in concept to the gating of the Mahalanobis distance computed from the Kalman residuals. Our spectral gating definition is based on the distance between the spectral distribution of the class ID of a track and the spectral distribution of the class ID resulting from the classification of a measurement. We further incorporate the distance between each class distribution (in spectral space) in the track association portion of our hyperspectral-aided tracker. Since functional forms of the joint probability distribution function do not exist, similarity measures such as the Kullback-Leibler divergence or Bhattacharyya distance cannot be used. Instead, we compute all pair-wise distances between all samples of the two classes and then summarize these distances in a meaningful way. This article presents our novel spectral gating approach and its use in track association. It further explores different similarity measures and their effect on spectral gating and track association.

We tested the saliency of a single vibrotractile target (T) among 2 to 7 nontargets (N), presented by 8 tactors that were equally distributed over a horizontal band around the torso. Targets and nontargets had different pulse duration, but the same activation period and no onset asynchrony. T-N similarity was varied by changing the difference between T and N pulse duration. For target present trials the response times increased with the number of stimulus items for all conditions tested, suggesting a serial discrimination process. For target absent trials the response times were independent of the number of stimulus items, suggesting a parallel discrimination process. We found no effect of T-N similarity and no search asymmetry. The present results suggest that tactile target search is not comparable to visual search.

In this paper we introduce and test a new similarity measure for use in a template matching process for target detection and recognition. The measure has recently been developed for multi-modal registration of medical images and is known as phase mutual information (PMI). The key advantage of PMI is that it is invariant to lighting conditions, the ratio between foreground and background intensity and the level of background clutter, which is critical for target detection and recognition from the surveillance images acquired from va rious sensors. Several experiments were conducted using real and synthetic datasets to evaluate the performance of PMI when compared with a number of commonly used similarity measures including mean squared difference, gradient error and intensity mutual information. Our results show that PMI consistently provided the most accu rate detection and recognition performance. Keywords: target recognition, phase mutual information, remote sensing, complex wavelets

The issues of applying facial recognition at significant distances are non-trivial and often subtle. This paper summarizes 7 years of effort on Face at a distance, which for us is far more than a fad. Our effort started under the DARPA Human Identification at a Distance (HID) program. Of all the programmers under HID, only a few of the efforts demonstrated face recognition at greater than 25ft and only one, lead by Dr. Boult, studied face recognition at distances greater than 50 meters. Two issues were explicitly studied. The first was atmospherics/weather, which can have a measurable impact at these distances. The second area was sensor issues including resolution, field-of-view and dynamic range. This paper starts with a discussion and some of results in sensors related issues including resolution, FOV, dynamic range and lighting normalization. It then discusses the "Photohead" technique developed to analyze the impact of weather/imaging and atmospherics at medium distances. The paper presents experimental results showing the limitations of existing systems at significant distance and under non-ideal weather conditions and presents some reasons for the weak performance. It ends with a discussion of our FASSTTM (failure prediction from similarity surface theory) and RandomEyesTM approaches, combined into the FIINDERTM system and how they improved FAAD.

The use of Fisher ratio (FR) algorithm to predict a pattern in an input seen has been applied in several applications in the literature with different success rate, depending on how close is the similarity of the statistical parameters between the background and the patterns. We propose a modification to the FR ratio algorithm that is dependent on the probability density function (PDF). The modified PDF-FR algorithm provides good improvements over that of the PDF used alone. We further enhance the performance of the PDF-FR using polarization-enhanced imagery.

This paper considers the applicability of algorithms, constraint solving and active structure across the spectrum of complexity of information fusion applications. Information fusion is recast as a cognitive application using dynamic structure building and constraint reasoning. The similarity between situation awareness and an undirected structure responding to change is highlighted. The efficiency and speed of operation of cognitive information fusion are touched on. A tsunami warning system provides an example which involves multiple threat and demonstrates the difference between segmented algorithms making decisions without context, and the active use of knowledge.

Reliable segmentation of the liver has been acknowledged as a significant step in several computational and diagnostic processes. While several methods have been designed for liver segmentation, comparative analysis of reported methods is limited by the unavailability of annotated datasets of the abdominal area. Currently available generic data-sets constitute a small sample set, and most academic work utilizes closed datasets. We have collected a dataset containing abdominal CT scans of 50 patients, with coordinates for the liver boundary. The dataset will be publicly distributed free of cost with software to provide similarity metrics, and a liver segmentation technique that uses Markov Random Fields and Active Contours. In this paper we discuss our data collection methodology, implementation of similarity metrics, and the liver segmentation algorithm.

Multivariate images are now commonly produced in many applications. If their process is possible due to computers power and new programming languages, theoretical difficulties have still to be solved. Standard image analysis operators are defined for scalars rather than for vectors and their extension is not immediate. Several solutions exist but their pertinence is hardly linked to context. In the present paper we are going to get interested in segmentation of vector images also including a priori knowledge. The proposed strategy combines a decision procedure (where points are classified) and an automatic segmentation scheme (where regions are properly extracted). The classification is made using a Bayesian classifier. The segmentation is computed via a region growing method: the morphological Watershed transform. A direct computation of the Watershed transform on vector images is not possible since vector sets are not ordered. So, the Bayesian classifier is used for computing a scalar distance map where regions are enhanced or attenuated depending on their similitude to a reference shape: the current distance is the Mahalanobis distance. This combination allows to transfer the decision function from pixels to regions and to preserve the advantages of the original Watershed transform defined for scalar functions. The algorithm is applied for segmenting colour images (with a priori) and medical images, especially dermatology images where skin lesions have to be detected.

Natural images are meaningful to humans — the physical world exhibits statistical regularities that permit the human visual system (HVS) to infer useful interpretations. These regularities communicate the visual structure of the physical world and govern the statistics of images (image structure). A signal processing framework is sought to analyze image characteristics for a relationship with human interpretation. This work investigates the first step toward an objective visual information evaluation: predicting the recognition threshold of different image representations. Given a image sequence, whose images begin as unrecognizable and are gradually refined to include more information according to some measure, the recognition threshold corresponds to first the image in the sequence in which an observer accurately identifies the content. Sequences are produced using two types of image representations: signal-based and visual structure preserving. Signal-based representations add information as dictated by conventional mathematical characterizations of images based on models of low-level HVS processing and use basis functions as the basic image components. Visual structure preserving representations add information to images attributed to visual structure and attempt to mimic higher-level HVS processing by considering the scene’s objects as the basic image components. An experiment is conducted to identify the recognition threshold image. Several full-reference perceptual quality assessment algorithms are evaluated in terms of their ability to predict the recognition threshold of different image representations. The cross-correlation component of a modified version of the multi-scale structural similarity (MS-SSIM) metric, denoted MS-SSIM*, exhibits a better overall correlation with the signal-based and visual structure preserving representations’ average recognition thresholds than the standard MS-SSIM cross-correlation component. These findings underscore the significance of visual structure in recognition and advocate a multi-scale image structure analysis for a rudimentary evaluation of visual information.

Artifact-metrics is an automated method of authenticating artifacts based on a measurable intrinsic characteristic. Intrinsic characters, such as microscopic random-patterns made during the manufacturing process, are very difficult to copy. A transmitted light image of the distribution can be used for artifact-metrics, since the fiber distribution of paper is random. Little is known about the individuality of the transmitted light image although it is an important requirement for intrinsic characteristic artifact-metrics. Measuring individuality requires that the intrinsic characteristic of each artifact significantly differs, so having sufficient individuality can make an artifact-metric system highly resistant to brute force attack. Here we investigate the influence of paper category, matching size of sample, and image-resolution on the individuality of a transmitted light image of paper through a matching test using those images. More concretely, we evaluate FMR/FNMR curves by calculating similarity scores with matches using correlation coefficients between pairs of scanner input images, and the individuality of paper by way of estimated EER with probabilistic measure through a matching method based on line segments, which can localize the influence of rotation gaps of a sample in the case of large matching size. As a result, we found that the transmitted light image of paper has a sufficient individuality.

In this work, a novel approach for restoration of Color faded images is presented. A Uniform fading model is assumed. The algorithm comprises of matching the blocks in the image with some predefined reference blocks. These reference blocks are used to represent the true color of objects. The Correlation Coefficient is used as a measure for similarity matching. The threshold used for determining the matching is chosen adaptively from the image itself. A fade detection algorithm is proposed for distinguishing color faded images from the images with true cast. The algorithm has been tested and validated over a number of image sequences.

We propose a document categorization method based on a document model that can be defined externally for each task and that categorizes Web content or business documents into a target category in accordance with the similarity of the model. The main feature of the proposed method consists of two aspects of semantics extraction from an input document. The semantics of terms are extracted by the semantic pattern analysis and implicit meanings of document substructure are specified by a bottom-up text clustering technique focusing on the similarity of text line attributes. We have constructed a system based on the proposed method for trial purposes. The experimental results show that the system achieves more than 80% classification accuracy in categorizing Web content and business documents into 15 or 70 categories.