Histogram Distance Research Articles

Near Duplicate Image Detecting Algorithm based on Bag of Visual Word Model

In recent years, near duplicate image detecting becomes one of the most important problems in image retrieval, and it is widely used in many application fields, such as copyright violations and detecting forged images. Therefore, in this paper, we propose a novel approach to automatically detect near duplicate images based on visual word model. SIFT descriptors are utilized to represent image visual content which is an effective method in computer vision research field to detect local features of images. Afterwards, we cluster the SIFT features of a given image into several clusters by the K-means algorithm. The centroid of each cluster is regarded as a visual word, and all the centroids are used to construct the visual word vocabulary. To reduce the time cost of near duplicate image detecting process, locality sensitive hashing is utilized to map high-dimensional visual features into low-dimensional hash bucket space, and then the image visual features are converted to a histogram. Next, for a pair of images, we present a local feature based image similarity estimating method by computing histogram distance, and then near duplicate images can be detected. Finally, a series of experiments are constructed to make performance evaluation, and related analyses about experimental results are also given

A method for text line detection in natural images

Text information in natural images is very important to cross-media retrieval, index and understanding. However, its detection is challenging due to varying backgrounds, low contrast between text and non-text regions, perspective distortion and other disturbing factors. In this paper, we propose a novel text line detection method which can detect text line aligned with a straight line in any direction. It is mainly composed of three steps. In the first step, we use the maximal stable extremal region detector with dam line constraint to detect candidate text regions, we then define a similarity measurement between two regions which combines sizes, absolute distance, relative distance, contextual information and color histograms. In the second step, we propose a text line identification algorithm based on the defined similarity measurement. The algorithm firstly searches three regions as the seeds of a line, and then expands to obtain all regions in the line. In the last step, we develop a filter to remove non-text lines. The filter uses a sparse classifier based on two dictionaries which are learned from feature vectors extracted from morphological skeletons of those candidate text lines. A comparative study using two datasets shows the excellent performance of the proposed method for accurate text line detection with horizontal or arbitrary consistent orientation.

Predicting pathologic tumor response to chemoradiotherapy with histogram distances characterizing longitudinal changes in 18F‐FDG uptake patterns

A family of fluorine-18 ((18)F)-fluorodeoxyglucose ((18)F-FDG) positron-emission tomography (PET) features based on histogram distances is proposed for predicting pathologic tumor response to neoadjuvant chemoradiotherapy (CRT). These features describe the longitudinal change of FDG uptake distribution within a tumor. Twenty patients with esophageal cancer treated with CRT plus surgery were included in this study. All patients underwent PET/CT scans before (pre-) and after (post-) CRT. The two scans were first rigidly registered, and the original tumor sites were then manually delineated on the pre-PET/CT by an experienced nuclear medicine physician. Two histograms representing the FDG uptake distribution were extracted from the pre- and the registered post-PET images, respectively, both within the delineated tumor. Distances between the two histograms quantify longitudinal changes in FDG uptake distribution resulting from CRT, and thus are potential predictors of tumor response. A total of 19 histogram distances were examined and compared to both traditional PET response measures and Haralick texture features. Receiver operating characteristic analyses and Mann-Whitney U test were performed to assess their predictive ability. Among all tested histogram distances, seven bin-to-bin and seven crossbin distances outperformed traditional PET response measures using maximum standardized uptake value (AUC = 0.70) or total lesion glycolysis (AUC = 0.80). The seven bin-to-bin distances were: L(2) distance (AUC = 0.84), χ(2) distance (AUC = 0.83), intersection distance (AUC = 0.82), cosine distance (AUC = 0.83), squared Euclidean distance (AUC = 0.83), L(1) distance (AUC = 0.82), and Jeffrey distance (AUC = 0.82). The seven crossbin distances were: quadratic-chi distance (AUC = 0.89), earth mover distance (AUC = 0.86), fast earth mover distance (AUC = 0.86), diffusion distance (AUC = 0.88), Kolmogorov-Smirnov distance (AUC = 0.88), quadratic form distance (AUC = 0.87), and match distance (AUC = 0.84). These crossbin histogram distance features showed slightly higher prediction accuracy than texture features on post-PET images. The results suggest that longitudinal patterns in (18)F-FDG uptake characterized using histogram distances provide useful information for predicting the pathologic response of esophageal cancer to CRT.

Approximate Algorithms for Computing Spatial Distance Histograms with Accuracy Guarantees

Particle simulation has become an important research tool in many scientific and engineering fields. Data generated by such simulations impose great challenges to database storage and query processing. One of the queries against particle simulation data, the spatial distance histogram (SDH) query, is the building block of many high-level analytics, and requires quadratic time to compute using a straightforward algorithm. Previous work has developed efficient algorithms that compute exact SDHs. While beating the naive solution, such algorithms are still not practical in processing SDH queries against large-scale simulation data. In this paper, we take a different path to tackle this problem by focusing on approximate algorithms with provable error bounds. We first present a solution derived from the aforementioned exact SDH algorithm, and this solution has running time that is unrelated to the system size N. We also develop a mathematical model to analyze the mechanism that leads to errors in the basic approximate algorithm. Our model provides insights on how the algorithm can be improved to achieve higher accuracy and efficiency. Such insights give rise to a new approximate algorithm with improved time/accuracy tradeoff. Experimental results confirm our analysis.

Objects Tracking in Images Sequence Using Center-Symmetric Local Binary Pattern (CS-LBP)

In this paper we present a method for objects tracking in images sequence. This approach is achieved into two main steps. In the first one, we constructed the Center-Symmetric Local Binary Pattern (CS-LBP) histogram pattern of each image in the sequence and the reference pattern. In the second one, we perform the algorithm by the pattern selected based on a distance measures to find similarity between two histograms. The maximum CS-LBP histogram distance gives best results than the chi-square one. The proposed approach has been tested on synthetic and real sequence images and the results are satisfactory.

Speech-driven talking face using embedded confusable system for real time mobile multimedia

This paper presents a real-time speech-driven talking face system which provides low computational complexity and smoothly visual sense. A novel embedded confusable system is proposed to generate an efficient phoneme-viseme mapping table which is constructed by phoneme grouping using Houtgast similarity approach based on the results of viseme similarity estimation using histogram distance, according to the concept of viseme visually ambiguous. The generated mapping table can simplify the mapping problem and promote viseme classification accuracy. The implemented real time speech-driven talking face system includes: 1) speech signal processing, including SNR-aware speech enhancement for noise reduction and ICA-based feature set extractions for robust acoustic feature vectors; 2) recognition network processing, HMM and MCSVM are combined as a recognition network approach for phoneme recognition and viseme classification, which HMM is good at dealing with sequential inputs, while MCSVM shows superior performance in classifying with good generalization properties, especially for limited samples. The phoneme-viseme mapping table is used for MCSVM to classify the observation sequence of HMM results, which the viseme class is belong to; 3) visual processing, arranges lip shape image of visemes in time sequence, and presents more authenticity using a dynamic alpha blending with different alpha value settings. Presented by the experiments, the used speech signal processing with noise speech comparing with clean speech, could gain 1.1 % (16.7 % to 15.6 %) and 4.8 % (30.4 % to 35.2 %) accuracy rate improvements in PER and WER, respectively. For viseme classification, the error rate is decreased from 19.22 % to 9.37 %. Last, we simulated a GSM communication between mobile phone and PC for visual quality rating and speech driven feeling using mean opinion score. Therefore, our method reduces the number of visemes and lip shape images by confusable sets and enables real-time operation.

Shape Classification Based on Normalized Distance and Angle Histograms Using PNN

This study presents an attempt to develop a reliable computerized algorithm, which could classify images into predetermined classes. For this purpose, the histogram of the normalized distance between each two points of the image (algorithm I) and the histogram of normalized distances between three points and the normalized angle of the image edge points (algorithm II) are analyzed. The probabilistic neural network (PNN) is implemented to do shape classification. Our proposed approach is tested on ten classes of MPEG-7 image database. It has been shown that feature extraction based on the distance histogram (algorithm I and algorithm II) is efficient due to its potential to preserve interclass and intra-class variation. In addition, these algorithms ensur invariance to geometric transformations (e.g. translation, rotation and scaling). The best classification accuracy is achieved by eight classes with the total accuracy of 90% and 92.5% for algorithm I and algorithm II, respectively. The reported experiment reveal that the proposed classification algorithm could be useful in the study of MPEG-7 shapes.

SU‐E‐J‐75: The Clinical Evaluation of a Minimum Point Distance Histogram for Image Registration in the 4DCT Based Gastric Cancer Radiotherapy

Purpose: The contour‐based evaluation is crucial in the radiotherapy and one popular parameter is the dice similarity coefficient (DSC). The DSC alone is insufficient in some situation and additional evaluation parameters are required. The purpose of this study is to create a minimum point distance histogram (mPDH) for contour‐based deformable image registration evaluation and to investigate the clinical dosimetric endpoints related to the mPDH in organs at risk for gastric patients with 4DCT images. Methods: The mPDH was created and tested in 4DCT images. The 0% phase (P0) and the 50% phase (P5) image data sets from 4DCT of 5 gastric cancer patients with contours delineated by a radiation oncologist were transferred to the VelocityVI image registration package. The contours on the P5 were rigidly transferred (rigid registration) and warped (deformable registration) to the P0. All contours were export to a homemade Matlab program for calculating the mPDH. The mPDHs were obtained for the rigid‐manual (RM) and the deformed‐manual (DM) contours. Furthermore, the original treatment plan was applied to the P0 for dose calculation and the dosimetry‐based investigation related to the mPDH was performed. Results: The mPDH provides a useful data for quantifying the agreement of the contours. The mean DI95%(the distance includes more than 95% of the points) and P3mm (the percent of points within 3mm distance) from mPDH show significant difference between the DM and RM (p<0.05). For dosimetric evaluation, there is no dose check point has difference larger than 3% if the DI95% is within 4mm. Conclusion: A new informative image registration evaluation tool is created. The mPDH provides a useful data for quantifying the agreement of the contours. The clinical validation of mPDH in the gastric cancer shows the feasibility of apply this tool in the radiotherapy for evaluation the clinical accuracy of deformable registration.

Landmark transfer with minimal graph

We present an efficient and robust algorithm for the landmark transfer on 3D meshes that are approximately isometric. Given one or more custom landmarks placed by the user on a source mesh, our method efficiently computes corresponding landmarks on a family of target meshes. The technique is useful when a user is interested in characterization and reuse of application-specific landmarks on meshes of similar shape (for example, meshes coming from the same class of objects). Consequently, across a set of multiple meshes consistency is assured among landmarks, regardless of landmark geometric distinctiveness. The main advantage of our method over existing approaches is its low computation time. Differently from existing non-rigid registration techniques, our method detects and uses a minimum number of geometric features that are necessary to accurately locate the user-defined landmarks and avoids performing unnecessary full registration. In addition, unlike previous techniques that assume strict consistency with respect to geodesic distances, we adopt histograms of geodesic distance to define feature point coordinates, in order to handle the deviation of isometric deformation. This allows us to accurately locate the landmarks with only a small number of feature points in proximity, from which we build what we call a minimal graph. We demonstrate and evaluate the quality of transfer by our algorithm on a number of Tosca data sets.

Robust fragments-based tracking with hue detecting-based template updating

Robust fragments-based tracking cannot update template,so the paper proposed a template updating method based on hue detecting.First,hue histogram distance between template and current target was calculated,and then the distance was compared with the threshold.If the distance is more than the threshold,the template should be fixed in next frames,or the template should be updated every frame.The experimental results on challenging sequences demonstrate the method can track targets when illumination changes as well as improve tracking accuracy.

Restrained-Ensemble Molecular Dynamics Simulations Based on Distance Histograms from Double Electron–Electron Resonance Spectroscopy

DEER (double electron-electron resonance) spectroscopy is a powerful pulsed ESR (electron spin resonance) technique allowing the determination of spin-spin distance histograms between site-directed nitroxide label sites on a protein in their native environment. However, incorporating ESR/DEER data in structural refinement is challenging because the information from the large number of distance histograms is complex and highly coupled. Here, a novel restrained-ensemble molecular dynamics simulation method is developed to incorporate the information from multiple ESR/DEER distance histograms simultaneously. Illustrative tests on three coupled spin-labels inserted in T4 lysozyme show that the method efficiently imposes the experimental distance distribution in this system. Different rotameric states of the χ1 and χ2 dihedrals in the spin-labels are also explored by restrained ensemble simulations. Using this method, it is hoped that experimental restraints from ESR/DEER experiments can be used to refine structural properties of biological systems.

Structural Refinement from Restrained-Ensemble Simulations Based on EPR/DEER Data: Application to T4 Lysozyme

DEER (double electron-electron resonance) is a powerful pulsed ESR (electron spin resonance) technique allowing the determination of distance histograms between pairs of nitroxide spin-labels linked to a protein in a native-like solution environment. However, exploiting the huge amount of information provided by ESR/DEER histograms to refine structural models is extremely challenging. In this study, a restrained ensemble (RE) molecular dynamics (MD) simulation methodology is developed to address this issue. In RE simulation, the spin-spin distance distribution histograms calculated from a multiple-copy MD simulation are enforced, via a global ensemble-based energy restraint, to match those obtained from ESR/DEER experiments. The RE simulation is applied to 51 ESR/DEER distance histogram data from spin-labels inserted at 37 different positions in T4 lysozyme (T4L). The rotamer population distribution along the five dihedral angles connecting the nitroxide ring to the protein backbone is determined and shown to be consistent with available information from X-ray crystallography. For the purpose of structural refinement, the concept of a simplified nitroxide dummy spin-label is designed and parametrized on the basis of these all-atom RE simulations with explicit solvent. It is demonstrated that RE simulations with the dummy nitroxide spin-labels imposing the ESR/DEER experimental distance distribution data are able to systematically correct and refine a series of distorted T4L structures, while simple harmonic distance restraints are unsuccessful. This computationally efficient approach allows experimental restraints from DEER experiments to be incorporated into RE simulations for efficient structural refinement.

Noncooperative bovine iris recognition via SIFT

Iris biometry has been widely used to recognize an individual in a natural and intuitive way. Conventional iris recognition systems transfer iris images to rectangle using polar coordinate after accurate segmentation, and have performed very well on accurate data. However, bovine iris images are usually irregular with respect to inactive participant, and the conventional methods cannot achieve high accuracy and true rotation invariance. In this paper, a new scheme is proposed based on scale invariant feature transform (SIFT) and bag-of-features. Firstly, region-based active contour is used to detect the inner boundary. Secondly, SIFT method is applied to detect the keypoints in the iris image, and points located in pupil region are removed. Then, feature vocabulary is constructed, and histogram representation for each iris image is generated. Finally, histogram distance is adopted for the matching test. Experimental results are provided to show the effectiveness and potential of developed noncooperative iris recognition.

Structure Determination from Disordered Ensembles of Identical Particles

X-ray scattering techniques have long ranked among the most important methods for studying amorphous materials and other highly disordered targets. Well-established X-ray scattering methods often consist of recording time-averaged scattered intensity maps which, under the Born approximation, straightforwardly reveal information about ensemble-averaged, two-point, electron density correlations within the target. In the case of isotropic targets that consist of disordered ensembles of randomly oriented particles, scattering data are typically reduced to a histogram of electron pair distances (the “pair distribution function,” or PDF). While the information contained in the one-dimensional PDF is limited, a rich set of structural properties can often be determined straightforwardly (e.g., radius of gyration, surface area, short-range correlation length scales, fractal dimension). One of the well-known pinnacles of the methodology is the application of small-angle X-ray scattering (SAXS) to solutions of identical biological macromolecules [1–3], which is now routinely used to rapidly determine ab initio low-resolution (>1 nm) protein structures [4].

Atomistic computer modeling of the local structure and mixing properties of a grossular-uvarovite solid solution

An original methodology for the atomistic computer modeling of solid solutions was applied for the study of the mixing properties and local structure of the grossular-uvarovite, i.e., Ca3Al2[SiO4]3 Ca3Cr2][SiO4]3, garnet series. The parameters of the interatomic potentials for end members of this series were optimized using experimental data on their structural, elastic, and thermodynamic characteristics. The optimized model of the potentials allowed us to describe the elastic, structural, and thermodynamic characteristics of grossular and uvarovite and estimate the energy of point defects in these crystal structures. Calculations of the mixing properties and local structure for seven different compositions of the solid solution were carried out on a “Chebyshev” supercomputer (Moscow State University) in a 2 × 2 × 4 supercell of the garnet-type structure containing 2560 atoms. Mixing properties, such as the enthalpy of mixing, parameters of interaction, excess mixing volume, deviation of bulk modulus from additivity, and the vibrational and configuration contribution to the entropy of mixing, were determined. This allowed us to estimate the stability field for the grossular-uvarovite solid solution. Histograms of the interatomic distances M-O (M = Ca, Al, Cr, Si) and O-O in supercells were plotted and the parameters of relaxation and changes of the CrO6 and AlO6 octahedron volumes were estimated. The data of the simulation are quite consistent with the experimental data on this system and supplement it significantly.

Objects Tracking in Images Sequence using Local Binary Pattern (LBP)

this paper we present a method for objects tracking in images sequence. This approach is achieved into two main steps. In the first one, we constructed the Local Binary Pattern (LBP) histogram pattern of each image in the sequence and the reference pattern. In the second one, we perform the algorithm by the pattern selected based on a distance measures to find similarity between two histograms. The maximum LBP histogram distance gives best results than the chi-square one. The proposed approach has been tested on synthetic and real sequence images and the results are satisfactory. Keywordsimage, Computer vision, Tracking, LBP histogram, chi-square distance..

Performance Efficiency of Quantization using HSV Colour Space and Vector Cosine Angle Distance in CBIR with Different Image Sizes

Content Based Image Retrieval (CBIR) is an active research field in the past decades. Against the traditional system where the images are retrieved based on the key word search, CBIR systems retrieve the images based on the visual content. Even though some of the modern systems like relevance feedback system which improves the performance of CBIR systems exists, the importance of retrieving the images based on the low level features like Colour, Texture and Shape still determine the development of CBIR systems and cannot be undermined. Colour Histograms, Histogram Distance Measurements, Colour Spaces and Quantization play an important role in retrieving images based on similarities. In this paper, a novel method is presented for determining the efficiency of different quantization methods using HSV Colour space and measuring the Vector Cosine Angle distance of the images with different sizes of images like 256 X 256, 128 X 128, 64 X 64, 32 X 32, 16 X 16 and 8 X 8 pixels for efficient image retrieval and comparing the time utilized for retrieval in each sizes and measuring the Overall efficiency.

A Contour Representation and Retrieval Algorithm based on Polar-histogram

This paper presents a novel method for contour-based shape retrieval. First, they come from contour points which can represent the shape very well as the object contour points got by contour tracing and denoising. Corner points, sampled points and two vector sets are obtained by leading vectors from each point to the contour centroid point. Then, the polar histogram of directions and distance in the vector sets are used to describe the shape. Finally, it combines the similarity measurement criterion of two contours with the polar histogram of the two feature points. The experiment result shows that our algorithm is efficient and is with better performance in the robustness to the scaling, rotation and translation, compared with the traditional algorithms.

Rotamer Library of Spin Labeled Cysteines Attached to T4 Lysozyme Deduced from Molecular Dynamics Simulations Constrained by Double Electron-Electron Resonance (Deer) Experiments

DEER (Double Electron Electron Resonance) is a powerful pulsed EPR technique allowing the determination of spin-spin distance histograms between side-directed nitroxide label sites on a protein in their native environment. In this study, a novel molecular dynamics simulation method, the restrained ensemble (RE) method, has been used for the refinement of spin labels inserted in T4 Lysozyme (T4L) structures. In the RE method, the spin-spin distance distribution histograms calculated from a multiple-copy molecular dynamics simulations are forced, via a special ensemble-based energy restraint, to match those extracted from 51 EPR/DEER experimental spin-spin pairs. To examine the effect of the restraint on the rotameric state of the spin label at the 37 different sites in T4L, conventional long molecular dynamics (MD) and locally enhanced sampling (LES) simulations were also performed. As expected, the distance histograms obtained from the RE simulations are very similar to those obtained from experiment; however, the distance histograms from conventional long MD and LES simulations deviate from experiment. From the analysis of these simulations, a general trend is found in rotamer population distribution along five dihedral angles connecting the nitroxide ring to the protein backbone. Overall, the rotamer population obtained from the RE simulation agrees with those obtained from x-ray structure. From the analysis of the dynamics of nitroxide atoms in spin label side chains, a force field for a pseudo nitroxide dummy atom has been parameterized. This pseudo nitroxide was used in an RE simulation coupled with the EPR/DEER experimental distance distribution data to refine distorted structures of T4L. Thus, experimental restraints from DEER experiments in conjunction with RE simulations can be used to refine structural propertied of biological systems.

Lane Marking Recognition for Constructing a Multi-information Map

For the lane departure warning system or the lane keeping system, it is important to detect lane lines stably in images from vehicle onboard cameras. We have developed the lane line detection system for platooning. This system can detect various kinds of lane markings stably and robustly because it uses a multi-information map containing road marking information, such as a kind of road marking, the width of a lane line or degree of blur, to detect lane markings. A multi-information map is tied to position data obtained from global positioning system (GPS). Therefore, a vehicle can obtain information about lane markings to detect at the present position from a multi-information map. This paper proposes the method to construct a multi-information map automatically by recognizing road markings in images from an onboard front camera. Input images are transformed to inverse perspective projection images. In these transformed images, seven features, such as the histogram of line angles, the number of corner points, the histogram of a lane line width, the histogram of a lane line height, the histogram of the horizontal distance between markings, the histogram of the vertical distance between markings and the color of a maker, are extracted to discriminate road markings. Experiments conducted in real road scenes show the effectiveness of the proposed method for constructing a multi-information map.