2D Histogram Research Articles

An optimum multi-level image thresholding segmentation using non-local means 2D histogram and exponential Kbest gravitational search algorithm

Multi-level image thresholding segmentation divides an image into multiple non-overlapping regions. This paper presents a novel two-dimensional (2D) histogram-based segmentation method to improve the efficiency of multi-level image thresholding segmentation. In the proposed method, a new non-local means 2D histogram and a novel variant of gravitational search algorithm (exponential Kbest gravitational search algorithm) have been used to find the optimal thresholds. Further, for the optimization, a 2D Rényi entropy has been redefined for multi-level thresholding. The proposed method has been tested on the Berkeley Segmentation Dataset and Benchmark (BSDS300) in terms of both subjective and objective assessments. The experimental results affirm that the proposed method outperforms the other 2D histogram-based image thresholding segmentation methods on majority of performance parameters.

Real-time Recognition and Pursuit in Robots Based on 3D Depth Data

In this work, we address the problem of robot pursuit based on a real-time object recognition system with 3D depth sensors. Compared with traditional RGBD data based recognition approaches, we propose a novel global online descriptor designed for object recognition from solely depth data. Proposed descriptor, which we name as Differential Histogram of Normal Vectors (DHONV), is designed to extract the geometric characteristics of the captured 3D surfaces of the objects presented in depth images. In order to obtain a brief description of the visible 3D surfaces of each object, we quantize the differential angles of the surface’s normal vectors into a 1D histogram. The object recognition experiments on a self-collected dataset and a benchmark RGB-D object dataset show that our proposed descriptor outperforms other depth data based descriptors. Moreover, we conducted real-time experiments with RoboCars. Our experiments with RoboCars validate our proposed method capability to perform a real-time recognition and pursuit tasks within indoor environment based solely on depth data.

Quantifying Tensor Field Similarity With Global Distributions and Optimal Transport.

Strain tensor fields quantify tissue deformation and are important for functional analysis of moving organs such as the heart and the tongue. Strain data can be readily obtained using medical imaging. However, quantification of similarity between different data sets is difficult. Strain patterns vary in space and time, and are inherently multidimensional. Also, the same type of mechanical deformation can be applied to different shapes; hence, automatic quantification of similarity should be unaffected by the geometry of the objects being deformed. This work introduces the application of global distributions used to classify shapes and vector fields in the pattern recognition literature, in the context of tensorial strain data. In particular, the distribution of mechanical properties of a field are approximated using a 3D histogram, and the Wasserstein distance from optimal transport theory is used to measure the similarity between histograms. To measure the method's consistency in matching deformations across different objects, the proposed approach was evaluated by sorting strain fields according to their similarity. Performance was compared to sorting via maximum shear distribution (a 1D histogram) and tensor residual magnitude (in perfectly registered objects). The technique was also applied to correlate muscle activation to muscular contraction observed via tagged MRI. The results show that the proposed approach accurately matches deformation regardless of the shape of the object being deformed. Sorting accuracy surpassed 1D shear distribution and was on par with residual magnitude, but without the need for registration between objects.

Asymmetric Cryptosystem for Phase Images in Fractional Fourier Domain Using LU-Decomposition and Arnold Transform

An asymmetric cryptosystem for phase images is proposed which uses amplitude and phase truncation operators in fractional Fourier domain. LU decomposition and Arnold transform are applied to further strengthen the cryptosystem. Analysis of 3D plots, histograms, and correlation distribution reveals that scheme resist the statistical attacks. Basic attacks like chosen plaintext, known plaintext, ciphertext only etc., are endured by virtue of asymmetric nature of cryptosystem. Well-known noise attack is also performed on the scheme. Results indicate that scheme can tolerate the significant noise and reveal information about the input images. Results also show the scheme sensitivity towards the encrypted parameters like orders of fractional Fourier transform and Arnold transform parameter.

Classification of alzheimer's disease subjects from MRI using fuzzy neural network with feature extraction using discrete wavelet transform

Alzheimer's Disease (AD) is a kind of dementia which is tricky to diagnose in accordance with clinical observations. Detection of Alzheimer’s diseases over brain Magnetic Resonance Imaging (MRI) data is main concern in the neurosciences. Traditional assessment of functional image scans typically relies on manual reorientation, visual reading and semi quantitative investigation of certain sections of the brain. Here, proposed Fuzzy Neural Network (FNN) scheme for the purpose of automated multiclass diagnosis of Dementia, in accordance with classification of MRI of human brain. During the initial stage of the work pre-processing is done to get rid of noises. The pre-processing and enhancement scheme includes two steps; initially the removal of film artifacts, for instance, labels and X-ray marks are eliminated from the MRI by means of tracking algorithm. Then, the elimination of high frequency elements by means of Ant Colony based Optimization (ACO) scheme. 2D histogram signal is obtained from preprocessed MR images of brain and subsequently further feature extraction is done through Discrete Wavelet Transform (DWT). This makes use of first few DWT coefficients as features and utilized for the purpose of classification by means of FNN. The features consequently derived are employed for the purpose of training a Fuzzy Neural Network (FNN) to classify features into three classes like Alzheimer’s, Mild Alzheimer's and Huntington's disease. The experimental result shows that the proposed method classification accuracy performance is better than other classification approaches.

Kernel density estimation and its application

Kernel density estimation is a technique for estimation of probability density function that is a must-have enabling the user to better analyse the studied probability distribution than when using a traditional histogram. Unlike the histogram, the kernel technique produces smooth estimate of the pdf, uses all sample points' locations and more convincingly suggest multimodality. In its two-dimensional applications, kernel estimation is even better as the 2D histogram requires additionally to define the orientation of 2D bins. Two concepts play fundamental role in kernel estimation: kernel function shape and coefficient of smoothness, of which the latter is crucial to the method. Several real-life examples, both for univariate and bivariate applications, are shown.

Automatic segmentation of multi-class images with NLS model

In this paper, automatic segmentation of multi-class images problem is considered. The 1D histogram of the multi-class image is approximated using Gaussian functions and the unknown parameters of the Gaussian functions are estimated using Non-linear Least Squares (NLS) optimisation; thereby the problem of segmentation of unknown image class is modelled as an optimisation problem. Further, the parameter estimation accuracy is improved by using the Pearson linear correlation coefficient as a regularisation term of the objective function. The experimental results demonstrate the NLS algorithm ability to estimate the parameters of the Gaussian functions and thereby automatically determine the multi-thresholds for segmentation.

3D histogram of backscatter strength for seafloor substrates classification

3D histogram of backscatter strength for seafloor substrates classification

A novel automated absolute intensity difference based technique for optimal MR brain image thresholding

The traditional Otsu technique for thresholding based on 2D histogram does not give accurate results. A bi-level thresholding case partitions the 2D histogram into four quadrants. This converts the global probability distribution to a probability distribution of two regions only resulting in partial loss of information. The brain regions (white matter (WM), gray matter (GM), cerebrospinal fluid (CSF)) have closely defined gray values, which require the intensity difference information for thresholding. So we propose a novel automated absolute intensity difference based (AIDB) technique for optimal MR brain image thresholding using adaptive coral reef optimization (ACRO). The basic idea is to extract the intensity difference information of the brain image from the 2D histogram matrix. A first-hand objective function, depending on the classical between class variance concepts, is investigated, which is maximized by ACRO. The key achievements of our technique are (i) improved thresholding results, (ii) obtaining more homogenous regions of the image and (iii) obtaining more precise shape of the edges. The proposed technique is tested with one hundred slices of the axial T2 – weighted MR brain images of Harvard medical dataset. The Otsu method for multilevel thresholding using the 2D histogram is considered for a comparison. Several performance measures are considered for the evaluation. It is observed that our technique outperforms the other standard methods.

Gaia Data Release 1

Context: The first Gaia data release (DR1) delivered a catalogue of astrometry and photometry for over a billion astronomical sources. Within the panoply of methods used for data exploration, visualisation is often the starting point and even the guiding reference for scientific thought. However, this is a volume of data that cannot be efficiently explored using traditional tools, techniques, and habits. Aims: We aim to provide a global visual exploration service for the Gaia archive, something that is not possible out of the box for most people. The service has two main goals. The first is to provide a software platform for interactive visual exploration of the archive contents, using common personal computers and mobile devices available to most users. The second aim is to produce intelligible and appealing visual representations of the enormous information content of the archive. Methods: The interactive exploration service follows a client-server design. The server runs close to the data, at the archive, and is responsible for hiding as far as possible the complexity and volume of the Gaia data from the client. This is achieved by serving visual detail on demand. Levels of detail are pre-computed using data aggregation and subsampling techniques. For DR1, the client is a web application that provides an interactive multi-panel visualisation workspace as well as a graphical user interface. Results: The Gaia archive Visualisation Service offers a web-based multi-panel interactive visualisation desktop in a browser tab. It currently provides highly configurable 1D histograms and 2D scatter plots of Gaia DR1 and the Tycho-Gaia Astrometric Solution (TGAS) with linked views. An innovative feature is the creation of ADQL queries from visually defined regions in plots. [abridged]

Lepidic Predominant Pulmonary Lesions (LPL): CT-based Distinction From More Invasive Adenocarcinomas Using 3D Volumetric Density and First-order CT Texture Analysis

This study aimed to differentiate pathologically defined lepidic predominant lesions (LPL) from more invasive adenocarcinomas (INV) using three-dimensional (3D) volumetric density and first-order texture histogram analysis of surgically excised stage 1 lung adenocarcinomas. This retrospective study was institutional review board approved and Health Insurance Portability and Accountability Act compliant. Sixty-four cases of pathologically proven stage 1 lung adenocarcinoma surgically resected between September 2006 and October 2015, including LPL (n = 43) and INV (n = 21), were evaluated using high-resolution computed tomography. Quantitative measurements included nodule volume, percent solid volume (% solid), and first-order texture histogram analysis including skewness, kurtosis, entropy, and mean nodule attenuation within each histogram quartile. Binomial logistic regression models were used to identify the best set of parameters distinguishing LPL from INV. Univariate analysis of 3D volumetric density and histogram features was statistically significant between LPL and INV groups (P < .05). Accuracy of a binomial logistic model to discriminate LPL from INV based on size and % solid was 85.9%. With optimized probability cutoff, the model achieves 81% sensitivity, 76.7% specificity, and area under the receiver operating characteristic curve of 0.897 (95% confidence interval, 0.821-0.973). An additional model based on size and mean nodule attenuation of the third quartile (Hu_Q3) of the histogram achieved similar accuracy of 81.3% and area under the receiver operating characteristic curve of 0.877 (95% confidence interval, 0.790-0.964). Both 3D volumetric density and first-order texture analysis of stage 1 lung adenocarcinoma allow differentiation of LPL from more invasive adenocarcinoma with overall accuracy of 85.9%-81.3%, based on multivariate analyses of either size and % solid or size and Hu_Q3, respectively.

Exploring potent ligand for proteins: insights from knowledge-based scoring functions and molecular interaction energies

Two different scoring functions, Hirshfeld fingerprint-based scoring (HFBS) and molecular operating environment (MOE), and the kernel energy method (KEM) along with counterpoise (CP)-corrected approach were used to estimate the binding energies of protein–ligand complexes and tested against a series of inhibitors of human aldose reductase enzyme. The new scoring function, HFBS, is based on Hirshfeld fingerprints, which are 2D histogram plots of the distances from the molecular Hirshfeld surface to the nearest atomic nuclei inside versus outside the surface and are highly sensitive to the immediate environment of the molecule. The Hirshfeld surface plotted over the ligand molecule helped to visualize the contacts with the active site residues and solvents, which were then taken into account for interaction energy calculations. Application of KEM-assisted CP-corrected approach facilitated an efficient way of calculating interaction energies in protein complex systems. Interaction energies calculated using MP2/6-31G(d) level of theory allowed us to rank the ligands by potency. We find that both the KEM-assisted CP-corrected interaction energies and the scoring functions used here predict comparable rankings for the strength of binding of the series of ligands as docked to the active site of the protein, which are also in good agreement with the experimental binding affinities in this case.

Action Recognition Using 3D Histograms of Texture and A Multi-Class Boosting Classifier.

Human action recognition is an important yet challenging task. This paper presents a low-cost descriptor called 3D histograms of texture (3DHoTs) to extract discriminant features from a sequence of depth maps. 3DHoTs are derived from projecting depth frames onto three orthogonal Cartesian planes, i.e., the frontal, side, and top planes, and thus compactly characterize the salient information of a specific action, on which texture features are calculated to represent the action. Besides this fast feature descriptor, a new multi-class boosting classifier (MBC) is also proposed to efficiently exploit different kinds of features in a unified framework for action classification. Compared with the existing boosting frameworks, we add a new multi-class constraint into the objective function, which helps to maintain a better margin distribution by maximizing the mean of margin, whereas still minimizing the variance of margin. Experiments on the MSRAction3D, MSRGesture3D, MSRActivity3D, and UTD-MHAD data sets demonstrate that the proposed system combining 3DHoTs and MBC is superior to the state of the art.

Crop Classification in Satellite Images through Probabilistic Segmentation Based on Multiple Sources.

Classification methods based on Gaussian Markov Measure Field Models and other probabilistic approaches have to face the problem of construction of the likelihood. Typically, in these methods, the likelihood is computed from 1D or 3D histograms. However, when the number of information sources grows, as in the case of satellite images, the histogram construction becomes more difficult due to the high dimensionality of the feature space. In this work, we propose a generalization of Gaussian Markov Measure Field Models and provide a probabilistic segmentation scheme, which fuses multiple information sources for image segmentation. In particular, we apply the general model to classify types of crops in satellite images. The proposed method allows us to combine several feature spaces. For this purpose, the method requires prior information for building a 3D histogram for each considered feature space. Based on previous histograms, we can compute the likelihood of each site of the image to belong to a class. The computed likelihoods are the main input of the proposed algorithm and are combined in the proposed model using a contrast criteria. Different feature spaces are analyzed, among them are 6 spectral bands from LANDSAT 5 TM, 3 principal components from PCA on 6 spectral bands and 3 principal components from PCA applied on 10 vegetation indices. The proposed algorithm was applied to a real image and obtained excellent results in comparison to different classification algorithms used in crop classification.

Improved shape matching and retrieval using robust histograms of spatially distributed points and angular radial transform

In this paper, the problem of shape based image retrieval is addressed by proposing a hybrid shape descriptor. The proposed descriptor conforms to human visual perception along with its low computational complexity. Since global features are related to the holistic characteristics of images, whereas local features describe the finer details within objects of images, in the proposed hybrid descriptor both global and local features of images are used to describe the entire aspects of image shape. For global features extraction, we use angular radial transform, which is also adopted by MPEG-7 as a region based shape descriptor. On the other hand, for local feature extraction, a novel local descriptor is proposed, which is referred to as histograms of spatially distributed points (HSDP). It is based on two components: radial distance and differential coefficient, which are used to build 2D histograms. Global and local features are combined using effective distance measures viz. Min-Max and Bray-Curtis. Their superiority is validated by experimental results. Apart from that, an extensive range of image databases is employed to assess the performance of the proposed hybrid descriptor. These databases represent several characteristics of shape such as partial occlusion, distortion, subject change, gray scale objects, rotated and noise affected objects, unstructured images, trademarks, blurred images, Corel images, etc. The results of wide range of experiments reveal that the fusion of ART and HSDP significantly improves the image retrieval accuracy and provides a robust and invariant solution for effective shape matching.

A compact discriminant hierarchical clustering approach for action recognition

In order to improve the accuracy of action recognition, a compact discriminant hierarchical clustering approach and an action recognition new framework are respectively proposed. Firstly, on the bases of low-level features 3D Self-Correlation Histogram of Oriented Gradient in Trajectory (3D_SCHOGT) and 3D Self-Correlation Histogram of Oriented Optical Flow in Trajectory (3D_SCHOOFT), the mid-level semantics possessing purity, representativeness and discriminativeness simultaneously are obtained using the proposed compact discriminant hierarchical clustering approach, in which removal of singularities, quantitative evaluations of purity, representativeness and discriminativeness, as well as additive constraint of information entropies for clusters are conducted respectively to assure the better purity, representativeness and discriminativeness. Secondly, by introducing category constraint, a discriminant classification model of Category Constraint Latent Support Vector Machines (CC-LSVM) is proposed, which enhances the discriminative ability of classifier. Finally, to further improve the accuracy of action recognition, a new framework is proposed, which introduces low-level features, mid-level semantics and mid-level semantic self-correlation features into the proposed CC-LSVM classifier in a weighted association way, makes full use of category information of actions, and mines the correlations between multi-semantic features and action categories. Consequently, the action recognition accuracy is improved. The accuracies on Weizmann, KTH, UCF-Sports and YouTube datasets are 100%, 98.83%, 98.67% and 90.73% respectively, which outperform all those in contrastive methods. Experiments demonstrate the effectiveness of proposed compact discriminant hierarchical clustering approach and new framework.

Association between maternal circulating 25 hydroxyvitamin D concentration and placental volume in the first trimester

Objectives: We aimed to assess placental volume and placental mean gray value in vitamin D deficiency and healthy placentas in the first trimester of pregnancy using three-dimensional (3D) ultrasonography (USG) and Virtual Organ Computer-aided Analysis (VOCAL).Methods: This prospective cross sectional study comprised 274 patients, divided into two groups according to the presence or absence of vitamin D deficiency (<20 ng/ml deficient, n = 153, >20 ng/ml not deficient, n= 121) in the first trimester of pregnancy. Placental volume and placental volumetric mean gray values were evaluated. Placental volume (cm3) was analyzed using the VOCAL imaging program and a 3D histogram was used to calculate the volumetric mean gray value (%).Results: Placental volume was significantly less in the vitamin D deficiency group (p = 0.017) Volumetric mean gray value of the placenta was significantly higher in the vitamin D deficiency group (p= 0.003). Maternal serum PAPP-A (MoM) and f-β Hcg (MoM) were significantly lower in the vitamin D deficiency group (p= 0.008, p = 0.003, respectively). In linear regression analyses, serum vitamin D concentration was significantly associated with the plasental volume (β = 0.16; p = 0.01).Conclusion: Placental configuration and development were associated with vitamin D even in the first trimester of pregnancy. To ensure healthy pregnancy outcomes, vitamin D screening applied in the early stages of pregnancy or even before pregnancy.

Image feature representation with orthogonal symmetric local weber graph structure

Image feature representation is a hot topic in the computer vision field. Inspired by Weber's law and local graph structure (LGS), we propose a novel image feature representation descriptor, called orthogonal symmetric local weber graph structure (OSLWGS). It contains two components: differential excitation pattern (DEP) and orthogonal symmetric LGS (OSLGS). In particular, DEP is extended by bringing difference of Gaussian (DoG), which can make OSLWGS robust to image noise. In addition, OSLGS can overcome some defects of LGS including non-symmetric and single horizontal structure problems. Furthermore, 2D OSLWGS histogram is generated by fusing DEP and OSLGS to improve the discriminative power and obtain more precise image description. And then, it is further encoded into 1D histogram and classified via sparse representation. Extensive experiments on FERET, CMUPIE, LFW, Yale B, simulated YALE partial occlusion, RawFooT and PhoTex databases validate the effectiveness of the proposed OSLWGS. Experimental results demonstrate that the proposed algorithm is an efficient and robust method compared with some state-of-the-art approaches.

Bandgap Inhomogeneity of a PbSe Quantum Dot Ensemble from Two-Dimensional Spectroscopy and Comparison to Size Inhomogeneity from Electron Microscopy

Femtosecond two-dimensional Fourier transform spectroscopy is used to determine the static bandgap inhomogeneity of a colloidal quantum dot ensemble. The excited states of quantum dots absorb light, so their absorptive two-dimensional (2D) spectra will typically have positive and negative peaks. It is shown that the absorption bandgap inhomogeneity is robustly determined by the slope of the nodal line separating positive and negative peaks in the 2D spectrum around the bandgap transition; this nodal line slope is independent of excited state parameters not known from the absorption and emission spectra. The absorption bandgap inhomogeneity is compared to a size and shape distribution determined by electron microscopy. The electron microscopy images are analyzed using new 2D histograms that correlate major and minor image projections to reveal elongated nanocrystals, a conclusion supported by grazing incidence small-angle X-ray scattering and high-resolution transmission electron microscopy. The absorption bandgap inhomogeneity quantitatively agrees with the bandgap variations calculated from the size and shape distribution, placing upper bounds on any surface contributions.

Optimal bladder filling during high-dose-rate intracavitary brachytherapy for cervical cancer: a dosimetric study.

PurposeThe aim of this study is to compare 3D dose volume histogram (DVH) parameters of bladder and other organs at risk with different bladder filling protocol during high-dose-rate intracavitary brachytherapy (HDR-ICBT) in cervical cancer, and to find optimized bladder volume.Material and methodsThis dosimetric study was completed with 21 patients who underwent HDR-ICBT with computed tomography/magnetic resonance compatible applicator as a routine treatment. Computed tomography planning was done for each patient with bladder emptied (series 1), after 50 ml (series 2), and 100 ml (series 3) bladder filling with a saline infusion through the bladder catheter. Contouring was done on the Eclipse Planning System. 7 Gy to point A was prescribed with the standard loading patterns. Various 3D DVH parameters including 0.1 cc, 1 cc, 2 cc doses and mean doses to the OAR’s were noted. Paired t-test was performed.ResultsThe mean (± SD) bladder volume was 64.5 (± 25) cc, 116.2 (± 28) cc, and 172.9 (± 29) cc, for series 1, 2, and 3, respectively. The 0.1 cm3,1 cm3, 2 cm3 mean bladder doses for series 1, series 2, and series 3 were 9.28 ± 2.27 Gy, 7.38 ± 1.72 Gy, 6.58 ± 1.58 Gy; 9.39 ± 2.28 Gy, 7.85 ± 1.85 Gy, 7.05 ± 1.59 Gy, and 10.09 ± 2.46 Gy, 8.33 ± 1.75 Gy, 7.6 ± 1.55 Gy, respectively. However, there was a trend towards higher bladder doses in series 3. Similarly, for small bowel dose 0.1 cm3, 1 cm3, and 2 cm3 in series 1, 2, and 3 were 5.44 ± 2.2 Gy, 4.41 ± 1.84 Gy, 4 ± 1.69 Gy; 4.57 ± 2.89 Gy, 3.78 ± 2.21 Gy, 3.35 ± 2.02 Gy, and 4.09 ± 2.38 Gy, 3.26 ± 1.8 Gy, 3.05 ± 1.58 Gy. Significant increase in small bowel dose in empty bladder (series 1) compared to full bladder (series 3) (p = 0.03) was noted. However, the rectal and sigmoid doses were not significantly affected with either series.ConclusionsBladder filling protocol with 50 ml and 100 ml was well tolerated and achieved a reasonably reproducible bladder volume during cervical brachytherapy. In our analysis so far, there is no significant impact of bladder filling on DVH parameters, although larger bladders tend to have higher doses. Small bowel doses are lesser with higher bladder volumes. Further evaluation and validation are necessary.