Small Homogeneous Regions Research Articles

Camera model identification based on forensic traces extracted from homogeneous patches

A crucial challenge in digital image forensics is to identify the source camera model used to generate given images. This is of prime importance, especially for Law Enforcement Agencies in their investigations of Child Sexual Abuse Material found in darknets or seized storage devices.In this work, we address this challenge by proposing a solution that is characterized by two main contributions. It relies on the extraction of rather small homogeneous regions that we extract very efficiently from the integral image, and on a hierarchical classification approach with convolutional neural networks as the underlying models. We rely on homogeneous regions as they contain camera traces that are less distorted than regions with high-level scene content. The hierarchical approach that we propose is important for scaling up and making minimal modifications when new cameras are added. Furthermore, this scheme performs better than the traditional single classifier approach. By means of thorough experimentation on the publicly available Dresden data set, we achieve an accuracy of 99.01% with 5-fold cross-validation on the ‘natural’ subset of this data set. To the best of our knowledge, this is the best result ever reported for Dresden data set.

Spectral–Spatial and Superpixelwise PCA for Unsupervised Feature Extraction of Hyperspectral Imagery

As the most classical unsupervised dimension reduction algorithm, principal component analysis (PCA) has been widely used in hyperspectral images (HSIs) preprocessing and analysis tasks. Recently proposed superpixelwise PCA (SuperPCA) has shown promising accuracy where superpixels segmentation technique was first used to segment an HSI to various homogeneous regions and then PCA was adopted in each superpixel block to extract the local features. However, the local features could be ineffective due to the neglect of global information especially in some small homogeneous regions and/or in some large homogeneous regions with mixed ground truth objects. In this article, a novel spectral–spatial and SuperPCA (S <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sup> -PCA) is proposed to learn the effective and low-dimensional features of HSIs. Inspired by SuperPCA we further adopt superpixels-based local reconstruction to filter the HSIs and use the PCA-based global features as the supplement of local features. It turns out that the global–local and spectral–spatial features can be well exploited. Specifically, each pixel of an HSI is reconstructed by the nearest neighbors’ pixels in the same superpixel block, which could eliminate the noise and enhance the spatial information adaptively. After the local reconstruction-based data preprocessing, PCA is performed on each region and the entire HSI to obtain local and global features, respectively. Then we simply concatenate them to get the global–local and spectral–spatial features for HSIs classification. The experimental results on two HSIs data sets demonstrate the superiority of the proposed method over the state-of-the-art methods. The source code of the proposed model is available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/XinweiJiang/S3-PCA</uri> .

Evaluation of ESACCI satellite soil moisture product using in-situ CTCZ observations over India

Recently available European Space Agency Climate Change Initiative (ESACCI) soil moisture dataset, derived by merging soil moisture values calculated using measurements from satellite-based active and passive sensors, is validated over the Indian region using in-situ observations from 117 Continental Tropical Convergence Zone (CTCZ) Programme stations spread across India. The dataset is compared for the monsoon season (June–September: JJAS) of two years – 2011–2012, over six regional domains which differ in soil characteristics and mean soil moisture values, thus taking the spatial heterogeneity into account. Evaluation shows that the mean JJAS ESACCI volumetric soil moisture is 25.5% ( $$\hbox {m}^{3}\,\hbox {m}^{-3}$$ ), with an intra-seasonal standard deviation of 6%. The root mean squared difference (RMSD) between ESACCI soil moisture product and CTCZ observations is 10% over the Indian region. Over smaller homogeneous regions, the RMSD values between the two products are smaller than 5%, except over southern India and north-east India. Overall, the ESACCI soil moisture dataset is in good agreement with the CTCZ in-situ soil moisture observations, and has relatively higher accuracy over the plains of northern and central India, as compared to other regions. However, the ESACCI soil moisture dataset shows higher intra-seasonal variability at shorter time-scale of 2–4 days, as compared to the CTCZ observations, possibly due to the difference in the soil sampling depths between the two datasets.

An effective research for diffusion annealing temperature and activation energy in Au surface-layered Bi-2212 ceramic composites

This study tries to respond two fundamental questions such as (I) what is the role of Au inclusions in the Bi-2212 polycrystalline materials prepared at the diffusion annealing temperature of 600–850 °C on the stabilization of superconductivity in small homogeneous regions and (II) what are the diffusion coefficient and corresponding activation energy of Au inclusions for the Bi-2212 superconducting system. Solution of the former question is in association with the characteristic pairing and coherence transitions extracted from the detailed dc resistivity versus temperature measurements when the latter questions are answered by the change of sample resistivity after the removal of thin-layer from the surface with the aid of the Arrhenius relation for the first time. The experimental measurement results show that the optimum diffusion annealing temperature is observed to be 800 °C where the minor phase, local structural distortions, dislocations, lattice defects and disorders in the Bi-2212 compounds degrade considerably and reach the global minimum points. Similarly, the Josephson coupled energy resides in the maximum value, and thus the superconducting grains become more and more coupled due to the increment in the percolation of intergrains. Moreover, the diffusion coefficient of Au individuals is obtained to increase regularly from 3.6186 × 10−8 to 2.79278 × 10−7 cm2 s−1 with the enhancement in the diffusion annealing temperature. At the same time, the temperature-dependent diffusion coefficient and related activation energy values of Au are computed to be about 2.601 × 10− 6 cm2 s−1 and 1.523 eV, respectively. According to the results calculated, 1.523 eV is the required minimum activation energy for the penetration of Au (heavy metal) ions into the Bi-2212 crystal structure.

Robust Matrix Discriminative Analysis for Feature Extraction From Hyperspectral Images

Linear discriminative analysis (LDA) is an effective feature extraction method for hyperspectral image (HSI) classification. Most of the existing LDA-related methods are based on spectral features, ignoring spatial information. Recently, a matrix discriminative analysis (MDA) model has been proposed to incorporate the spatial information into the LDA. However, due to sensor interferers, calibration errors, and other issues, HSIs can be noisy. These corrupted data easily degrade the performance of the MDA. In this paper, a robust MDA (RMDA) model is proposed to address this important issue. Specifically, based on the prior knowledge that the pixels in a small spatial neighborhood of the HSI lie in a low-rank subspace, a denoising model is first employed to recover the intrinsic components from the noisy HSI. Then, the MDA model is used to extract discriminative spatial–spectral features from the recovered components. Besides, different HSIs exhibit different spatial contextual structures, and even a single HSI may contain both large and small homogeneous regions simultaneously. To sufficiently describe these multiscale spatial structures, a multiscale RMDA model is further proposed. Experiments have been conducted using three widely used HSIs, and the obtained results show that the proposed method allows for a significant improvement in the classification performance when compared to other LDA-based methods.

Region-Based Structure Preserving Nonnegative Matrix Factorization for Hyperspectral Unmixing

Hyperspectral unmixing is one of the most important techniques in the remote sensing image analysis. In recent years, the nonnegative matrix factorization (NMF) method is widely used in hyperspectral unmixing. In order to solve the nonconvex problem of the NMF method, a number of constraints have been introduced into NMF models, including sparsity, manifold, smoothness, etc. However, these constraints ignore an important property of a hyperspectral image, i.e., the spectral responses in a homogeneous region are similar at each pixel but vary in different homogeneous regions. In this paper, we introduce a novel region-based structure preserving NMF (R-NMF) to explore consistent data distribution in the same region while discriminating different data structures across regions in the unmixed data. In this method, a graph cut algorithm is first applied to segment the hyperspectral image to small homogeneous regions. Then, two constraints are applied to the unmixing model, which preserve the structural consistency within the region while discriminating the differences between regions. Results on both synthetic and real data have validated the effectiveness of this method, and shown that it has outperformed several state-of-the-art unmixing approaches.

Deep Learning Approach for Car Detection in UAV Imagery

This paper presents an automatic solution to the problem of detecting and counting cars in unmanned aerial vehicle (UAV) images. This is a challenging task given the very high spatial resolution of UAV images (on the order of a few centimetres) and the extremely high level of detail, which require suitable automatic analysis methods. Our proposed method begins by segmenting the input image into small homogeneous regions, which can be used as candidate locations for car detection. Next, a window is extracted around each region, and deep learning is used to mine highly descriptive features from these windows. We use a deep convolutional neural network (CNN) system that is already pre-trained on huge auxiliary data as a feature extraction tool, combined with a linear support vector machine (SVM) classifier to classify regions into “car” and “no-car” classes. The final step is devoted to a fine-tuning procedure which performs morphological dilation to smooth the detected regions and fill any holes. In addition, small isolated regions are analysed further using a few sliding rectangular windows to locate cars more accurately and remove false positives. To evaluate our method, experiments were conducted on a challenging set of real UAV images acquired over an urban area. The experimental results have proven that the proposed method outperforms the state-of-the-art methods, both in terms of accuracy and computational time.

Shape-Based Building Detection in Visible Band Images Using Shadow Information

This paper introduces a novel methodology for automated detection of buildings from single high-resolution optical images with only visible red, green, and blue bands of data. In particular, we first investigate the shadow evidence to focus on building regions. Then, a novel Markov random field (MRF)-based region growing segmentation technique is proposed. Image is oversegmented into smaller homogeneous regions that can be used to replace the rigid structure of the pixel grid. An iterative classification merging is then applied over this set of regions. At each iteration, regions are classified using a region-level MRF model, then, according to the position of shadows, regions having the same class are merged to produce new regions whose shapes are appropriate to rectangles. The final buildings are determined using a recursive minimum bounding rectangle. The experimental results prove that the proposed method is applicable in various areas (high dense urban, suburban, and rural) and is highly robust and reliable.

A Split-and-Merge-Based Uterine Fibroid Ultrasound Image Segmentation Method in HIFU Therapy.

High-intensity focused ultrasound (HIFU) therapy has been used to treat uterine fibroids widely and successfully. Uterine fibroid segmentation plays an important role in positioning the target region for HIFU therapy. Presently, it is completed by physicians manually, reducing the efficiency of therapy. Thus, computer-aided segmentation of uterine fibroids benefits the improvement of therapy efficiency. Recently, most computer-aided ultrasound segmentation methods have been based on the framework of contour evolution, such as snakes and level sets. These methods can achieve good performance, although they need an initial contour that influences segmentation results. It is difficult to obtain the initial contour automatically; thus, the initial contour is always obtained manually in many segmentation methods. A split-and-merge-based uterine fibroid segmentation method, which needs no initial contour to ensure less manual intervention, is proposed in this paper. The method first splits the image into many small homogeneous regions called superpixels. A new feature representation method based on texture histogram is employed to characterize each superpixel. Next, the superpixels are merged according to their similarities, which are measured by integrating their Quadratic-Chi texture histogram distances with their space adjacency. Multi-way Ncut is used as the merging criterion, and an adaptive scheme is incorporated to decrease manual intervention further. The method is implemented using Matlab on a personal computer (PC) platform with Intel Pentium Dual-Core CPU E5700. The method is validated on forty-two ultrasound images acquired from HIFU therapy. The average running time is 9.54 s. Statistical results showed that SI reaches a value as high as 87.58%, and normHD is 5.18% on average. It has been demonstrated that the proposed method is appropriate for segmentation of uterine fibroids in HIFU pre-treatment imaging and planning.

Building damage assessment after the earthquake in Haiti using two post-event satellite stereo imagery and DSMs

In this article, a novel after-disaster building damage monitoring method is presented. This method combines the multispectral imagery and digital surface models (DSMs) from stereo matching of two dates to obtain three kinds of changes: collapsed buildings, newly built buildings and temporary shelters. The proposed method contains three basic steps. The first step is to focus on the DSMs and orthorectified images preparation. The second step is to segment the panchromatic images in obtaining small homogeneous regions. In the last step, a rule-based classification is built on the change information from iteratively reweighted multivariate alteration detection (IR-MAD) and height to extract the three kinds of changes. To further improve the accuracy of the results, a region-based grey-level co-occurrence matrix texture measurement is used. The proposed method is applied to monitor building changes after the 2010 Haiti earthquake, and the obtained results are further evaluated both visually and numerically.

3D geometric split–merge segmentation of brain MRI datasets

In this paper, a novel method for MRI volume segmentation based on region adaptive splitting and merging is proposed. The method, called Adaptive Geometric Split Merge (AGSM) segmentation, aims at finding complex geometrical shapes that consist of homogeneous geometrical 3D regions. In each volume splitting step, several splitting strategies are examined and the most appropriate is activated. A way to find the maximal homogeneity axis of the volume is also introduced. Along this axis, the volume splitting technique divides the entire volume in a number of large homogeneous 3D regions, while at the same time, it defines more clearly small homogeneous regions within the volume in such a way that they have greater probabilities of survival at the subsequent merging step. Region merging criteria are proposed to this end. The presented segmentation method has been applied to brain MRI medical datasets to provide segmentation results when each voxel is composed of one tissue type (hard segmentation). The volume splitting procedure does not require training data, while it demonstrates improved segmentation performance in noisy brain MRI datasets, when compared to the state of the art methods.

Superpixel-based conditional random field for image classification

Concerning the high time complexity of inference and parameter estimation in graph model,the concept of superpixel was introduced into the Conditional Random Field(CRF),and a superpixel-based CRF image classification method was proposed.This method first over segmented the image into small homogeneous regions which were called superpixels by using mean shift method.Then the graphical model was constructed with superpixels as nodes and the neighboring nodes as edges.The corresponding definition of CRF and the methods for parameter estimation and labeling inference were proposed and implemented.The experimental results show that better classification results are obtained by the superpixel-based CRF model.At the same time,running time is largely reduced.

Pattern Recognition in Numerical Data Sets and Color Images through the Typicality Based on the GKPFCM Clustering Algorithm

We take the concept of typicality from the field of cognitive psychology, and we apply the meaning to the interpretation of numerical data sets and color images through fuzzy clustering algorithms, particularly the GKPFCM, looking to get better information from the processed data. The Gustafson Kessel Possibilistic Fuzzy c-means (GKPFCM) is a hybrid algorithm that is based on a relative typicality (membership degree, Fuzzy c-means) and an absolute typicality (typicality value, Possibilistic c-means). Thus, using both typicalities makes it possible to learn and analyze data as well as to relate the results with the theory of prototypes. In order to demonstrate these results we use a synthetic data set and a digitized image of a glass, in a first example, and images from the Berkley database, in a second example. The results clearly demonstrate the advantages of the information obtained about numerical data sets, taking into account the different meaning of typicalities and the availability of both values with the clustering algorithm used. This approach allows the identification of small homogeneous regions, which are difficult to find.

Color and Depth-Based Superpixels for Background and Object Segmentation

We present an approach to multimodal semantic segmentation based on both color and depth information. Our goal is to build a semantic map containing high-level information, namely objects and background categories (carpet, parquet, walls …). This approach was developed for the Panoramic and Active Camera for Object Mapping (PACOM)11The PACOM project is supported by DGA in the frame of the “CAROTTE” competition and funded by ANR under the subvention 2009 CORD 102. CAROTTE is organized by the French research funding agency (ANR) and the French armament procurement agency (DGA). Website: <http://www.defi-carotte.fr> project in order to participate in a French exploration and mapping contest called CAROTTE. Our method is based on a structured output prediction strategy to detect the various elements of the environment, using both color and depth images from the Kinect camera. The image is first over-segmented into small homogeneous regions named “superpixels” to be classified and characterized using a bag of features representation. For each superpixel, texture and color descriptors are computed from the color image and 3D descriptors are computed from the associated depth image. A Markov Random Field (MRF) model then fuses texture, color, depth and neighboring information to associate a label to each superpixel extracted from the image. We present an evaluation of different segmentation algorithms for the semantic labeling task and the interest of integrating depth information in the superpixel computation task.

A regional image fusion based on similarity characteristics

In this paper, we propose an image-driven regional fusion method based on a specific region partition strategy according to the redundant and complementary correlation of the input images. Different from the traditional regional fusion approaches dividing one or more input images, our final region map is generated from the similarity comparisons between source images. Inspired by the success of structural similarity index (SSIM), the similarity characteristics of source images are represented by luminance, contrast, and structure comparisons. To generate redundant and complementary regions, we over segment the SSIM map using watershed, and merge the small homogeneous regions with close correlation based on the similarity components. In accordance with the concentrated similarity of different regions, the fusion principles for special regions are constructed to combine the redundant or complementary property. In our method, the redundant and complementary regions of input images are distinguished effectively, which can aid in the sequent fusion process. Experimental results demonstrate that our approach achieve superior results in the different fusion applications. Compared with the existing work, the proposed approach outperforms in both visual presentation and objective evaluation.

Uncertainty in land cover datasets for global land‐surface models derived from 1‐km global land cover datasets

AbstractThe influence of the uncertainties or differences in 1‐km global land cover datasets on a land cover dataset used in land‐surface modelling is explored. The uncertainties in six 1‐km global land cover datasets were found to be transferred to land cover datasets derived by either the dominant land cover type method (DLM) or the area ratio method (ARM). The agreement among the DLM‐derived land cover datasets (the DLM agreement) was higher than the per‐pixel agreement among the six 1‐km global land cover datasets owing to the spatial aggregation effect. The agreement among the ARM‐derived land cover datasets using the ARM (the ARM agreement) was higher than the DLM agreement because of the area ratio retention effect. The area ratios of all land cover types affect the ARM agreement, whereas only the dominant land cover type affects the DLM agreement. The DLM and ARM agreements were both strongly correlated with the per‐pixel agreement among the 1‐km global land cover datasets. Therefore, reducing the uncertainty in the 1‐km global land cover datasets is the key to reducing the uncertainty in the land cover datasets used in land‐surface models. Improving the land cover classification, especially in areas with small homogeneous regions or in transition zones between major land cover types, is also important for reducing the uncertainty in the datasets used for land‐surface models. These sources of uncertainty should be taken into account when interpreting the land‐surface model results. Copyright © 2011 John Wiley &amp; Sons, Ltd.

Dynamic contrast-enhanced magnetic resonance imaging of human cervical carcinoma xenografts: Pharmacokinetic analysis and correlation to tumor histomorphology

Background and purpose Biomarkers that can predict the outcome of treatment accurately are needed for treatment individualization in advanced carcinoma of the uterine cervix. The potential of dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) was investigated in the present preclinical study. Materials and methods CK-160 and TS-415 human cervical carcinoma xenografts were subjected to DCE-MRI at 1.5 T using a spatial resolution of 0.23 × 0.47 × 2.0 mm 3. Parametric images of K trans (the volume transfer constant of Gd-DTPA) and v e (the extravascular extracellular volume fraction) were produced by pharmacokinetic analysis of the DCE-MRI data and compared with the histomorphology of the imaged tissue. Results Analysis of small homogeneous tumor regions showed that K trans, but not v e, differed significantly between parenchymal tissue, connective tissue, and necrotic tissue, consistent with the vascularity of these compartments. However, strong correlations between K trans and the fractional volume of the compartments could not be detected for larger tumor regions, primarily because the majority of the voxels represented a chaotic mixture of parenchymal, connective, and necrotic tissue. Conclusion The potential of DCE-MRI in providing detailed information on the histomorphology of cervical carcinoma is limited, mainly because the tumor tissue shows significant morphological heterogeneity at the subvoxel level.

A Multilevel Parcel-Based Approach to Change Detection in Very High Resolution Multitemporal Images

This letter presents a novel parcel-based context-sensitive technique for unsupervised change detection in very high geometrical resolution images. In order to improve pixel-based change-detection performance, we propose to exploit the spatial-context information in the framework of a multilevel approach. The proposed technique models the scene (and hence changes) at different resolution levels defining multitemporal and multilevel ldquoparcelsrdquo (i.e., small homogeneous regions shared by both original images). Change detection is achieved by applying a multilevel change vector analysis to each pixel of the considered images. This technique properly analyzes the multilevel and multitemporal parcel-based context information of the considered spatial position. The adaptive nature of multitemporal parcels and their multilevel representation allow one a proper modeling of complex objects in the investigated scene as well as borders and details of the changed areas. Experimental results confirm the effectiveness of the proposed approach.

Investigation of the use of MOSFET for clinical IMRT dosimetric verification

(Received 22 October 2001; accepted for publication 26 March 2002; published 22 May 2002) With advanced conformal radiotherapy using intensity modulated beams, it is important to have radiation dose verification measurements prior to treatment. Metal oxide semiconductor field effect transistors (MOSFET) have the advantage of a faster and simpler reading procedure compared to thermoluminescent dosimeters (TLD), and with the commercial MOSFET system, multiple detectors can be used simultaneously. In addition, the small size of the detector could be advantageous, especially for point dose measurements in small homogeneous dose regions. To evaluate the feasibility of MOSFET for routine IMRT dosimetry, a comprehensive set of experiments has been conducted, to investigate the stability, linearity, energy, and angular dependence. For a period of two weeks, under a standard measurement setup, the measured dose standard deviation using the MOSFETs was +/- 0.015 Gy with the mean dose being 1.00 Gy. For a measured dose range of 0.3 Gy to 4.2 Gy, the MOSFETs present a linear response, with a linearity coefficient of 0.998. Under a 10 x 10 cm2 square field, the dose variations measured by the MOSFETs for every 10 degrees from 0 to 180 degrees is +/- 2.5%. The percent depth dose (PDD) measurements were used to verify the energy dependence. The measured PDD using the MOSFETs from 0.5 cm to 34 cm depth agreed to within +/- 3% when compared to that of the ionization chamber. For IMRT dose verification, two special phantoms were designed. One is a solid water slab with 81 possible MOSFET placement holes, and another is a cylindrical phantom with 48 placement holes. For each IMRT phantom verification, an ionization chamber and 3 to 5 MOSFETs were used to measure multiple point doses at different locations. Preliminary results show that the agreement between dose measured by MOSFET and that calculated by Corvus is within 5% error, while the agreement between ionization chamber measurement and the calculation is within 3% error. In conclusion, MOSFET detectors are suitable for routine IMRT dose verification.

Data reduction by separation of signal and noise components for multivariate spatial images

Using the spatial dependence of observations from multivariate images, it is possible to construct methods for data reduction that perform better than the widely used principal components procedure. Switzer and Green introduced the min/max autocorrelation factors (MAF) process for transforming the data to a new set of vectors where the components are arranged according to the amount of autocorrelation. MAF performs well when the underlying image consists of large homogeneous regions. For images with many transitions between smaller homogeneous regions, however, MAF may not perform well. A modification of the MAF process, the restricted min/max autocorrelation factors (RMAF) process, which takes into account the transitions between homogeneous regions, is introduced. Simulation experiments show that large improvements can be achieved using RMAF rather than MAF.