Variations In Image Intensity Research Articles

An Improved Illumination Normalization and Robust Feature Extraction Technique for Face Recognition Under Varying Illuminations

Invariant feature extraction under diverse illuminations is challenging for face recognition. Light intensity variations in face images are predominant in large-scale features. In existing techniques, such features are truncated to achieve illumination-invariant features. However, salient features are lost during small-scale feature extraction that affect performance. Thus, objective in proposed work is to attain improved illumination normalization where large-scale and small-scale feature information is efficiently extracted for face recognition. First, reflectance ratio and histogram equalization (RRHE)-based new illumination normalization framework is proposed in which illumination deviations are annulled. Then, histogram equalization is employed to enhance contrast of reflectance ratio image by adjusting pixel intensities. Then, robust feature extraction in discrete wavelet packet transform domain (RFDWPT) from RRHE images is performed using various orthogonal wavelets with distinct vanishing moments. Here, small-scale features (noise effect) of RRHE images are discarded and final feature vector is formed by appropriate small-scale and large-scale features. This results in illumination-normalized salient features for eigen space analysis where nearest neighbor classification is performed on compact size training and test features. Compared with other face recognition techniques under different illumination conditions, significant enhancement in recognition accuracy is achieved on benchmark databases such as Yale B, CMU-PIE, Yale and extended Yale B.

Fractional-order difference curvature-driven fractional anisotropic diffusion equation for image super-resolution

Image super-resolution methods-based existing edge indicating operators — namely Gauss curvature, mean curvature and gradient — cannot effectively identify the edges, ramps and flat regions and suffer from the loss of fine textures. To address these issues, this paper presents a fractional anisotropic diffusion equation based on a new edge indicator, named fractional-order difference curvature, which can characterize the intensity variations in images. We introduce the frequency-domain definition for fractional-order derivative by the Fourier transform, which is easy to implement numerically. The new edge indicator is better than the existing edge indicating operators in distinguishing between ramps and edges and can better handle the fine textures. Comparative results for natural images validate that the proposed method can yield a visually pleasing result and better values of MSSIM and PSNR.

A Local Feature Descriptor Based on Combination of Structure and Texture Information for Multispectral Image Matching

Due to the significant nonlinear intensity changes of multispectral images, automatic image feature point matching is a challenging task. This letter addresses the problem and proposes a novel descriptor combining the structure and texture information to solve the nonlinear intensity variations of multispectral images. We first propose directional maps, i.e., the directional response maps (DMs) and the directional response binary maps (DBMs), which can capture the common structure and texture properties of multispectral images, respectively. We then use the spatial pooling pattern of the histogram of oriented gradients to separately describe the local region of each point of interest based on the DMs and DBMs. In order to speed up the calculation, we apply Gaussian filters to the DMs and average filters to the DBMs to construct the per-pixel histogram bins. Finally, we conjoin the normalized feature vectors corresponding to the structure description and texture description of each point of interest to obtain the histograms of directional maps (HoDMs). The proposed HoDM descriptor was evaluated using three data sets composed of images obtained in both visible light and infrared spectra. The experimental results confirm that the proposed HoDM descriptor is robust to the nonlinear intensity changes of multispectral images and has a superior matching performance as well as a much higher computational efficiency.

RETRACTED ARTICLE: Gender classification from face images by mixing the classifier outcome of prime, distinct descriptors

Since the last decade, the area of recognizing gender of a person from an image of his/her face has been playing an important role in the research field. A automatic gender recognition is an important concept, essential for many fields like forensic science and automatic payment system. However, it is very onerous due to high variability factors such as illumination, expression, pose, age, scales, camera quality and occlusion. Humans can easily recognize the difference between genders, but it is a critical task for computer. To overcome this issue, many experimental results have been explained in the existing literature as per the advancement of machine vision. But, still definite optimal solution could not be found. For practical usage, a novel full approach to gender classification which is mainly based on image intensity variation, shape and texture features is proposed in this work. These multi-attribute features are mixed at different spatial scales or levels. The proposed novel system uses two datasets such as Facial ExpressIon Set (FEI) dataset and self-built dataset with various facial expressions. In this research, eight local directional pattern algorithms are used for extracting facial edge feature. Local binary pattern is also used for extracting texture feature, whereas intensity as a added feature. Finally, spatial histograms computed from the above features are concatenated to build a gender descriptor. The proposed descriptor efficiently extracts discriminating information from three different levels, including regional, global and directional level. After the extraction of a gender descriptor, effective linear kernel-based support vector machine superior to other classifiers is used to classify the face image as either male or female. The experimental results show that the classification accuracy obtained with the mixture of outcome of multi-scale, multi-block, distinct and prime feature classification is better than having a single-scaled image. It is worth mentioning that the proposed approach is implemented in MATLAB which achieves an accuracy of 99% on the FEI face dataset (200 faces) and 94% on self-built dataset (200 faces).

Localized region based active contours with a weakly supervised shape image for inhomogeneous video segmentation of train bogie parts in building an automated train rolling examination

Active Contours have been widely acknowledged for providing a dependable solution to complex image segmentation problems which are represented as a functional optimization problem. Inhomogeneous image intensity regions present difficulties for the evolving curve, which are driven by nonlinear variations in a region’s intensity pixels. The problem was approached using the local region’s statistical information for improving the segmentation accuracies. However, the local information of the region was calculated using the inhomogeneous pixel intensities, which in turn degrade the segmentation outputs. In this paper, we approach this problem by introducing a weakly supervised shape image (WSSI), which form a pre-defied shape term within a local window and a local region difference term to improve the segmentation results. The proposed model is robust to image intensity variations and are computationally efficient on high-resolution images. To test and validate the proposed active contour model, we choose a real-time application, Automated Rolling Stock Examination using computer vision. The problem here is to extract the bogie parts using the proposed method to monitor their conditional health on a moving train from the captured high speed video sequence. We have created the bogie dataset with five trains at different time zones using a 240fps sports action camera in full HD mode. We apply our proposed method on these video frames to segment 10 vital parts of the train bogie on a 10000-frame video sequence per train. The proposed method has been compared with similar state-of-the-art localized region based active contour methods for segmentation accuracy.

Multi-sensor remote sensing image change detection based on sorted histograms

ABSTRACTChange detection using multi-sensor remote sensing images, such as synthetic aperture radar (SAR) and optical images, is poorly researched and thus remains a challenging task. In this study, we address this problem by proposing a novel automatic change detection method. Different sensors have completely different physical principles. Thus, the resulting multi-sensor images have completely different radiometric values. First, we introduce a sorted histogram concept that sorts the bins in descending order, noticing that multi-sensor images with absence of change have the same combination of objects, and each object in different images has the same proportions and a unique range of grey values. The sorted histogram discards the visual property correspondence between images and is capable of capturing the local internal image layout. Then, various histogram-based distances are employed to estimate the distance between each sorted histogram pair. After the whole image has been analysed, we obtain a divergence index map. The sorted histogram not only has the theoretical advantage of robustness in the intensity variations in multi-sensor images but also the practical advantage of low computational complexity compared with existing methods. Experiments on SAR and optical datasets with different resolutions show promising results in terms of detection capability and run time.

Characterization of freeze–thaw effects within clay by 3D X-ray Computed Tomography

Accurate quantification of moisture content redistribution and physical property change due to freeze–thaw is important for understanding frost heave and thaw settlement of fine-grained soils including clay. This paper presents 3D X-ray Computed Tomography (CT) data for a clay specimen before and after freeze–thaw and physical property data obtained by conventional laboratory testing, and the relationship among the date sets. Undisturbed clay specimens were subject to one-directional freeze–thaw in a closed system under different freezing temperatures to collect 3D X-ray CT images, and the variation in CT image intensity (CTI) before and after freeze–thaw were analyzed to reveal the spatial effects of freeze–thaw. Meanwhile, soil properties including moisture content, void ratio, and dry density were obtained for samples taken from different heights of the specimens with and without freeze–thaw to obtain their changes. Close correlations were observed between the physical property changes and the CTI variation. Linear equations were established between the changes of physical properties and the CTI variation. These equations could potentially be applied for high-resolution quantitative assessment of soil physical property changes due to freeze–thaw by using 3D X-ray CT. This study demonstrates that, compared with traditional test methods, CT scanning can be advantageous in revealing the internal change in soil physical properties due to freeze–thaw quantitatively and nondestructively.

Segmentation of 3D images of plant tissues at multiple scales using the level set method

BackgroundDevelopmental biology has made great strides in recent years towards the quantification of cellular properties during development. This requires tissues to be imaged and segmented to generate computerised versions that can be easily analysed. In this context, one of the principal technical challenges remains the faithful detection of cellular contours, principally due to variations in image intensity throughout the tissue. Watershed segmentation methods are especially vulnerable to these variations, generating multiple errors due notably to the incorrect detection of the outer surface of the tissue.ResultsWe use the level set method (LSM) to improve the accuracy of the watershed segmentation in different ways. First, we detect the outer surface of the tissue, reducing the impact of low and variable contrast at the surface during imaging. Second, we demonstrate a new edge function for a level set, based on second order derivatives of the image, to segment individual cells. Finally, we also show that the LSM can be used to segment nuclei within the tissue.ConclusionThe watershed segmentation of the outer cell layer is demonstrably improved when coupled with the LSM-based surface detection step. The tool can also be used to improve watershed segmentation at cell-scale, as well as to segment nuclei within a tissue. The improved segmentation increases the quality of analysis, and the surface detected by our algorithm may be used to calculate local curvature or adapted for other uses, such as mathematical simulations.

Microfluidic-Based Measurement Method of Red Blood Cell Aggregation under Hematocrit Variations.

Red blood cell (RBC) aggregation and erythrocyte sedimentation rate (ESR) are considered to be promising biomarkers for effectively monitoring blood rheology at extremely low shear rates. In this study, a microfluidic-based measurement technique is suggested to evaluate RBC aggregation under hematocrit variations due to the continuous ESR. After the pipette tip is tightly fitted into an inlet port, a disposable suction pump is connected to the outlet port through a polyethylene tube. After dropping blood (approximately 0.2 mL) into the pipette tip, the blood flow can be started and stopped by periodically operating a pinch valve. To evaluate variations in RBC aggregation due to the continuous ESR, an EAI (Erythrocyte-sedimentation-rate Aggregation Index) is newly suggested, which uses temporal variations of image intensity. To demonstrate the proposed method, the dynamic characterization of the disposable suction pump is first quantitatively measured by varying the hematocrit levels and cavity volume of the suction pump. Next, variations in RBC aggregation and ESR are quantified by varying the hematocrit levels. The conventional aggregation index (AI) is maintained constant, unrelated to the hematocrit values. However, the EAI significantly decreased with respect to the hematocrit values. Thus, the EAI is more effective than the AI for monitoring variations in RBC aggregation due to the ESR. Lastly, the proposed method is employed to detect aggregated blood and thermally-induced blood. The EAI gradually increased as the concentration of a dextran solution increased. In addition, the EAI significantly decreased for thermally-induced blood. From this experimental demonstration, the proposed method is able to effectively measure variations in RBC aggregation due to continuous hematocrit variations, especially by quantifying the EAI.

Polarization management to mitigate misalignment-induced fringe fading in fiber-based optical coherence tomography.

In fiber-based optical coherence tomography (OCT), the interference fringes suffer from the fading effect due to misalignment of the light polarization states between the reference and sample arms, resulting in sensitivity degradation and image intensity variation. We theoretically and experimentally analyzed the relation between the misalignment and the fading coefficient. Assuming that the variation of the light polarization in single-mode fiber (SMF) was a random process, we statistically quantified the fading effect. Furthermore, in OCT configuration based on the Michelson interferometer, we reported an interesting observation that the polarization states of light traveling a round-trip in SMF are not evenly distributed on the Poincare sphere. Based on this observation, we demonstrated the existence of an optimal output polarization state of the reference arm to mitigate the fading effect. We demonstrated that in an optimal setup, the statistical average signal-to-noise ratio could be 3.5 dB higher than a setup without proper polarization management.

Simulating Longitudinal Brain MRIs with Known Volume Changes and Realistic Variations in Image Intensity.

This paper presents a simulator tool that can simulate large databases of visually realistic longitudinal MRIs with known volume changes. The simulator is based on a previously proposed biophysical model of brain deformation due to atrophy in AD. In this work, we propose a novel way of reproducing realistic intensity variation in longitudinal brain MRIs, which is inspired by an approach used for the generation of synthetic cardiac sequence images. This approach combines a deformation field obtained from the biophysical model with a deformation field obtained by a non-rigid registration of two images. The combined deformation field is then used to simulate a new image with specified atrophy from the first image, but with the intensity characteristics of the second image. This allows to generate the realistic variations present in real longitudinal time-series of images, such as the independence of noise between two acquisitions and the potential presence of variable acquisition artifacts. Various options available in the simulator software are briefly explained in this paper. In addition, the software is released as an open-source repository. The availability of the software allows researchers to produce tailored databases of images with ground truth volume changes; we believe this will help developing more robust brain morphometry tools. Additionally, we believe that the scientific community can also use the software to further experiment with the proposed model, and add more complex models of brain deformation and atrophy generation.

Simultaneous measurement of erythrocyte deformability and blood viscoelasticity using micropillars and co-flowing streams under pulsatile blood flows.

The biophysical properties of blood provide useful information on the variation in hematological disorders or diseases. In this study, a simultaneous measurement method of RBC (Red Blood Cell) deformability and blood viscoelasticity is proposed by evaluating hemodynamic variations through micropillars and co-flowing streams under sinusoidal blood flow. A disposable microfluidic device is composed of two inlets and two outlets, two upper side channels, and two lower side channels connected to one bridge channel. First, to measure the RBC deformability, the left-lower side channel has a deformability assessment chamber (DAC) with narrow-sized micropillars. Second, to evaluate the blood viscoelasticity in co-flowing streams, a phosphate buffered saline solution is supplied at a constant flow rate. By closing or opening a pinch valve connected to the outlet of DAC, blood flows in forward or back-and-forth mode. A time-resolved micro-particle image velocimetry technique and a digital image processing technique are used to quantify the blood velocity and image intensity. Then, RBC deformability is evaluated by quantifying the blood volume passing through the DAC under forward flow, and quantifying the variations of blood velocity and image intensity in the DAC under back-and-forth flow. Using a discrete circuit model, blood viscoelasticity is obtained by evaluating variations of blood velocity and co-flowing streams. The effect of several factors (period, hematocrit, and base solution) on the performance is quantitatively evaluated. Based on the experimental results, the period of sinusoidal flow and hematocrit are fixed at 30 s and 50%, respectively. As a performance demonstration, the proposed method is employed to detect the homogeneous and heterogeneous blood composed of normal RBCs and hardened RBCs. These experimental results show that the RBC deformability is more effective to detect minor subpopulations of heterogeneous bloods, compared with blood viscoelasticity. Therefore, it leads to the conclusion that the proposed method has the ability to evaluate RBC deformability and blood viscoelasticity under sinusoidal blood flow, with sufficient accuracy and high-throughput.

EVolution: an edge-based variational method for non-rigid multi-modal image registration

Image registration is part of a large variety of medical applications including diagnosis, monitoring disease progression and/or treatment effectiveness and, more recently, therapy guidance. Such applications usually involve several imaging modalities such as ultrasound, computed tomography, positron emission tomography, x-ray or magnetic resonance imaging, either separately or combined.In the current work, we propose a non-rigid multi-modal registration method (namely EVolution: an edge-based variational method for non-rigid multi-modal image registration) that aims at maximizing edge alignment between the images being registered. The proposed algorithm requires only contrasts between physiological tissues, preferably present in both image modalities, and assumes deformable/elastic tissues. Given both is shown to be well suitable for non-rigid co-registration across different image types/contrasts (T1/T2) as well as different modalities (CT/MRI). This is achieved using a variational scheme that provides a fast algorithm with a low number of control parameters. Results obtained on an annotated CT data set were comparable to the ones provided by state-of-the-art multi-modal image registration algorithms, for all tested experimental conditions (image pre-filtering, image intensity variation, noise perturbation). Moreover, we demonstrate that, compared to existing approaches, our method possesses increased robustness to transient structures (i.e. that are only present in some of the images).

Multi-scale local structure patterns histogram for describing visual contents in social image retrieval systems

Content based image retrieval systems rely heavily on the set of features extracted from images. Effective image representation emerges as a crucial step in such systems. A key challenge in visual content representation is to reduce the so called `semantic gap'. It is the inability of existing methods to describe contents in a human-oriented way. Content representation methods inspired by the human vision system have shown promising results in image retrieval. Considerable work has been carried out during the past two decades for developing methods to extract descriptors inspired by the human vision system and attempt to retrieve visual contents efficiently according to the user needs, thereby reducing the semantic gap. Despite the extensive research being conducted in this area, limitations in current image retrieval systems still exist. This paper presents a descriptor for personalized social image collections which utilizes the local structure patterns in salient edge maps of images at multiple scales. The human visual system at the basic level is sensitive to edges, corners, intersections, and other such intensity variations in images generating local structure patterns. Analyzing these patterns at multiple scales allow the most salient fine-grained and coarse-grained features to be captured. The features are accumulated in a local structure patterns histogram to index images allowing flexible querying of visual contents. The retrieval results show that the proposed descriptor ranks well among similar state-of-the-art methods for large social image collections.

Compressed domain visual information retrieval based on I-frames in HEVC

Compressed domain retrieval is important in the retrieval of HEVC coded videos, because full decompression of HEVC coded videos is very time consuming. In this paper, a texture based retrieval method is proposed for either video retrieval of HEVC coded videos or image retrieval of coded images as HEVC I-frames. The various prediction unit sizes and high number of prediction modes which are employed in I-frame coding of HEVC, provides higher information about the texture of the coded picture compared to the I-frame coding in H.264/AVC. The proposed texture based image retrieval method for HEVC coded visual information is based on histograms of prediction modes and prediction unit sizes. This method achieves 0.34 ANMRR in the image retrieval experiments and 0.33 ANMRR in the conducting video retrieval experiments, which are better compared to the other compressed domain retrieval methods based on H.264/AVC. On the other hand, the experimental evaluations indicate good robustness of the proposed method against variations in quantization parameter and image intensity. Moreover, the timing analysis indicates that feature extraction time by the proposed method is about 35 % of the decoding time of a coded video.

Kernel-based adaptive sampling for image reconstruction and meshing

This paper introduces a kernel-based sampling approach for image reconstruction and meshing. Given an input image and a user-specified number of points, the proposed method can automatically generate adaptive distribution of samples globally. We formulate the problem as an optimization to reconstruct the image by summing a small number of Gaussian kernels to approximate the given target image intensity or density. Each Gaussian kernel has the fixed size and the same energy. After the optimization, the samples are well distributed according to the image intensity or density variations as well as faithfully preserved the feature edges, which can be used to reconstruct high-quality images. Finally, we generate the adaptive triangular or tetrahedral meshes based on the well-spaced samples in 2D and 3D images. Our results are compared qualitatively and quantitatively with the state-of-the-art in image sampling and reconstruction on several examples by using the standard measurement criteria.

Methods for investigating the local spatial anisotropy and the preferred orientation of cones in adaptive optics retinal images.

The ability to noninvasively image the cone photoreceptor mosaic holds significant potential as a diagnostic for retinal disease. Central to the realization of this potential is the development of sensitive metrics for characterizing the organization of the mosaic. Here we evaluated previously-described and newly-developed (Fourier- and Radon-based) methods of measuring cone orientation in simulated and real images of the parafoveal cone mosaic. The proposed algorithms correlated well across both simulated and real mosaics, suggesting that each algorithm provides an accurate description of photoreceptor orientation. Despite high agreement between algorithms, each performed differently in response to image intensity variation and cone coordinate jitter. The integration property of the Fourier transform allowed the Fourier-based method to be resistant to cone coordinate jitter and perform the most robustly of all three algorithms. Conversely, when there is good image quality but unreliable cone identification, the Radon algorithm performed best. Finally, in cases where the cone coordinate reliability was excellent, the method previously described by Pum and colleagues performed best. These descriptors are complementary to conventional descriptive metrics of the cone mosaic, such as cell density and spacing, and have the potential to aid in the detection of photoreceptor pathology.

Experimental evaluation of the ‘transport-of-intensity’ equation for magnetic phase reconstruction in Lorentz transmission electron microscopy

The ‘transport-of-intensity’ equation (TIE) is a general phase reconstruction methodology that can be applied to Lorentz transmission electron microscopy (TEM) through the use of Fresnel-contrast (defocused) images. We present an experimental study to test the application of the TIE for quantitative magnetic mapping in Lorentz TEM without aberration correction by examining sub-micrometer sized Ni80Fe20 (Permalloy) elements. For a JEOL JEM 2100F adapted for Lorentz microscopy, we find that quantitative magnetic phase reconstructions are possible for defoci distances ranging between approximately 200μm and 800μm. The lower limit originates from competing sources of image intensity variations in Fresnel-contrast images, namely structural defects and diffraction contrast. The upper defocus limit is due to a numerical error in the estimation of the intensity derivative based on three images. For magnetic domains, we show quantitative reconstructions of the product of the magnetic induction vector and thickness in element sizes down to approximately 100nm in lateral size and 5nm thick resulting in a minimal detection of 5Tnm. Three types of magnetic structures are tested in terms of phase reconstruction: vortex cores, domain walls, and element edges. We quantify vortex core structures at a diameter of 12nm while the structures of domain walls and element edges are characterized qualitatively. Finally, we show by image simulations that the conclusions of this experimental study are relevant to other Lorentz TEM in which spherical aberration and defocus are dominant aberrations.

On The Effect Of Image Brightness And Contrast Nonuniformity On Statistical Texture Parameters

Abstract Computerized texture analysis characterizes spatial patterns of image intensity, which originate in the structure of tissues. However, a number of texture descriptors also depend on local average image intensity and/or contrast. This variations, known as image nonuniformity (inhomogeneity) artefacts often occur, e.g. in MRI. Their presence may lead to errors in tissue description. This unwanted effect is explained in this paper using statistical texture descriptors applied for MRI slices of a normal and fibrotic liver. To reduce the errors, correction of image spatial nonuniformity prior to texture analysis is performed. The issue of sensitivity of popular texture parameters to image nonuniformities is discussed. It is illustrated by classification examples of natural Brodatz textures, digitally modified to account for inhomogeneities – modeled as smooth variations of image intensity and contrast. A set of texture features is identified which represent certain immunity to image inhomogeneities.

Analytic signal phase-based myocardial motion estimation in tagged MRI sequences by a bilinear model and motion compensation.

Different mathematical tools, such as multidimensional analytic signals, allow for the calculation of 2D spatial phases of real-value images. The motion estimation method proposed in this paper is based on two spatial phases of the 2D analytic signal applied to cardiac sequences. By combining the information of these phases issued from analytic signals of two successive frames, we propose an analytical estimator for 2D local displacements. To improve the accuracy of the motion estimation, a local bilinear deformation model is used within an iterative estimation scheme. The main advantages of our method are: (1) The phase-based method allows the displacement to be estimated with subpixel accuracy and is robust to image intensity variation in time; (2) Preliminary filtering is not required due to the bilinear model. The proposed algorithm, integrating phase-based optical flow motion estimation and the combination of global motion compensation with local bilinear transform, allows spatio-temporal cardiac motion analysis, e.g. strain and dense trajectory estimation over the cardiac cycle. Results from 7 realistic simulated tagged magnetic resonance imaging (MRI) sequences show that our method is more accurate compared with state-of-the-art method for cardiac motion analysis and with another differential approach from the literature. The motion estimation errors (end point error) of the proposed method are reduced by about 33% compared with that of the two methods. In our work, the frame-to-frame displacements are further accumulated in time, to allow for the calculation of myocardial Lagrangian cardiac strains and point trajectories. Indeed, from the estimated trajectories in time on 11 in vivo data sets (9 patients and 2 healthy volunteers), the shape of myocardial point trajectories belonging to pathological regions are clearly reduced in magnitude compared with the ones from normal regions. Myocardial point trajectories, estimated from our phase-based analytic signal approach, seem therefore a good indicator of the local cardiac dynamics. Moreover, they are shown to be coherent with the estimated deformation of the myocardium.