Gray Level Values Research Articles

A modified method for image encryption based on chaotic map and genetic algorithm

The security of digital data has been attending more than past, spatially image data security. In this study, a hybrid image encryption method has been proposed based on genetic algorithm and chaos. Encryption process consists of three main steps: confusion phase, diffusion phase, and improvement phase using a genetic algorithm. At first, Chen’s chaotic map is used in the confusion phase to generate a scrambled image by shuffling plain-image pixels, and in the diffusion step, Logistic-Sine map alters those pixels gray-level values. It produces some of encrypted images which were considered as the initial population for the genetic algorithm. Then, by using the genetic algorithm, the encrypted images are optimized as much as possible. Finally, the best encrypted image is the final cipher image. The experimental results and several security analyses show that the proposed modified method provides an efficient scheme for image encryption and good robustness against frequent statistical and security attacks.

An artificial intelligence system using machine-learning for automatic detection and classification of dental restorations in panoramic radiography

The aim of this study was to develop a computer vision algorithm based on artificial intelligence, designed to automatically detect and classify various dental restorations on panoramic radiographs. A total of 738 dental restorations in 83 anonymized panoramic images were analyzed. Images were automatically cropped to obtain the region of interest containing maxillary and mandibular alveolar ridges. Subsequently, the restorations were segmented by using a local adaptive threshold. The segmented restorations were classified into 11 categories, and the algorithm was trained to classify them. Numerical features based on the shape and distribution of gray level values extracted by the algorithm were used for classifying the restorations into different categories. Finally, a Cubic Support Vector Machine algorithm with Error-Correcting Output Codes was used with a cross-validation approach for the multiclass classification of the restorations according to these features. The algorithm detected 94.6% of the restorations. Classification eliminated all erroneous marks, and ultimately, 90.5% of the restorations were marked on the image. The overall accuracy of the classification stage in discriminating between the true restoration categories was 93.6%. This machine-learning algorithm demonstrated excellent performance in detecting and classifying dental restorations on panoramic images.

Thresholding strategies to measure vessel density by optical coherence tomography angiography

ObjectiveA variety of binarization strategies have been used to measure vessel density by optical coherence tomography angiography (OCT-A), but it is uncertain if they produce similar results. The purpose of the study was to evaluate the impact of different thresholding methods and contrast and brightness adjustment on OCT-A vessel density metrics. DesignObservational, cross-sectional case series. ParticipantsConsecutive healthy volunteers. MethodsHealthy volunteers underwent fovea-centred 3 mm × 3 mm OCT-A scans using PlexElite 9000. Images of the superficial vascular plexus were generated using the instrument’s automated segmentation. Images were thresholded with 5 different threshold tools in ImageJ (Default, Huang, IsoDat, Mean, and Otsu), and the threshold grey level value defined by each method was recorded. Brightness and contrast were also increased or decreased by 50% compared with the default. Binarization was performed using the threshold values from each method, and vessel densities were computed and compared. Main outcome measuresSuperficial plexus vessel density was measured and compared using different adjust threshold tools and changing brightness and contrast. ResultsTwenty eyes of 20 healthy participants were included. Different threshold strategies produced measurements with different mean values (p < 0.0001). Pairwise comparisons revealed differences between all groups (p < 0.0001) except between the IsoData and Otsu thresholding approaches (p > 0.270). Increasing or decreasing the brightness or to 50% of the mean value also yielded statistically significant differences (p < 0.0001). ConclusionsThe method of thresholding and adjustments in contrast and brightness can significantly impact retinal vessel density measurements. These findings highlight the importance of using consistent thresholding strategies for clinical studies.

Detection of Myocardial Tissue Alterations in Hypertrophic Cardiomyopathy Using Texture Analysis of T2-Weighted Short Inversion Time Inversion Recovery Magnetic Resonance Imaging.

The aim of this study was to evaluate the usefulness of texture analysis of T2-weighted short inversion time inversion recovery (T2-STIR) for detecting myocardial tissue alterations in hypertrophic cardiomyopathy (HCM). Twenty patients with HCM and 11 controls were examined. Texture analysis was performed for the hypertrophied regions with and without and abnormal hyperintensity (AHI) and for the interventricular septum of the controls on T2-STIR. T2 mapping was performed to measure myocardial T2 values. A gray-level nonuniformity value of 64.7 was the best discriminator between patients and controls with an area under the curve of 0.93 on a receiver operating characteristic curve. T2 values did not differ between them. The gray-level nonuniformity was significantly smaller in AHI regions than in the hypertrophied regions without AHI in HCM patients. Texture analysis is useful for quantitatively detecting myocardial tissue altenations, including AHI, associated with HCM on T2-STIR.

Improvement of image quality with fusion in radiography of high and low intensity lateral head

Radiological examination of the head bone is an integral part in the management of patients suffering from head trauma. This is because X-ray of the head bone is still quite significant in diagnosing fractures of the head bone. X-ray examination of cases of injury to the facial bones required two times the examination of the lateral head of high and low intensity x-ray to produce different image information due to heterogeneity of the head bone. At this time there is no method to improve image quality by combining the two images. in this study a method of improving image quality with fusion on high-low lateral head bone radiographs is proposed. This research is an experimental study to compare two variables measured from unequal (free) samples, where the group that is compared is more than two, namely the quality of lateral images of high intensity head, low intensity and fusion. Image quality assessment is done using a histogram which is then analysed using the Friedman test. The results showed that the average gray level on the highest histogram was sequentially at high intensity, fusion and finally at low intensity. The statistical test results obtained p value 0.007 which means that there are differences in the quality of lateral head images at high intensities, low intensities and fusion. Fusion image quality obtained grey level values that are between high and low intensity images, this illustrates that using of image fusion is able to provide more complete image information.

A Multi-Layer Perceptron for Color Index based Vegetation Segmentation

Vegetation segmentation in a field color image is a process of distinguishing vegetation objects of interests like crops and weeds from a background of soil and/or other residues. The performance of the process is crucial in automatic precision agriculture which includes weed control and crop status monitoring. To facilitate the segmentation, color indices have predominantly been used to transform the color image into its gray-scale image. A thresholding technique like the Otsu method is then applied to distinguish vegetation parts from the background. An obvious demerit of the thresholding based segmentation will be that classification of each pixel into vegetation or background is carried out solely by using the color feature of the pixel itself without taking into account color features of its neighboring pixels. This paper presents a new pixel-based segmentation method which employs a multi-layer perceptron neural network to classify the gray-scale image into vegetation and nonvegetation pixels. The input data of the neural network for each pixel are 2-dimensional gray-level values surrounding the pixel. To generate a gray-scale image from a raw RGB color image, a well-known color index called Excess Green minus Excess Red Index was used. Experimental results using 80 field images of 4 vegetation species demonstrate the superiority of the neural network to existing threshold-based segmentation methods in terms of accuracy, precision, recall, and harmonic mean.

Common-path generation of stable cylindrical perfect vector vortex beams of arbitrary order

A highly flexible and efficient method of generating stable radially and azimuthally polarized perfect optical vortex beams and all higher order cylindrical perfect vector vortex beams is proposed and demonstrated. The method is the most convenient implementation of the coherent superposition of two orthogonally circularly polarized optical vortex beams of arbitrary integer topological charges. The proposed method employs a spatial light modulator to control the relative phase between the vertical and horizontal polarization components of an input perfect vortex beam in a common-path configuration to generate arbitrary ordered cylindrical perfect vector vortex beams by changing the reference gray-level value. Calibration curve of relative phase vs grayscale of the phase function on the spatial light modulator is obtained to facilitate the determination of required phase-offset using pre-calculated grayscale color-map. The generated beams consist of high mode purity and states of polarization, as obtained from measured spatially resolved Stokes parameter, are uniformly distributed throughout the beam cross-section. The interference pattern of the two beams in a projected linear polarization state also give the cylindrically symmetric petal beams with a control over the number and orientation of petals.

Image Thresholding Using the Complement Feature

A new feature (the complement feature) is proposed in an Eigen formulations for performing global image thresholding. The goal is to find an intensity or gray-level value below which is the background while above it is the foreground (object). Each pixel in the image is represented by a (2D) unit vector where the x-component is the normalized (to [0,1] or [-1,1]) intensity of the pixel, while the y-component is its complement (e.g., Euclidian L2-Norm). The correlation matrix can then constructed to find the cross-correlation, Eigen vectors (axes of inertia) and Eigen values (description of respective sizes). Several implementations for each of the three previously mentioned categories are proposed to perform image thresholding. Interestingly, some of the proposed implementations do not require exhaustive search and a direct solution can be obtained. The results are promising on a wide range of images as demonstrated by comparison with the well-known Otsu method.

An improved Otsu threshold segmentation algorithm

Image segmentation is widely used as a fundamental step for various image processing applications. This paper focuses on improving the famous image thresholding method named Otsu's algorithm. Based on the fact that threshold acquired by Otsu's algorithm tends to be closer to the class with larger intraclass variance when the foreground and background have large intraclass variance difference, an improved strategy is proposed to adjust the threshold bias. We analysed the relationship between pixel greyscale value and the change of cumulative pixel number, and selected the ratio of pixel grey level value to a certain cumulative pixel number as the adjusted threshold. Experiments using typical testing images were set up to verify the proposed method both quantitatively and qualitatively. Two widely used metrics named misclassification error (ME) and dice similarity coefficient (DSC) were adopted for quantitative evaluation, and both quantitative and qualitative results indicated that the proposed algorithm could better segment the testing images and get competitive misclassification error and DSC values compared with Otsu's method and its improved versions proposed by Hu and Gong (2009) and Xu et al. (2011), and the time consumption of our method can be significantly reduced.

Application of Fractal and Gray-Level Co-Occurrence Matrix Indices to Assess the Forest Dynamics in the Curvature Carpathians—Romania

The mountain ecosystems face significant damage from deforestation and environmental forest changes. We investigated the evolution of tree types of cover areas, deforested areas and total deforested areas from Curvature Carpathians using Gray-Level Co-occurrence Matrix and fractal analysis. The forest dynamics mapping was one of the main objectives of this study and it was carried out using multiple fractal and GLCM indices. We approached the analysis of satellite forest images by calculation of four fractal indices such as Pyramid dimension, Cube Counting Dimension, Fractal Fragmentation-Compaction Index and Tug-of-War lacunarity. We also calculated fractal dimension because it is an index of complexity comparing how the detail in a pattern changes with the scale at which it is measured. Fractal dimension is useful for estimation of irregularity or roughness of fractal and natural objects that do not conform to Euclidian geometry. While the fractal dimension quantifies how much space is occupied, the Tug-of-War lacunarity complements fractal dimension with its ability to quantify how space is occupied. Analysis was further supplemented by the Gray-Level Co-occurrence Matrix analysis because it quantifies spatial probability distributions of gray level values between pixel pairs within an image. The calculated Gray-Level Co-occurrence Matrix features included Angular Second Moment, Contrast, Correlation, Inverse Difference Moment and Entropy. Such comprehensive analysis has the advantage of combining fractal analysis that extracts quantitative information about the morphological complexity of the image with the spatial distribution of the gray pixel intensities as calculated by the co-occurrence features provided by Gray-Level Co-occurrence Matrix. Evolution of deforested areas, expansion of agricultural land and the increased demand for quality timber have affected the forests ecosystems and, the regional sustainable development of local communities.

Texture parameters of R2* maps are correlated with iron concentration and red blood cells count in clot analogs: A 7-T micro-MRI study

Background and purposePrevious studies have suggested that mechanical revascularization in acute ischemic stroke (AIS) patients could be affected by clot histology. In this 7-T micro-MRI study, we used R2* relaxometry of clot analogs to evaluate the relationship between texture parameters of R2* maps and clot constituents. Materials and methodsTwelve AIS clot analogs were experimentally generated to obtain a wide range of red blood cell concentrations. All clots underwent a MR acquisition using a 7-T micro-MR system. A 3D multi-echo gradient-echo sequence was performed and R2* maps were generated. First order and second order statistics of R2* histograms within the clots were calculated. Iron concentration in clots was measured using absorption spectrometry and red blood cell count (RBC) was obtained by histopathological analysis. ResultsRBC count was strongly correlated with iron concentration within clots (r=0.87, P<.001). Higher RBC count and iron concentration were significantly correlated with first order parameters including: (a) global positive shift of the R2* histogram with higher ‘10th percentile’, ‘median’, ‘mean’ and ‘90th percentile’; (b) increase of the global magnitude of voxel values with higher ‘total energy’ and ‘root mean squared’; (c) greater uniformity of the voxel values with higher ‘uniformity’ and lower ‘entropy’. Second order statistical parameters confirmed that higher RBC count and iron concentration correlated with (a) greater concentration of high gray-level values in the image; (b) more “coarse” texture of R2* maps. ConclusionsTexture analysis of MRI-R2* maps can accurately estimate the red blood cell count and iron content of AIS clot analogs.

Pixel-wise classification using support vector machine for binarization of degraded historical document image

&lt;span lang="EN-GB"&gt;Binarization&lt;/span&gt;&lt;span lang="EN-GB"&gt; of historical documents nowadays is very important as digital archiving has become the best and preferred solution for the retrieval and storage of valuable archives. However, the process becomes more challenging due to the degradation of historical documents. Hence, this paper described a method on binarization of historical documents using the learning concept. Support vector machine (SVM) learning was used as a classifier in this work. After training some images with the help of ground truth images, a model was developed. Testing images then used the model to segregate each pixel as text or non-text. The grey level and RGB values were chosen as descriptors for a particular pixel and comparisons were made between these two descriptors. The intensities of the local neighbourhood for every pixel were used in the experiment. To compare these descriptors, standard dataset HDIBCO2014, DIBCO2012 and DIBCO2016 were used in the training and testing phase. The results from the experiment clearly showed that grey level values gave better performance compared to RGB values.&lt;/span&gt;

Measurements of High Energy Cosmic Rays and Cloud presence: A method to estimate Cloud Coverage in Space and Ground-Based Infrared Images

Several projects and already-operative observatories aimed at detecting High Energy Cosmic Rays (HECR) are/will be equipped with instruments to monitor the atmosphere. Since cloud presence can affect the night-time indirect measurements of the HECRs and Cherenkov radiation, it is crucial to know the meteorological conditions during the observation period of the HECR detectors. Several meteorological satellites already provide useful information, however to obtain accurate reconstructions of the detected events it is more suitable using devices that operate synchronously with the main detector. To this purpose, infrared cameras that acquire images of the whole field of view are thought to support the atmosphere monitoring during observations from both space and ground. Meaningful parameters, like cloud coverage and cloud top/bottom height, can be retrieved from the analysis of those data. Multi-spectral information are typically analyzed and combined to obtain cloud masks for each image, where a cloudy/cloud-free probability flag is associated with each pixel. These algorithms normally use several spectral bands that are not always available in non-meteorological sensors. A different approach is presented in this paper. It only relies on the gray level values of the image pixel, and it can be applied on thermal infrared as well as visible images acquired from both space and ground. To test the method on real cloudy scenes, images from polar satellite and all-sky data archives are considered, and the results are compared to the corresponding cloudiness masks provided by the same data repositories.

Edge Detection Using Integrate and Fire Neuron

Edge detection is one of the most basic stages of image processing and have been used in many areas. Its purpose is to determine the pixels formed the objects. Many researchers have aimed to determine objects' edges correctly, like as they are determined by the human eye. In this study, a new edge detection technique based on spiking neural network is proposed. The proposed model has a different receptor structure than the ones found in literature and also does not use gray level values of the pixels in the receptive field directly. Instead, it takes the gray level differences between the pixel in the center of the receptive field and others as input. The model is tested by using BSDS train dataset. Besides, the obtained results are compared with the results calculated by Canny edge detection method.

Obtaining High-Dose-Rate $\gamma$ -Ray Detection With Commercial Off-the-Shelf CMOS Pixel Sensor Module

This paper presents the response of a commercial off-the-shelf (COTS) complementary metal–oxide–semiconductor (CMOS) active pixel sensor (APS) module to $\gamma $ -rays delivered from Cobalt-60 at a high-dose rate and evaluates its performance as a potential high-dose-rate and wide range $\gamma $ -ray detection device. The experimental results show that the rate of noise generation is not linear with respect to the total ionizing dose, and the radiation damage sustained by the sensor modules exhibits a total ionizing dose threshold. A conservative value of this threshold for the test sensor is 38 Gy. In addition, the average pixel gray level value and the proportion of pixels responding to radiation increase with increasing dose rate, and linear responses are obtained for both in the dose rate range of 5.24–69.24 Gy/h. The upper limit of the linear radiation response range depends on the capability of the COTS sensor module, while the lower limit depends on the number of radiation response events in a frame; the upper limit of the linear response range can be increased by reducing the integration time. This paper provides valuable suggestions for adopting CMOS-APSs for high-dose-rate and wide range radiation detection, and it is an important complement to our previous studies focused on the linear response of the CMOS-APS under low-dose-rate irradiation.

Evaluation of parametrial infiltration in cervical cancer with voxel-based segmentation of integrated 18F-FDG PET/MRI images: A preliminary study

PurposeTo identify parametrial infiltration (PMI) in cervical cancer with voxel-based segmentation of integrated PET/MRI images. MethodThis retrospective study enrolled 79 cervical cancer patients confirmed by pathology (FIGO stage IB to IIB) who underwent 18F-FDG PET/MRI prior to surgery. Region of interest (ROI) at the largest tumor level was delineated on the T2W-MR image, and the ROI was applied to PET image of the corresponding layer. Then, these images were postprocessed with segmentation and gray level calculations in the parauterine area. ResultsIn total, 37 patients (46.8%) had postoperative pathology-confirmed PMI, and 42 patients (53.2%) showed no PMI. There was a moderate correlation between pathological results and the gray level values of each region (rs > 0.5, P < 0.001). According to FIGO stage, as the cervical lesions became more malignant, the gray level values gradually increased.The diagnostic results of MRI and PET/MRI were in good agreement (kappa = 0.693, P < 0.001); the accuracy (78.5%), sensitivity (64.9%) and NPV (74.5%) of PET/MRI were slightly higher than those of MRI (74.7%,59.5%,71.2%, respectively), with no statistically significant difference (P = 1.000). The diagnostic results of MRI and PET/MRI+gray level values were generally consistent (kappa = 0.475, P < 0.001); the accuracy (87.3%), sensitivity(83.8%) and NPV(86.4%) of PET/MRI+gray level values were higher than those of MRI, with statistically significant differences (all P values < 0.05). ConclusionsIt is feasible to evaluate PMI based on PET/T2W-MRI voxel segmentation and to obtain quantitative and visual indicators. PET/MRI and gray level values considered together can also improve the accuracy, sensitivity and NPV of PMI diagnosis.

Extrema Points Application in Determining Iris Region of Interest

Extrema points are usually applied to solve everyday problems, for example, to determine the potential of a created tool and for optimisation. In this study, extrema points were used to help determine the region of interest (ROI) for the iris in iris recognition systems. Iris recognition is an automated method of biometric identification that uses mathematical pattern-recognition techniques on the images of one or both irises of an individual's eyes, where the complex patterns are unique, stable, and can be seen from a distance. In order to obtain accurate results, the iris must be localised correctly. Hence, to address this issue, this paper proposed a method of iris localisation in the case of ideal and non-ideal iris images. In this study, the algorithm was based on finding the classification for the region of interest (ROI) with the help of a Support Vector Machine (SVM) by applying a histogram of grey level values as a descriptor in each region from the region growing technique. The valid ROI was found from the probabilities graph of the SVM obtained by looking at the global minimum conditions determined by a second derivative model in a graph of functions. Furthermore, the model from the global minimum condition values was used in the test phase, and the results showed that the ROI image obtained helped in the elimination of sensitive noise with the involvement of fewer computations, while reserving relevant information.

Reliability and accuracy of cone beam computed tomography versus conventional multidetector computed tomography for image-guided craniofacial implant planning: An in vitro study.

To assess the reliability and accuracy of linear measurements on three-dimensional (3D) cross-sectional images, both acquired with cone beam computed tomography (CBCT) and multi-detector row CT (MDCT). Bone thickness was evaluated with regard to image-guided planning of craniofacial implant surgery. Five dry human skulls were used. Cuts were made with a circular bone saw at the ideal implant positions in the nasal, orbital, and temporal regions prior to acquisition of CBCT and MDCT scans. After imaging examination, bone width was assessed by three independent observers using a caliper and defined as a reference. In the next step, cross-sectional images of the regions with the aforementioned cuts were reconstructed from 3D virtual models generated from the digital DICOM datasets with the use of 3D image-based planning software. Subsequently, linear measurements were performed. The systematic difference and interobserver and intraobserver variation of MDCT and CBCT linear measurements were compared with the physical measurements at different locations in the nasal, orbital, and temporal region, respectively. Also, the potential influence of different gray-level values was investigated. The quantitative accuracy of distance measurements was performed using a two-way analysis of variance (ANOVA) and variance component analyses. Only differences with P values < .05 were considered significant. All radiologic measurements showed a significant overestimation of the bony dimensions, reaching more than the used voxel sizes of 0.3 mm for CBCT and 0.5 mm for MDCT. For CBCT, an average measurement bias of 0.39 to 0.53 mm and for MDCT of 0.57 to 0.59 mm was found. MDCT images showed less interobserver variation in linear measurements on cross-sectional images from 3D virtual models compared with CBCT images. Contrast settings statistically significantly influenced linear measurements of bone width for CBCT images (P < .0015) and interobserver variation on MDCT imaging (P < .029). Both CBCT images (KaVo 3D eXam Imaging System) and MDCT images (Aquilion ONE, Toshiba) showed a highly consistent submillimeter overestimation of the anatomical truth in assessing bone thickness of nasal, orbital, and temporal regions of ex vivo specimens. When using CBCT and MDCT images for presurgical assessment, one should be aware of the overestimation of the cortical bone thickness.

Detecting bone changes along dental implants, after immediate or delayed loading, using digital subtraction on cropped panoramic radiographs. A prospective clinical trial with minimum 3-year follow up

Aim The aim of this study was to assess bone changes along implants after immediate or delayed loading, using subtractions of digital images originated from cropped panoramic radiographs and visual evaluation. Materials and methods Eleven patients received 4 Ankylos implants interforaminal in the mandible. In 7 patients the implants were loaded immediately and 4 followed delayed loading. All patients were restored with a telescopic overdenture with Syncone abutments. From each patient 3 panoramic radiographs (PRs) were obtained: upon delivery of the restoration (T1), 6 months later (T2) and after 3 years (T3). 33 implants were finally selected. The radiographs were analyzed using the Emago® Software. The grey scale values were measured either manually (Stage A) or automatically (Stage B) in six areas (neck, middle and apex; both mesially and distally) along the implants’ sides to evaluate the bone density during clinical function. Images were also visually evaluated by five observers to detect bone changes at the cervical implant area. Results Strong positive correlation between the two stages (A and B) was found in all 3 examinations (Pearson’s r 0.84-0.98). The t-test showed no statistically significant differences in grey level values between immediate and delayed loading (p<0.05) and no statistically significant changes in the visual evaluation among implants undergoing either immediately or delayed loading (p<0.05). Conclusions Emago® is a valuable method for bone level assessment around implants’ neck. The grey value measurements of the bone adjacent to the implants that have been loaded either immediately or delayed do not significantly differ after 3 years of fuction. The visual assessment of the PRs images supports these findings.

Application of Gray Level Co-Occurrence Matrix Analysis as a New Method for Enzyme Histochemistry Quantification.

Enzyme histochemistry is a valuable histological method which provides a connection between morphology, activity, and spatial localization of investigated enzymes. Even though the method relies purely on arbitrary evaluations performed by the human eye, it is still wildly accepted and used in histo(patho)logy. Texture analysis emerged as an excellent tool for image quantification of subtle differences reflected in both spatial discrepancies and gray level values of pixels. The current study of texture analysis utilizes the gray-level co-occurrence matrix as a method for quantification of differences between ecto-5'-nucleotidase activities in healthy hippocampal tissue and tissue with marked neurodegeneration. We used the angular second moment, contrast (CON), correlation, inverse difference moment (INV), and entropy for texture analysis and receiver operating characteristic analysis with immunoblot and qualitative assessment of enzyme histochemistry as a validation. Our results strongly argue that co-occurrence matrix analysis could be used for the determination of fine differences in the enzyme activities with the possibility to ascribe those differences to regions or specific cell types. In addition, it emerged that INV and CON are especially useful parameters for this type of enzyme histochemistry analysis. We concluded that texture analysis is a reliable method for quantification of this descriptive technique, thus removing biases and adding it a quantitative dimension.