Set Of Pixels Research Articles

Fully automated background phase correction using M-estimate SAmple consensus (MSAC)-Application to2Dand 4D flow.

Flow quantification by phase-contrast MRI is hampered by spatially varying background phase offsets. Correction performance by polynomial regression on stationary tissue may be affected by outliers such as wrap-around or constant flow. Therefore, we propose an alternative, M-estimate SAmple Consensus (MSAC) to reject outliers, and improve and fully automate background phase correction. The MSAC technique fits polynomials to randomly drawn small samples from the image. Over several trials, it aims to find the best consensus set of valid pixels by rejecting outliers to the fit and minimizing the residuals of the remaining pixels. The robustness of MSAC to its few parameters was investigated and verified using third-order polynomial correction fits on a total of 118 2D flow (97 with wrap-around) and 18 4D flow data sets (14 with wrap-around), acquired at 1.5 T and 3T. Background phase was compared with standard stationary correction and phantom correction. Pulmonary/systemic flow ratios in 2D flow were derived, and exemplary 4D flow analysis was performed. The MSAC technique is robust over a range of parameter choices, and a unique set of parameters is suitable for both 2D and 4D flow. In 2D flow, phase errors were significantly reduced by MSAC compared with stationary correction (p=0.005), and stationary correction shows larger errors in pulmonary/systemic flow ratios compared with MSAC. In 4D flow, MSAC shows similar performance as stationary correction. The MSAC method provides fully automated background phase correction to 2D and 4D flow data and shows improved robustness over stationary correction, especially with outliers present.

Multi-view density-based field-road classification for agricultural machinery: DBSCAN and object detection

Field-road classification that automatically identifies the operation modes (either in-field or on-road) of GNSS (Global Navigation Satellite System) points plays an important role for the operational performance analysis of agricultural vehicles. Intuitively, a field often has high point density because in-field driving speed is rather low and the distance between consecutive strips is closed. In this paper, two methods were used to capture the in-field high-density characteristic: DBSCAN (Density-Based Spatial Clustering of Applications with Noise) and an object detection model. DBSCAN is a widely-used density-based clustering algorithm, which clusters the points with high point density into a cluster. Alternatively, a trajectory can be transformed into an image, and an object detection model can be applied to detect objects in the image, where an object is a set of pixels with high pixel density (i.e., a set of points with high point density). Finally, the two field-road classification results are combined using DBI (Davis Bouldin index), a metric which can evaluate the quality of either classification result. The developed method was validated by the harvesting trajectories of two crops (wheat and paddy), and the density-based field-road classification achieved 85.97% and 73.34% accuracy on the wheat data and the paddy data, respectively.

Balanced pixel interpolation algorithm when identifying the object’s contours on the borders of the image

The operation of algorithms for identifying object’s contours using two-dimensional convolution operation on the boundaries of raster images depends entirely on the location of the transformed pixel in the pixel matrix. The problem is related to the need for the convolution algorithm itself to use an additional set of pixels located outside the pixel matrix of the processed image [1, 2, 3]. In this paper, an algorithm for balanced interpolation of pixels at image boundaries in addition to algorithms based on statistical averages [4, 5] is proposed. Various sets of coefficients which are located at a certain pixel layout and participate in the interpolation algorithm is considered. A comparative analysis of the results of the balanced interpolation algorithm with the results using the arithmetic mean methods is carried out. Also, an example of using a new algorithm to solve the problem of the object’s contours identification on the borders of a raster halftone image is presented. The described algorithm is easy to understand, use and integrate with other algorithms and it does not require significant computing power.

Design of an optimized fuzzy system for edge detection in images

Edge Detection is the first stage in the image division into separate parts. Image division is the partitioning of a digital image to the different zones or the set of pixels. Edge detection is one of the techniques applied in digital image processing often. The purpose of detecting pixels is to match the edges in the image. Filtering, Enhancement, and Detection are three steps in edge detection. Images are usually destroyed by casual changes in intensity intervals called noise or confusion. some noise variations include salt and pepper, pulse, and Gaussian. However, there is a relation between edge detection power and noise reduction. Using filters to the noise reduction causes the loss of edge detection power. For facilitating the edges detection, it is essential for the determination of pixels’ intensity constraints in their neighborhood. Many points in an image have a nontransparent slope, and all of them are not the edges of the joint space. Therefore, some of the linear and nonlinear methods such as Sobel, Prewitt, and Robert have to be used to determine the edge points. The fuzzy logic and the system based on it, is one of the most effective methods for edge detection. This paper presents an optimized rule-based fuzzy inference system and designs the efficiency mask matric. The simulation results for edge detection are presented using the traditional edge detection techniques, including Binary Filter, Sobel Filter, Prewitt Filter, and Robert Filter. Also, it is presented using the fuzzy approach. The simulation results show that the designed fuzzy system has been able to detect the edges of the image more accurately and help to increase the sharpness and quality of the edges. Therefore, the proposed method has more accurate and more reliable results and reduces false edge detection comparison to the traditional methods.

Compressive Domain Deep CNN for Image Classification and Performance Improvement Using Genetic Algorithm-Based Sensing Mask Learning

The majority of digital images are stored in compressed form. Generally, image classification using convolution neural network (CNN) is done in uncompressed form rather than compressed one. Training the CNN in the compressed domain eliminates the requirement for decompression process and results in improved efficiency, minimal storage, and lesser cost. Compressive sensing (CS) is one of the effective and efficient method for signal acquisition and recovery and CNN training on CS measurements makes the entire process compact. The most popular sensing phenomenon used in CS is based on image acquisition using single pixel camera (SPC) which has complex design implementation and usually a matrix simulation is used to represent the SPC process in numerical demonstration. The CS measurements using this phenomenon are visually different from the image and to add this in the training set of the compressed learning framework, there is a need for an inverse SPC process that is to be applied all through the training and testing dataset image samples. In this paper we proposed a simple sensing phenomenon which can be implemented using the image output of a standard digital camera by retaining few pixels and forcing the rest of the pixels to zero and this reduced set of pixels is assumed as CS measurements. This process is modeled by a binary mask application on the image and the resultant image still subjectively legible for human vision and can be used directly in the training dataset. This sensing mask has very few active pixels at arbitrary locations and there is a lot of scope to heuristically learn the sensing mask suitable for the dataset. Only very few attempts had been made to learn the sensing matrix and the sole effect of this learning process on the improvement of CNN model accuracy is not reported. We proposed to have an ablation approach to study how this sensing matrix learning improves the accuracy of the basic CNN architecture. We applied CS for two class image dataset by applying a Primitive Walsh Hadamard (PWH) binary mask function and performed the classification experiment using a basic CNN. By retaining arbitrary amount of pixel in the training and testing dataset we applied CNN on the compressed measurements to perform image classification and studied and reported the model performance in terms of training and validation accuracies by varying the amount of pixels retained. A novel Genetic Algorithm-based compressive learning (GACL) method is proposed to learn the PWH mask to optimize the model training accuracy by using two different crossover techniques. In the experiment conducted for the case of compression ratio (CR) 90% by retaining only 10% of the pixels in every images both in training and testing dataset that represent two classes, the training accuracy is improved from 67% to 85% by using diagonal crossover in offspring creation of GACL. The robustness of the method is examined by applying GACL for user defined multiclass dataset and achieved better CNN model accuracies. This work will bring out the strength of sensing matrix learning which can be integrated with advanced training models to minimize the amount of information that is to be sent to central servers and will be suitable for a typical IoT frame work.

LUNG SCANS SEGMENTATION USING MARKER-CONTROLLED WATERSHED TRANSFORMATION

Image segmentation is the process of partitioning a digital image into multiple segments knows as set of pixels. Image segmentation is typically used to locate objects and boundaries (lines, curves, etc.) in images. It is the process of assigning a label to every pixel in an image such that pixels with the same label share certain visual characteristics. The Watershed Transform consists of an image partitioning into its constitutive regions. This transform is easily adapted to be used in different types of images and it allows distinguishing complex objects. The marker watershed transformation is an improvement one on the basis of the watershed transform, which is set a tag in the image. The tag can be a point, a line or an area, the importance is its location instead of the marked shape. Each tag represents the image of a final partition and selecting a tag is a key factor in the decision segmentation.

DuMLP-Pin: A Dual-MLP-Dot-Product Permutation-Invariant Network for Set Feature Extraction

Existing permutation-invariant methods can be divided into two categories according to the aggregation scope, i.e. global aggregation and local one. Although the global aggregation methods, e. g., PointNet and Deep Sets, get involved in simpler structures, their performance is poorer than the local aggregation ones like PointNet++ and Point Transformer. It remains an open problem whether there exists a global aggregation method with a simple structure, competitive performance, and even much fewer parameters. In this paper, we propose a novel global aggregation permutation-invariant network based on dual MLP dot-product, called DuMLP-Pin, which is capable of being employed to extract features for set inputs, including unordered or unstructured pixel, attribute, and point cloud data sets. We strictly prove that any permutation-invariant function implemented by DuMLP-Pin can be decomposed into two or more permutation-equivariant ones in a dot-product way as the cardinality of the given input set is greater than a threshold. We also show that the DuMLP-Pin can be viewed as Deep Sets with strong constraints under certain conditions. The performance of DuMLP-Pin is evaluated on several different tasks with diverse data sets. The experimental results demonstrate that our DuMLP-Pin achieves the best results on the two classification problems for pixel sets and attribute sets. On both the point cloud classification and the part segmentation, the accuracy of DuMLP-Pin is very close to the so-far best-performing local aggregation method with only a 1-2% difference, while the number of required parameters is significantly reduced by more than 85% in classification and 69% in segmentation, respectively. The code is publicly available on https://github.com/JaronTHU/DuMLP-Pin.

Part-Based Obstacle Detection Using a Multiple Output Neural Network.

Detecting the objects surrounding a moving vehicle is essential for autonomous driving and for any kind of advanced driving assistance system; such a system can also be used for analyzing the surrounding traffic as the vehicle moves. The most popular techniques for object detection are based on image processing; in recent years, they have become increasingly focused on artificial intelligence. Systems using monocular vision are increasingly popular for driving assistance, as they do not require complex calibration and setup. The lack of three-dimensional data is compensated for by the efficient and accurate classification of the input image pixels. The detected objects are usually identified as cuboids in the 3D space, or as rectangles in the image space. Recently, instance segmentation techniques have been developed that are able to identify the freeform set of pixels that form an individual object, using complex convolutional neural networks (CNNs). This paper presents an alternative to these instance segmentation networks, combining much simpler semantic segmentation networks with light, geometrical post-processing techniques, to achieve instance segmentation results. The semantic segmentation network produces four semantic labels that identify the quarters of the individual objects: top left, top right, bottom left, and bottom right. These pixels are grouped into connected regions, based on their proximity and their position with respect to the whole object. Each quarter is used to generate a complete object hypothesis, which is then scored according to object pixel fitness. The individual homogeneous regions extracted from the labeled pixels are then assigned to the best-fitted rectangles, leading to complete and freeform identification of the pixels of individual objects. The accuracy is similar to instance segmentation-based methods but with reduced complexity in terms of trainable parameters, which leads to a reduced demand for computational resources.

An Efficient Reversible Digital Oil Painting Technique for Smartphone and Tablet Users

With the increase in mobility in technology, artists are looking for ways to create paintings using their tablets and smartphones while on the move. Digital oil painting is a revolutionary technique where an artist uses digital paintbrush to simulate the traditional bristle paintbrush of a painting to get an oil paint image. In this article, we propose a novel realistic technique for reversible digital oil painting to accelerate the users to (re)paint an oil paint image to convey the surrounding atmosphere, express their emotions and feelings, or showcase a time of day or type of weather through that painting. Realism is all about accuracy. To repaint, the original image is retrieved from the existing oil paint image by reversing the pixels to its original value. We derive a mathematical expression to determine the probability of a pixel, with a set of neighbor pixels, being oil painted to get an oil paint image of the desired quality, which reduces the time and space complexities of the technique. We also develop prototypes on Android, Windows, and Ubuntu operating systems that successfully implement the proposed technique.

On the exhaustive generation of discrete figures with connectivity constraints

Abstract This paper deals with a generalization of polyominoes called (a, b)-connected discrete figures, where a and b respectively denotes the connectivity of the foreground (i.e. black pixels) and background (i.e. white pixels). Formally, a finite set of pixels P is (a, b)-connected if P is a-connected and P̄ is b-connected. By adapting a combinatorial structure enumeration algorithm due to Martin, we successfully generate (a, b)-connected discrete figures up to size n = 18.

EVALUATION OF PIXEL SELECTION METHODS FOR TRAFFIC INFRASTRUCTURE MONITORING USING SENTINEL-1 INSAR

Abstract. The Synthetic Aperture Radar (SAR) satellite Sentinel-1 provides excellent traffic infrastructure monitoring capabilities due to its short revisit time, wide-scale coverage and free of charge data policy. However, pixels from Sentinel-1 have a medium spatial resolution so that traffic infrastructure is only covered by a few pixels. Moreover, Interferometric Synthetic Aperture Radar (InSAR) yields deformation time series for coherent pixels only, thus limiting the number of pixels reporting the ground motion at traffic infrastructure. Although various InSAR time series methods have been successfully applied for traffic infrastructure monitoring, the selection of appropriate methods achieving a high pixel density has not yet been evaluated. In this study, we test whether we can improve the monitoring capabilities by combining different InSAR time series methods. On the one hand, we applied widely used Stanford Method for Persistent Scatterers (StaMPS) as a baseline method to retrieve the deformation time series. On the other hand, we enhanced the phase quality in a pre-processing step using the Phase-Linking (PL) approach and afterwards estimated the deformation time series also with StaMPS based on pixels selected by PL. We compared and evaluated the achieved pixel densities from both methods at main roads, highways and railways in a study area in Germany. We found that the InSAR time series methods selected complementary sets of pixels at all traffic infrastructure types. Moreover, the results indicate a great potential for railway monitoring using Sentinel-1 InSAR due to both high pixel density and homogeneous spatial distribution of pixels. Interestingly, coherent scatterers selected by StaMPS were observed to coincide with large traffic signs at highways which show a double-bounce scattering in the amplitude images. This study shows the benefits of combining PL and StaMPS for increased pixel density at traffic infrastructure and confirms Sentinel-1 data as a suitable data source for traffic infrastructure monitoring.

DEVELOPMENT OF THE ARCHITECTURE OF DOCUMENT OPTICAL CHARACTER RECOGNITION SYSTEM

This paper aims to develop information technology for document optical character recognition systems. The difficulty of processing images, which are a set of pixels, causes inconvenience in working with such data. This problem can be solved in different ways: usual mathematical approaches, a single complicated neural network, and a set of problem-specific deep neural networks. Usual mathematical approaches perform poor with unstructured data like images. A single neural network is like a swiss knife: it can do many tasks, but none with the best quality. So we will use two different deep neural networks, each for the appropriate part of the problem. The critical elements of this technology are the module for text detection and segmentation of the image, the module for text recognition in Ukrainian and English languages, the module for parsing multiple keywords, and the module for searching for the final data. The first and second modules consist of several machine learning models with specific architecture, depending on their task. All trained models are tested for accuracy and noise resistance and will be used in the future for searching required data from different document images. Output data of the developed system provide speedup, automation processing images and scans of the documents, reduce the number of mistakes caused by human factor. All data is converted from image pixels into a structured text set represented in the document, which the machine can easily use. We can use such technology in banking and insurance, where we can send images of documents and they will be automatically processed and converted into user name, surname, date of birth, serial number, and required fields for specific services.

Trainable segmentation for transmission electron microscope images of inorganic nanoparticles.

We present a trainable segmentation method implemented within the python package ParticleSpy. The method takes user labelled pixels, which are used to train a classifier and segment images of inorganic nanoparticles from transmission electron microscope images. This implementation is based on the trainable Waikato Environment for Knowledge Analysis (WEKA) segmentation, but is written in python, allowing a large degree of flexibility and meaning it can be easily expanded using other python packages. We find that trainable segmentation offers better accuracy than global or local thresholding methods and requires as few as 100 user-labelled pixels to produce an accurate segmentation. Trainable segmentation presents a balance of accuracy and training time between global/local thresholding and neural networks, when used on transmission electron microscope images of nanoparticles. We also quantitatively investigate the effectiveness of the components of trainable segmentation, its filter kernels and classifiers, in order to demonstrate the use cases for the different filter kernels in ParticleSpy and the most accurate classifiers for different data types. A set of filter kernels is identified that are effective in distinguishing particles from background but that retain dissimilar features. In terms of classifiers, we find that different classifiers perform optimally for different image contrast; specifically, a random forest classifier performs best for high-contrast ADF images, but that QDA and Gaussian Naïve Bayes classifiers perform better for low-contrast TEM images.

Noise level and similarity evaluations of non-local means algorithm in chest digital tomosynthesis X-ray imaging system: An experimental study

As a method for diagnosing chest lesions, a chest digital tomosynthesis (CDT) X-ray imaging system based on projection data using a limited angle has been widely used in the medical field since its development. In these CDT X-ray images, noise reduction methods using software that reduce the accuracy of lesion detection are essential. The aim of this study is to model the non-local means (NLM)-based algorithm, which is known to be very effective in removing noise from X-ray images, and to confirm its applicability in the CDT system. CDT X-ray images using a human phantom were generated employing the filtered back-projection reconstruction method with a projection angle of ±36.15°. For quantitative evaluation, a reference image was obtained using the full radiation dose, and a noisy image was obtained using the minimum radiation dose to increase the amount of noise. The NLM noise reduction algorithm was modeled as a method for obtaining weights based on the similarity of the neighboring set of pixels. Conventional filtering methods were used in the comparison group to analyze the efficiency of the NLM algorithm. As a result, we confirmed that the coefficient of variation of the noise level was improved about 9.74 times compared with the noisy image when the NLM noise reduction algorithm was applied to the CDT X-ray image. When the similarity evaluation parameters were measured, we proved that 11%–53% better values were derived compared with the noisy image in the NLM algorithm. In particular, the performance of the NLM algorithm showed superior results to those obtained with the conventional filtering methods. In conclusion, the applicability of the NLM noise reduction algorithm to CDT X-ray images using limited projection data was demonstrated.

2D Wavelet Tree Ordering Based Localized Total Variation Model for Efficient Image Restoration

The degraded image during the process of image analysis needs more number of iterations to restore it. These iterations take long waiting time and slow scanning, resulting in inefficient image restoration. A few numbers of measurements are enough to recuperate an image with good condition. Due to tree sparsity, a 2D wavelet tree reduces the number of coefficients and iterations to restore the degraded image. All the wavelet coefficients are extracted with overlaps as low and high sub-band space and ordered them such that they are decomposed in the tree ordering structured path. Some articles have addressed the problems with tree sparsity and total variation (TV), but few authors endorsed the benefits of tree sparsity. In this paper, a spatial variation regularization algorithm based on tree order is implemented to change the window size and variation estimators to reduce the loss of image information and to solve the problem of image smoothing operation. The acceptance rate of the tree-structured path relies on local variation estimators to regularize the performance parameters and update them to restore the image. For this, the Localized Total Variation (LTV) method is proposed and implemented on a 2D wavelet tree ordering structured path based on the proposed image smooth adjustment scheme. In the end, a reliable reordering algorithm proposed to reorder the set of pixels and to increase the reliability of the restored image. Simulation results clearly show that the proposed method improved the performance compared to existing methods of image restoration.

Brain Tumor Segmentation and Classification from MRI Images using Improved FLICM Segmentation and SCA Weight Optimized Wavelet-ELM Model

Image segmentation is an essential technique of brain tumor MRI image processing for automated diagnosis of an image by partitioning it into distinct regions referred to as a set of pixels. The classification of the tumor affected and non-tumor becomes an arduous task for radiologists. This paper presents a novel image enhancement based on the SCA (Sine Cosine Algorithm) optimization technique for the improvement of image quality. The improved FLICM (Fuzzy Local Information C Means) segmentation technique is proposed to detect the affected regions of brain tumor from the MRI brain tumor images and reduction of noise from the MRI images by introducing a fuzzy factor to the objective function. The SCA weight-optimized Wavelet-Extreme Learning Machine (SCA-WELM) model is also proposed for the classification of benign tumors and malignant tumors from MRI brain images. In the first instance, the enhanced images are undergone improved FLICM Segmentation. In the second phase, the segmented images are utilized for feature extraction. The GLCM feature extraction technique is considered for feature extraction. The extracted features are aligned as input to the SCA-WELM model for the classification of benign and malignant tumors. The following dataset (Dataset-255) is considered for evaluating the proposed classification approach. An accuracy of 99.12% is achieved by the improved FLICM segmentation technique. The classification performance of the SCA-WELM is measured by sensitivity, specificity, accuracy, and computational time and achieved 0.98, 0.99, 99.21%, and 97.2576 seconds respectively. The comparison results of SVM (Support Vector Machine), ELM, SCA-ELM, and proposed SCA-WELM models are presented to show the robustness of the proposed SCA-WELM classification model.

Stochastic Higher-Order Independent Component Analysis for Hyperspectral Dimensionality Reduction

Hyperspectral imaging is a remote sensing technique that measures the spectrum of each pixel in the image of a scene. Various methods have been developed to reduce the spectral dimension of hyperspectral images in order to facilitate their analysis. Independent Component Analysis (ICA) is a class of algorithms which extract statistically independent features. FastICA, is one of the most used ICA algorithms because it is simple and fast. However, FastICA often finds irrelevant stationary points (e.g., minima instead of maxima) and is not scalable as it uses at each iteration the whole set of pixels. In this paper, we present a new stochastic algorithm, called SHOICA, which smoothly approximates the non-convex loss functions of ICA using higher-order Taylor minorizers. Because SHOICA guarantees ascent of its objective function, it identifies (local) maxima. Moreover, because SHOICA is stochastic, it facilitates minibatching and thus is scalable and appropriate for large datasets. Hence, we show that our method is faster and the extracted features are better than those of FastICA. The quality of features extracted, as well as time and epochs required by FastICA and SHOICA are compared practically, on dimensionality reduction and classification tasks of real hyperspectral images.

Recognition method of unspecified face expressions based on machine learning

Traditional face recognition methods usually complete facial expression recognition for designated faces, and the pixel set at the edge of face image is chaotic, which leads to poor accuracy of unspecified facial expression recognition. In order to improve the accuracy of unknown facial expression recognition, a method of unknown facial expression recognition based on machine learning is proposed. The feature detection model of unspecified facial expressions is constructed, and the features are divided into regional blocks. Fusion block feature information establishes a spatial feature projection model, weights the feature information entropy, extracts statistical features and edge information entropy features, reorganises features and matching edge pixel sets and completes the recognition of various facial expression features. Experimental results show that the accuracy of this method is significant, reaching 1, which effectively improves the recognition efficiency and anti-interference performance.

Edge Tracing Using Gaussian Process Regression.

We introduce a novel edge tracing algorithm using Gaussian process regression. Our edge-based segmentation algorithm models an edge of interest using Gaussian process regression and iteratively searches the image for edge pixels in a recursive Bayesian scheme. This procedure combines local edge information from the image gradient and global structural information from posterior curves, sampled from the model's posterior predictive distribution, to sequentially build and refine an observation set of edge pixels. This accumulation of pixels converges the distribution to the edge of interest. Hyperparameters can be tuned by the user at initialisation and optimised given the refined observation set. This tunable approach does not require any prior training and is not restricted to any particular type of imaging domain. Due to the model's uncertainty quantification, the algorithm is robust to artefacts and occlusions which degrade the quality and continuity of edges in images. Our approach also has the ability to efficiently trace edges in image sequences by using previous-image edge traces as a priori information for consecutive images. Various applications to medical imaging and satellite imaging are used to validate the technique and comparisons are made with two commonly used edge tracing algorithms.

Experimental study of the adaptive gain feature for improved position-sensitive ion spectroscopy with Timepix2

In the present work, we study the Timepix2 pixels’ high energy response in the so-called adaptive gain mode. Therefore, Timepix2 with a 500 μm thick silicon sensor was irradiated with protons of energies in the range from 400 keV to 2 MeV and α-particles of 5.5 MeV from 241Am. A novel method was developed to determine the energy deposit in single pixels of particle imprints, which are spread out over a set of neighbor pixels (cluster). We show that each pixel is capable of measuring the deposited energy from 4 keV up to ∼3.2 MeV. Reconstructing the full energy content of the clusters, we found relative energy resolutions () better than 2.7% and better than 4% for proton and α-particle data, respectively. In a simple experiment with a 5.5 MeV α-particle source, we demonstrate that energy losses in thin (organic) specimen can be spatially resolved, mapping out sample thickness variations, with a resolution around 1–2 μm, across the sensor area. The inherent spatial resolution of the device was determined to be 350 nm in the best case.