Development Of Image Processing Algorithms Research Articles

VORONOI-BASED SKELETONIZATION ALGORITHM FOR SEGMENTING THE NETWORK OF BIOLOGICAL NEURONS

Context. The problem of automated processing and analysis of microscopy image data is of high relevance due to its extreme impact on the research and recent developments in the field of biology and medicine. Efficient image processing algorithms facilitate the development of new medical diagnostic tools and therapy processes. They help us to broaden our knowledge of underlying mechanisms and processes inside living organisms. The primal focus of this paper is the processing of the microscopy images of the biological neural network. This aims to facilitate further studies of biological neural network that would lead to the development of better methods for diagnosis, prevention and cure of the related deceases. Objective. The goal of the work is to development of an efficient image processing algorithm for segmenting the network of biological neurons based on the fluorescent microscopy image data. Method. The introduced algorithm for segmenting the network of biological neurons comprises several steps. Firstly, we apply image processing routines, which aim to enhance the quality of the image data and extract the contours of the biological neural network. Then we construct the skeleton of the network applying the Voronoi diagram for line segments extracted from the object’s contours. We employ Voronoi skeleton to identify the cellular somas and differentiate them from axons and dendrites. Results. The developed Voronoi-based algorithm allows us to segment individual neurons, localize their somas, axons and dendrites and extract graph representation of the neural network. The underlying Voronoi diagram data structure allows us to compute such graph efficiently in O(N log N) operations (where N is a number of contour points). The proposed segmentation method was implemented in the C++/Python programming language and evaluated on the fluorescent images from CellImageLibrary (CIL). Conclusions. The proposed segmentation method aims to facilitate studies of biological neural networks. It computes segmentation of the network of biological neurons in O(N log N) operations using the Voronoi diagram data structure. This data structure, in turn, gives us an attributed graph representation of the segmented network. Therefore, classical graph processing algorithms can be applied to analyze the neural and compute such network’s characteristics as the number of connections between individual neurons, the shortest signal transduction path between two neurons, etc.

BubGAN: Bubble generative adversarial networks for synthesizing realistic bubbly flow images

Bubble segmentation and size detection algorithms have been developed in recent years for their high efficiency and accuracy in measuring bubbly two-phase flows. In this work, we proposed an architecture called bubble generative adversarial networks (BubGAN) for the generation of realistic synthetic images which could be further used as training or benchmarking data for the development of advanced image processing algorithms. The BubGAN is trained initially on a labeled bubble dataset consisting of ten thousand images. By learning the distribution of these bubbles, the BubGAN can generate more realistic bubbles compared to the conventional models used in the literature. The trained BubGAN is conditioned on bubble feature parameters and has full control of bubble properties in terms of aspect ratio, rotation angle, circularity and edge ratio. A million bubble dataset is pre-generated using the trained BubGAN. One can then assemble realistic bubbly flow images using this dataset and associated image processing tool. These images contain detailed bubble information, therefore do not require additional manual labeling. This is more useful compared with the conventional GAN which generates images without labeling information. The tool could be used to provide benchmarking and training data for existing image processing algorithms and to guide the future development of bubble detecting algorithms.

Development of a Peanut Canopy Measurement System Using a Ground-Based LiDAR Sensor.

Plant architecture characteristics contribute significantly to the microclimate within peanut canopies, affecting weed suppression as well as incidence and severity of foliar and soil-borne diseases. However, plant canopy architecture is difficult to measure and describe quantitatively. In this study, a ground-based LiDAR sensor was used to scan rows of peanut plants in the field, and a data processing and analysis algorithm was developed to extract feature indices to describe the peanut canopy architecture. A data acquisition platform was constructed to carry the ground-based LiDAR and an RGB camera during field tests. An experimental field was established with three peanut cultivars at Oklahoma State University's Caddo Research Station in Fort Cobb, OK in May and the data collections were conducted once each month from July to September 2015. The ground-based LiDAR used for this research was a line-scan laser scanner with a scan-angle of 100°, an angle resolution of 0.25°, and a scanning speed of 53 ms. The collected line-scanned data were processed using the developed image processing algorithm. The canopy height, width, and shape/density were evaluated. Euler number, entropy, cluster count, and mean number of connected objects were extracted from the image and used to describe the shape of the peanut canopies. The three peanut cultivars were then classified using the shape features and indices. A high correlation was also observed between the LiDAR and ground-truth measurements for plant height. This approach should be useful for phenotyping peanut germplasm for canopy architecture.

An innovative person detection system based on thermal imaging cameras dedicate for underground belt conveyors

Within the INESI-project (Increasing Efficiency and Safety Improvement in Underground Mining Transportation Routes) long-wavelength infrared (LWIR) cameras are used for detecting persons on underground belt conveyors or within hazardous areas e.g. in front of crusher or skip vessels by the project partners KOMAG and the Institute for Advanced Mining Technologies (AMT). The test case for evaluating the performance of thermal imaging regarding these applications is the Polish Sobieski underground coal mine operated by Tauron mining company. By the development of thermal image processing algorithms, an automated detection of persons and classification of different objects was achieved. This may allow implementing smart services for person detection on underground belt conveyors as well as material characterization between coal, rock and disturbing objects on belt conveyors.

New image processing algorithm for terminal guidance of multiple kinetic-energy impactors for disrupting hazardous asteroids

This paper describes the preliminary study results of developing a hypervelocity terminal intercept guidance system of a multiple kinetic-energy impactor vehicle (MKIV). The proposed MKIV system is intended to fragment or pulverize an asteroid of smaller than approximately 150 m in diameter that is detected with a mission lead time of shorter than 10 years, without using nuclear explosive devices. This paper focuses on the development of a new image processing algorithm based on Otsu’s method for the coordinated terminal intercept guidance and control of multiple kinetic-energy impactors employing visual and/or infrared sensors. A scaled polyhedron shape model of asteroid (216) Kleopatra is used as a fictional target asteroid. GPU-based simulation results demonstrate the feasibility of impacting a small irregular-shaped asteroid by using the proposed new image processing algorithm and a classical pulsed TPN (true proportional navigation) terminal guidance law.

Vision-based system for long-term remote monitoring of large civil engineering structures: design, testing, evaluation

This paper presents a full research and development cycle of a vision-based system for long-term remote monitoring of civil engineering constructions. To measure displacements, the system analyzes reference mark position using a developed image processing algorithm. All computational operations are performed by FPGA to ensure high performance. The developed monitoring system has an accuracy of 0.45 mm (3 standard deviations) at the distance up to 50 m. The measurement error remains within this value even in harsh environments. The value of this paper is formed by the possibility of stable 24/7 monitoring in low-temperature conditions (up to C).

Rapeseed Seedling Stand Counting and Seeding Performance Evaluation at Two Early Growth Stages Based on Unmanned Aerial Vehicle Imagery.

The development of unmanned aerial vehicles (UAVs) and image processing algorithms for field-based phenotyping offers a non-invasive and effective technology to obtain plant growth traits such as canopy cover and plant height in fields. Crop seedling stand count in early growth stages is important not only for determining plant emergence, but also for planning other related agronomic practices. The main objective of this research was to develop practical and rapid remote sensing methods for early growth stage stand counting to evaluate mechanically seeded rapeseed (Brassica napus L.) seedlings. Rapeseed was seeded in a field by three different seeding devices. A digital single-lens reflex camera was installed on an UAV platform to capture ultrahigh resolution RGB images at two growth stages when most rapeseed plants had at least two leaves. Rapeseed plant objects were segmented from images of vegetation indices using typical Otsu thresholding method. After segmentation, shape features such as area, length-width ratio and elliptic fit were extracted from the segmented rapeseed plant objects to establish regression models of seedling stand count. Three row characteristics (the coefficient of variation of row spacing uniformity, the error rate of the row spacing and the coefficient of variation of seedling uniformity) were further calculated for seeding performance evaluation after crop row detection. Results demonstrated that shape features had strong correlations with ground-measured seedling stand count. The regression models achieved R-squared values of 0.845 and 0.867, respectively, for the two growth stages. The mean absolute errors of total stand count were 9.79 and 5.11% for the two respective stages. A single model over these two stages had an R-squared value of 0.846, and the total number of rapeseed plants was also accurately estimated with an average relative error of 6.83%. Moreover, the calculated row characteristics were demonstrated to be useful in recognizing areas of failed germination possibly resulted from skipped or ineffective planting. In summary, this study developed practical UAV-based remote sensing methods and demonstrated the feasibility of using the methods for rapeseed seedling stand counting and mechanical seeding performance evaluation at early growth stages.

Imaging and analysis of a three-dimensional spider web architecture.

Spiders are abundantly found in nature and most ecosystems, making up more than 47 000 species. This ecological success is in part due to the exceptional mechanics of the spider web, with its strength, toughness, elasticity and robustness, which originate from its hierarchical structures all the way from sequence design to web architecture. It is a unique example in nature of high-performance material design. In particular, to survive in different environments, spiders have optimized and adapted their web architecture by providing housing, protection, and an efficient tool for catching prey. The most studied web in literature is the two-dimensional (2D) orb web, which is composed of radial and spiral threads. However, only 10% of spider species are orb-web weavers, and three-dimensional (3D) webs, such as funnel, sheet or cobwebs, are much more abundant in nature. The complex spatial network and microscale size of silk fibres are significant challenges towards determining the topology of 3D webs, and only a limited number of previous studies have attempted to quantify their structure and properties. Here, we focus on developing an innovative experimental method to directly capture the complete digital 3D spider web architecture with micron scale resolution. We built an automatic segmentation and scanning platform to obtain high-resolution 2D images of individual cross-sections of the web that were illuminated by a sheet laser. We then developed image processing algorithms to reconstruct the digital 3D fibrous network by analysing the 2D images. This digital network provides a model that contains all of the structural and topological features of the porous regions of a 3D web with high fidelity, and when combined with a mechanical model of silk materials, will allow us to directly simulate and predict the mechanical response of a realistic 3D web under mechanical loads. Our work provides a practical tool to capture the architecture of sophisticated 3D webs, and could lead to studies of the relation between architecture, material and biological functions for numerous 3D spider web applications.

Histogram-based standardization of intravascular optical coherence tomography images acquired from different imaging systems.

Intravascular optical coherence tomography (OCT) is widely used for analysis of the coronary artery disease. Its high spatial resolution allows for visualization of arterial tissue components in detail. There are different OCT systems on the market, each of which produces data characterized by its own intensity range and distribution. These differences should be taken into account for the development of image processing algorithms. In order to overcome this difference in the intensity range and distribution, we developed a framework for matching intensities based on the exact histogram matching technique. In our method, the key step for using the exact histogram matching is to determine the target histogram. For this, we proposed two schemes: a global scheme that uses a single histogram as the target histogram for all the pullbacks, and a local scheme that selects for each single image a target histogram from a predefined database. These two schemes are compared on a unique dataset containing pairs of pullbacks that were acquired shortly after each other with systems from two vendors, St. Jude and Terumo. Pullbacks were aligned according to anatomical landmarks, and a database of matched histogram pairs was created. A leave-one-out cross validation was used to compare performance of the two schemes. The matching accuracy was evaluated by comparing: (a) histograms using Euclidean (dx2 ) and Kolmogorov-Smirnov (dKS ) distances, and (b) median intensity level within anatomical regions of interest. Leave-one-out validation indicated that both matching schemes yield comparably high accuracies across the entire validation dataset. The local scheme outperforms the global scheme with marginally lower dissimilarities at both histogram level and intensity level. High visual similarity was observed when comparing the matched images to their aligned counterparts. Both local and global schemes are robust and produce accurate intensity matching. While local scheme performs marginally better than the global scheme, it requires a predefined histogram dataset and is more time consuming. Thus, for offline standardization of the images, the local scheme should be preferred for being more accurate. For online standardization or when another system is involved, the global scheme can be used as a simple and nearly-as-accurate alternative.

High-precision absolute linear encoder based on a standard calibrated scale

This paper presents the full research and development cycle of a high-precision absolute linear encoder based on a standard calibrated scale. Already available and used in industry standard scales of invar alloy were employed in the study. The scales have incremental indexes with 1 mm spacing intervals without an absolute code. However, the existing technical task is to measure the absolute position in the range of 2 m with accuracy less than 5 μm. For that, the developed encoder rationally combines magnetic measuring channel for the index numbering and an optical channel for the precise estimation of the encoder position. First, for the development, a simulation was performed to synthesize and analyze an image of an index. This image was used to develop a real-time double-threshold image processing algorithm to estimate the index position. Later the developed image processing algorithm was verified by preliminary testing and supported by a presented three-stage calibration procedure. The final measurements proved that the designed and developed encoder has the accuracy of 1.65 μm (3 standard deviations) at the speed up to 3 m/s. The possibility of use of standard calibrated scales with the presented encoder to solve existing and new industrial tasks forms the value of this paper. A possible use of the existing scales also provides unification and compatibility with conventional metrology equipment.

An improved image processing technique for determination of volume and surface area of rising bubble

Bubble volume and bubble surface area are key parameters that affect the working performance of bubble columns. Due to their non-intrusive characteristics and high spatial resolution, image processing techniques can be used to measure bubble volume. However, bubbles in practical application are not always perfectly spherical or ellipsoidal. In homogenous flow regimes where bubble interaction is weak, the bubble geometry can be classified into three types: round cap, ellipsoidal, and disk-shaped. For large and severely distorted bubbles, it is difficult to employ existing image processing methods for measuring the bubble volume. This study describes an image analysis technique that was developed to obtain the volume and surface area of large and severely deformed bubbles. This proposed image processing method is based on a differential segmentation concept and possesses better adaptability because it considers both the bubble geometry and deflection angle of the bubble. The developed image processing technique is verified using the results of a bubble collection experiment. By making use of the developed image processing algorithm, the volume and surface area of discrete bubbles have been calculated. The relationship between bubble volume distribution and gas flow rate is discussed and the characteristics of bubble surface area variance are shown. Moreover, the influences of bubble volume and surface area on the bubble rise velocity are analyzed.

Optical flow and image segmentation analysis for noninvasive precise mapping of microwave thermal ablation in X-ray CT scans - ex vivo study

Purpose: To develop image processing algorithms for noninvasive mapping of microwave thermal ablation using X-ray CT.Methods: Ten specimens of bovine liver were subjected to microwave ablation (20–80 W, 8 min) while scanned by X-ray CT at 5 s intervals. Specimens were cut and manually traced by two observers. Two algorithms were developed and implemented to map the ablation zone. The first algorithm utilises images segmentation of Hounsfield units changes (ISHU). The second algorithm utilises radial optical flow (ROF). Algorithm sensitivity to spatiotemporal under-sampling was assessed by decreasing the acquisition rate and reducing the number of acquired projections used for image reconstruction in order to evaluate the feasibility of implementing radiation reduction techniques.Results: The average radial discrepancy between the ISHU and ROF contours and the manual tracing were 1.04±0.74 and 1.16±0.79mm, respectively. When diluting the input data, the ISHU algorithm retained its accuracy, ranging from 1.04 to 1.79mm. By contrast, the ROF algorithm performance became inconsistent at low acquisition rates. Both algorithms were not sensitive to projections reduction, (ISHU: 1.24±0.83mm, ROF: 1.53±1.15mm, for reduction by eight fold). Ablations near large blood vessels affected the ROF algorithm performance (1.83±1.30mm; p < 0.01), whereas ISHU performance remained the same.Conclusion: The two suggested noninvasive ablation mapping algorithms can provide highly accurate contouring of the ablation zone at low scan rates. The ISHU algorithm may be more suitable for clinical practice as it appears more robust when radiation dose reduction strategies are employed and when the ablation zone is near large blood vessels.

Characterization of failure mechanisms of composite structures subjected to fatigue dominated by the self-heating effect

A self-heating effect in a non-stationary regime is a very dangerous phenomenon occurring in polymeric composites during cyclic loading, which significantly intensifies a degradation process and leads to a catastrophic failure of the loaded structure. In this paper, the authors performed fatigue tests until achieving various self-heating temperature values on the tested specimens’ surfaces, and further inspection using the X-ray computed tomography. The developed image processing algorithm allows for extraction and classification of different types of damage. The obtained results allow precise determining of a critical self-heating temperature due to a very high accuracy of the applied method as well as describing in detail a degradation mechanism of a polymeric composite structure subjected to fatigue with the accompanying self-heating effect. It was also possible to combine observed events in the temperature and acoustic emission evolution with an appearance of structural damage in the tested structures and describe a general phenomenology of the degradation process of composite structures working in such conditions. The obtained results allow for improvement of design requirements of composite structures working in mechanical fatigue conditions as well as proper maintenance of composite constructions in order to avoid critical ranges of generated heat during cyclic loading.

Model of colposcopy using polarized light and effective early

Cervical disease is one of the common diseases, it occurs in women and has a growing tendency. In particular, cervical cancer is one of the most common diseases. The disease can be cured if it is detected early and treated under the guidance of a physician. The usual cervical examination methods are biopsies, and colposcopy. Recently, many studies have applied imaging techniques in the analysis and evaluation of cervical pathology characteristics [1-3]. In this study, we improved the traditional colposcopy with a polarized light source, and captured images with high resolution. Based on the image obtained, we developed image processing algorithms, initially analyzed and evaluated some of the common features of cervical disease

تشخیص تازگی گوشت گوساله به کمک پردازش تصویر و سطح پاسخ

گوشت و محصولات مرتبط با آن ارزش تجاریی بالایی داشته و یکی از مهمترین اقلام سبد غذایی خانوار را تشکیل می‌دهد. با توجه به عرضه گوشت در قصابی‌ها و نیز استفاده از آن در کارخانه‌های فرآوری نیاز به اطمینان از تازگی آن احساس می‌شود چه بسا گوشت با گذشت از زمان ذبح آن نه تنها از کیفیت آن کاسته می‌شود بلکه ممکن است به سبب فساد موجب بیماری نیز شود لذا هدف از این تحقیق تشخیص تازگی گوشت گوساله با تخمین مدت زمان گذشته از ذبح می‌باشد. برای این منظور از سه قسمت ران، سر دست و گردن گوساله ذبح شده نمونه‌هایی تهیه شد و نمونه‌ها در دو محیط استاندارد و رایج یکی در یخچال با دمای 3 درجه سانتی‌گراد و دیگری در محیط خنک با دمای میانگین 8 درجه سانتی‌گراد نگهداری شد سپس از نمونه‌ها در زمان‌های مشخص (هر 2 ساعت) تصویربرداری شد و از تصاویر تهیه شده توسط پردازش تصویر و به کمک نرم‌افزار MATLAB پارامترهایی استخراج گردید. از بین پارامترهای استخراج شده توسط آنالیز حساسیت سه پارامتر به‌عنوان عامل تأثیرگذار در مدت زمان گذشته از ذبح انتخاب گردید که عبارتند از: خصوصیت بافت، میزان کنتراست و زبری سطح گوشت. در نهایت به کمک روش سطح پاسخ و توسط نرم‌افزارDesign Expert مدل‌های مناسبی تدوین و بهینه گردید.

Marker-guided auto-landing on a moving platform

PurposeThe purpose of this paper is to develop a method for a vision-based automatic landing of a multi-rotor unmanned aerial vehicle (UAV) on a moving platform. The landing system must be highly accurate and meet the size, weigh, and power restrictions of a small UAV.Design/methodology/approachThe vision-based landing system consists of a pattern of red markers placed on a moving target, an image processing algorithm for pattern detection, and a servo-control for tracking. The suggested approach uses a color-based object detection and image-based visual servoing.FindingsThe developed prototype system has demonstrated the capability of landing within 25 cm of the desired point of touchdown. This auto-landing system is small (100×100 mm), light-weight (100 g), and consumes little power (under 2 W).Originality/valueThe novelty and the main contribution of the suggested approach are a creative combination of work in two fields: image processing and controls as applied to the UAV landing. The developed image processing algorithm has low complexity as compared to other known methods, which allows its implementation on general-purpose low-cost hardware. The theoretical design has been verified systematically via simulations and then outdoors field tests.

Analysis of confocal microscopy image data of Physcomitrella chloroplasts to reveal adaptation principles leading to structural stability at the nanoscale

AbstractProteins of the FtsZ (filamentous temperature‐sensitive Z) family establish complex polymeric spatial patterns in plastids of the moss Physcomitrella patens. These structures represent a "plastoskeleton" that might contribute to plastid shape and stability. The aim of this work is to develop computer models of FtsZ network connectivity and dynamics. These computer models are developed from green fluorescent protein (GFP) images obtained by Prof. Reski's Plant Biotechnology group at the University of Freiburg by means of laser scanning confocal microscopy. Subsequently, structural reconstruction techniques based on cellular automata algorithm are applied on the raw image data to compensate for any information that is lost in the process of imaging. Segmentation of the processed data will result in the computer model of the targeted structures, which are used for further analysis. Model generation and experimental testing in the moss system is conducted in an iterative process with the aim of both forward and reverse biomimetics. A developed image processing algorithm with the aim of quantification of structural characteristics is utilized to extract structural features of the FtsZ network in Physcomitrella enabling us a statistical analysis on the extracted data. (© 2016 Wiley‐VCH Verlag GmbH &amp; Co. KGaA, Weinheim)

Development and testing of image processing algorithm to estimate weed infestation level in corn fields

The challenges of modern agriculture have led to the development of localized management tools which allow the rationalization of the use and application of pesticides, a reduction in production costs and the optimization of agricultural processes. This study was carried out to develop an algorithm capable of orienting weed control in the management of a corn crop, using digital image analysis to identify the level of weed infestation in the field. The seeds of six species of weed were sown in an experimental plot of corn, and daily images were captured for 40 days for the evaluation of the level of weed infestation (low, intermediate or high). The algorithm developed was able to target information about the plants and soil accurately and discriminate the residual information as referring to either the culture or weeds. The proposed algorithm has achieved 90% accuracy in identifying the level of infestation from images already evaluated by experts. The results can thus be used as part of weed control strategy, with the incorporation of the geographic coordinates of the image making possible the construction of a map of the level of weed infestation in the different areas where the crop is growing.

Improvement of an objective model of compressed breasts undergoing mammography

Introduction Mammography clinical performance still has room for improvement, and the development of image processing algorithms with an objective model of compressed breasts could help in this task. Purpose To develop an accurate model of compressed breasts undergoing mammography based on objective analysis, able to represent the shape of acquired clinical mammography views and also generating realistic paired cranio-caudal (CC) and medio-lateral oblique (MLO) view shapes from a same breast. Materials and methods We improve an existing model by overcoming the bias of detector size, removing the nipple and extraneous tissue, pairing the CC and MLO views from a same breast, and incorporating the pectoralis contour. The shapes of the breast in 872 mammograms were automatically detected, and then reduced to a model with linearly independent variables via principal component analysis. We tested its ability to represent 100 independent mammograms by measuring the average distance error (ADE). Results The model based on twelve principal components (containing 99.2% of the total variance of the data) was found to depict breast shapes with high fidelity (ADE = 1.31 mm), while fewer components still provide adequate representation (ADE = 3.60 mm). The histograms of the first twelve parameters were successfully fitted with Gaussian distributions and can be used to generate new contours. Conclusion Our model can successfully generate paired CC and MLO view shapes from the same simulated breast, as well as characterize with high accuracy clinical acquired mammograms with a small set of parameters, which can aid dosimetry and scatter correction research. Disclosure None to disclose.

FLEX End-to-End Mission Performance Simulator

The FLuorescence EXplorer (FLEX) mission, selected as the European Space Agency's eighth Earth Explorer, aims to globally measure the sun-induced-chlorophyll-fluorescence spectral emission from terrestrial vegetation. In the frame of the FLEX mission, several industrial and scientific studies have analyzed the instrument design, image processing algorithms, or modeling aspects. At the same time, a common tool is needed to address the overall FLEX mission performance by combining all these features. For this reason, an end-to-end mission performance simulator has been developed for the FLEX mission (FLEX-E). This paper describes the FLEX-E software design, which combines the generation of complex synthetic scenes with an advanced modeling of the instrument behavior and the full processing scheme up to the final fluorescence product. The results derived from FLEX-E simulations indicate that the instrument and developed image processing algorithms are able to retrieve the sun-induced fluorescence with an accuracy below the 0.2 $\text{mW}\cdot\text{m}^{-2}\cdot\text{sr}^{-1}\cdot \text{nm}^{-1}$ mission requirement. It is expected that FLEX-E will not only optimize the FLEX retrieval algorithms and technical requirements, but also serve as the baseline for the ground processing implementation and testing of calibration/validation procedures.