Developed Image Processing Method Research Articles

IMAGE CLASSIFICATION OF VINE LEAF DISEASES USING COMPLEX-VALUED NEURAL NETWORK

Leaf diseases are a serious challenge in the agricultural industry affecting crop quality and yield especially in grapevines. Early recognition and classification of grape leaf diseases is crucial to enable farmers to take appropriate preventive measures in maintaining the health of their crops. The research utilized an innovative approach based on Complex-Valued Neural Network (CVNN) to address the problem. Using Complex-Valued Neural Network (CVNN) this research seeks to identify and classify grape leaf diseases through a series of experiments. A total of 100 images divided into 4 classes namely Black Rot, ESCA, Leaf Blight, and Healthy were collected to train the model. The results show that the trained CVNN model successfully achieved a training accuracy of 100% and a testing accuracy of 97%, demonstrating excellent performance in classifying grape leaf diseases. This states that the proposed approach has great potential to be an effective tool in helping growers manage their vineyards more efficiently and effectively. The developed image processing method is expected to be applied in designing a system to perform image classification of diseases on grape leaves.

Digital variance angiography in patients undergoing lower limb arterial recanalization: cost-effectiveness analysis within the English healthcare setting.

Aim: Digital variance angiography (DVA) is a recently developed image processing method capable of improving image quality compared with the traditionally used digital subtraction angiography (DSA), among patients undergoing lower limb x-ray angiography. This study aims to explore the potential cost-effectiveness of DVA from an English National Health Service perspective. Materials & methods: A two-part economic model, consisting of a decision tree and a Markov model, was developed to consider the costs and health outcomes associated with the use of DVA as part of current practice imaging, compared with x-ray angiography using standard DSA. The model explored the impact of DVA on the development of acute kidney injury (AKI), chronic kidney disease and radiation-induced cancer over a lifetime horizon. Both deterministic and probabilistic analyses were performed to assess the cost per quality-adjusted life-year (QALY). Results: Base-case results indicate that DVA results in cost savings of £309 per patient, with QALYs also improving (+0.025) over a lifetime. As shown in sensitivity analysis, a key driver of model results is the relative risk (RR) reduction of contrast-associated acute kidney injury associated with use of DVA. The intervention also decreases the risk of carcinoma over a lifetime. Scenario analyses show that cost savings range from £310 to £553, with QALY gains ranging from 0.048 to 0.109 per patient. Conclusion: The use of DVA could result in a decrease in costs and an increase in QALYs over a lifetime, compared with existing imaging practice. The potential for this technology to offer an economically viable alternative to existing image processing methods, through a reduction in contrast media volume and radiation exposure, has been demonstrated.

BUS-BRA: A breast ultrasound dataset for assessing computer-aided diagnosis systems.

Computer-aided diagnosis (CAD) systems on breast ultrasound (BUS) aim to increase the efficiency and effectiveness of breast screening, helping specialists to detect and classify breast lesions. CAD system development requires a set of annotated images, including lesion segmentation, biopsy results to specify benign and malignant cases, and BI-RADS categories to indicate the likelihood of malignancy. Besides, standardized partitions of training, validation, and test sets promote reproducibility and fair comparisons between different approaches. Thus, we present a publicly available BUS dataset whose novelty is the substantial increment of cases with the above-mentioned annotations and the inclusion of standardized partitions to objectively assess and compare CADsystems. The BUS dataset comprises1875 anonymized images from1064 female patients acquired via four ultrasound scanners during systematic studies at the National Institute of Cancer (Rio de Janeiro, Brazil). The dataset includes biopsy-proven tumors divided into722 benign and342 malignant cases. Besides, a senior ultrasonographer performed a BI-RADS assessment in categories2 to5. Additionally, the ultrasonographer manually outlined the breast lesions to obtain ground truth segmentations. Furthermore, 5- and 10-fold cross-validation partitions are provided to standardize the training and test sets to evaluate and reproduce CAD systems. Finally, to validate the utility of the BUS dataset, an evaluation framework is implemented to assess the performance of deep neural networks for segmenting and classifying breastlesions. The BUS dataset is publicly available for academic and research purposes through an open-access repository under the name BUS-BRA: A Breast Ultrasound Dataset for Assessing CAD Systems. BUS images and reference segmentations are saved in Portable Network Graphic (PNG) format files, and the dataset information is stored in separate Comma-Separated Value (CSV)files. The BUS-BRA dataset can be used to develop and assess artificial intelligence-based lesion detection and segmentation methods, and the classification of BUS images into pathological classes and BI-RADS categories. Other potential applications include developing image processing methods like despeckle filtering and contrast enhancement methods to improve image quality and feature engineering for imagedescription.

Experimental investigation on the nonlinear dynamic responses of the coupled floating submerged artificial seabed-mooring system in internal solitary waves

A new deepwater artificial seabed (DAS) production system is developed as a competitive offshore field development solution in deep and ultra-deep waters. This paper experimentally investigates the acting mechanism of ISWs on the nonlinear dynamic responses of the coupled floating submerged artificial seabed-mooring (ASM) system in a large-scale density-stratified flume. A compositive method for measuring and analyzing the interactions between the ASM system and the ISW is proposed. On this basis, the spatio-temporal features of the dynamic motion responses, the mooring tension variations and the flow field surrounding the ASM coupling system are characterized. The minute motion responses of the test model are captured by a charge-coupled device camera and subsequently processed using a developed image processing method. The temporal tension variations in the mooring lines are measured utilizing a non-contact optical measurement technique. The fluid-structure interaction characteristics between the flow field and the test model are revealed through the particle image velocimetry technique. In addition, the effects of crucial environmental factors on the nonlinear coupled dynamic responses of the ASM system are systematically explored in the experiments. The results indicate that the nonlinear dynamic responses of the ASM system in ISWs are characterized by the significant surge motion (maximum: 14.7% of the water depth), the coupled heave motion with the surge response, and the considerable mooring tension variation (maximum: 31.8% of the pre-tension), especially with the test model located within the density pycnocline.

Features of the Application of the Detection Algorithm Based on the Background Subtraction Method in the Scanning Optoelectronic Surveillance System

The article considers the approach developed by the authors to adapt the detection algorithm based on the background subtraction method to work in a scanning optoelectronic surveillance system. This algorithm is the basis of the developed image processing method applied to the problem of detecting moving objects by an optoelectronic thermal imaging surveillance system. At the same time, this method provides a solution to the tasks of protecting a critical object with an optoelectronic surveillance system, which must function both in stationary and scanning mode. The use of an improved mixture of Gaussian distributions to build a background model makes it possible to adapt to periodic changes in pixel brightness from dynamic background elements of the observed scene. However, the application of this detection algorithm in a scanning optoelectronic system requires the solution of the following problematic issues: the exclusion of false highlighting of the areas of the processed image in the foreground when transferring the sensor field of view; the elimination of errors in the initial values of the parameters of a mixture of Gaussian distributions. The application of the approach proposed by the authors to solving these issues is implemented in a specialized optoelectronic surveillance system and allows achieving the same quality of the detector based on the background subtraction method in scanning mode as in stationary mode.

Evaluating the Effectiveness of Image Processing in the Task of Detecting Moving Objects by an Optoelectronic Surveillance System

The article considers the approach proposed by the authors to evaluate the effectiveness of image processing in detecting moving objects by an optoelectronic surveillance system. The variety of indicators currently used by researchers to assess the quality of image processing suggests that common approaches have not yet been developed. The application of specific indicators is determined by the features of the implemented approaches to the image processing, as well as the specifics of the task in the interests of which the processing is carried out. The problem considered by the authors, assessing the effectiveness of the developed image processing method in relation to the problem of detecting moving objects by an optoelectronic surveillance system, determines the need for its consideration in two directions. The first is from the point of view of the effectiveness of the implemented approaches to image processing in order to increase the peak signal-to-noise ratio. The second is, in terms of increasing the efficiency of the automatic detector, by reducing the level of its false alarm. At the same time, the need for additional determination of the probability of correct detection and the construction of detection curves is mandatory, since in their entirety they are generally accepted indicators of the quality of detection. The application of the proposed approach will allow further comparison of the quality of the developed image processing method with other similar methods, as well as evaluation of the work of newly developed ones.

Development of modeling to investigate polyurethane pad hardness in chemical mechanical planarization/polishing (CMP) process

In chemical mechanical polishing (CMP) for IC fabrication, porous pads are critical for achieving extremely consistent throughput in CMP process. The pad hardness, porosity of pad, and pore sizes in the thermoplastic polyurethanes foam fabrication procedure determine the properties of CMP pads. This paper aims to develop a methodology for modeling macro and micro pad hardness. The IC1000 CMP pad has been analyzed with a developed image processing method to determine porosity and pores size. In addition, nano-indentation tests are used to determine physical properties of micro-solid components. For macro hardness analysis, five different sizes of three-dimensional representative volume elements (RVE) have been investigated using the random sequential adsorption technique. Furthermore, simulation of macro pad hardness of RVE models are completed with finite element method. Results of this study not only achieves macro hardness of CMP pad simulation as 3% errors as compared with developed micro-indentation test, but also complete three dimensional porous pad modeling with RVE.

Image processing based drape measurement of fabrics using circular Hough transformation

The drape behaviour of fabric is regarded as an aesthetic property, especially in the apparel and home textile industries. It has an influence on how well the appearance of a fabric in the end use. Fabric drape testing instrument developed by Cusick has been commonly used for the objective measurement of fabric drape behaviour. The device and the classic cut-and-weigh procedure is still the standard method of measuring drape. This method needs consumables and skilled operator for drawing, cutting, and weighing operations. To eliminate the disadvantages of this conventional system, image processing algorithm based on the Circular Hough Transform is developed to calculate the drape coefficient of fabrics in this study. Various woven and knitted fabrics were tested by both the conventional and the developed image processing methods. Drape results obtained from both systems represented a very strong relationship with a correlation coefficient of 0.99. As a result, fast, accurate and robust objective fabric drape test method has been developed.

Fully automated detection, segmentation, and analysis of in vivo RPE single cells.

To develop a fully automated method of retinal pigmented epithelium (RPE) cells detection, segmentation and analysis based on in vivo cellular resolution images obtained with the transscleral optical phase imaging method (TOPI). Fourteen TOPI-RPE images from 11 healthy individuals were analysed. The developed image processing method encompassed image filtering and normalisation, detection and removal of blood vessels, cell detection and cell membrane segmentation. The produced measures were cellular density of RPE layer, cell area, number of neighbouring cells, eccentricity, circularity and solidity. In addition, we proposed coefficient of variation (CV) of RPE cellular membrane (CMDCV) and the solidity of the RPE cell membrane-shape as new metrics for the assessment of RPE single cells. The observed median cellular density of the RPE layer was 3743 cells/µm2 (interquartile rate (IQR) 1687), with a median observed RPE cell area of 193 µm2 (IQR 141). The mean number of neighbouring cells was 5.22 (standard deviation (SD) 0.05) per RPE cell. The mean RPE cell eccentricity was 0.67 (SD 0.02), median circularity 0.83 (IQR 0.01), and median solidity 0.92 (IQR 0.00). The median CMDCV was 0.19 (IQR 0.02). The method is characterised by a median image processing and analysis time of 48 sec (IQR 12) per image. The present study provides the first fully automated quantitative assessment of human RPE single cells in vivo. The method provides a baseline for future research in the field of clinical ophthalmology, enabling characterisation and diagnostics of retinal diseases at the single-cell level.

Personalized approach to developing image processing and analysis methods for medical video systems.

Abstract The paper describes the new approach to developing image processing methods for medical video systems. The core idea is the personalized workflow of video data processing and analysis. It allows to increase the sensitivity and specificity of the physician - the user of system. At the visual analysis by the physician, personalization should provide the image representation as much as possible corresponding to physiological and psycho-visual features of the physician - the image should be comfortable for the analysis. In automatic analysis, the personalized approach allows the physician to set the optimal level of interaction with the system. An experienced specialist will need the results of diagnostic features evaluation and statistical analysis, while in the training mode one will need more AI diagnostic functions of the system. The paper provides specific examples of the personalized approach implementation in the visualization, enhancement and analysis of medical video data.

Digital image-based quantification of chlorpyrifos in water samples using a lipase embedded paper based device

A paper-based device (PBD) for the detection of chlorpyrifos pesticide at field application was fabricated based on the principles of enzyme inhibition and image processing. Rhizopus niveus lipase, p-nitrophenol palmitate and Whatman No.1 paper were used as an enzyme, substrate and support matrix, respectively. The performance of functionalized PBD was tested for lateral flow assay reaction in pure water (negative control), artificial pesticide water (positive control) and selected fruits and vegetables wash water (test). The digital image of the PBD after the test was captured using an android smartphone and analyzed in MATLAB software. Different colour space models such as, grey, RGB, HSV and YCbCr were studied and the Cb coordinate was chosen for its higher linearity (R2 = 0.988) with pesticide concentration. Experimental variations such as paper length, relative concentration ratio of the substrate and enzyme were investigated to minimize the product cost and analysis time. The developed PBD showed a significant response over wide range of sample solution's pH and operational temperature. Further, a long-term storage stability was measured for developed PBD. The LOD and LOQ were found to be 0.065 mgL−1 and 0.198 mgL−1. The results obtained from newly developed image processing method showed 92.8% accuracy with microtiter plate assay. Higher MRL was determined in the wash water of cauliflower, grapes, coriander leaves, brinjal and bitter guard. Overall, the developed paper biosensor was precise, cost effective and most suitable for field applications.

Direct calculation of inter-particle distance in suspension by image processing

With the difficulties to measure inter-particle distance in a suspension, the theoretical value under the several assumptions has been used. In this study, an image processing method for directly calculating inter-particle distances in a suspension was developed. This method enables inter-particle distances to be calculated regardless of the particle size, distribution, and morphology. A surface of suspension composed of particles and wax-polymeric binder was polished with acetone to expose the particles from the binder. The particles measured by scanning electron microscope were distinguished from the binder through the developed image processing method based on the intensity difference between the particles and binder. The inter-particle distances between the randomly selected particles and neighboring particles were calculated using the centroids and boundaries obtained by image processing. To determine the inter-particle distance as a representative value, a Monte Carlo method was employed. The inter-particle variation was defined to determine the iteration number for the Monte Carlo method. Finally, the inter-particle distances for the particle volume fraction of 40 and 50 vol% were obtained by the developed method. In addition, this developed method is available to describe the physical phenomenon such as a powder-binder separation and critical solid loading.

Evaluation of morphological properties of railway ballast particles by image processing method

Abstract The properties of individual ballast particles affect the behavior of ballast layer under train loading. One of the most important individual properties is the morphological characteristics of ballast particles represented by surface texture and angularity. In the present study, the morphological properties of ballast particles are quantified by developing surface texture (ST) index and angularity index (AI) determined on two-dimensional aggregate images. For this purpose, four different types of fresh ballast aggregates (basalt, marl, dolomite and trachyte), rounded river aggregate and degraded ballast sample obtained from railway track are analyzed for each specific sieve size fraction by developed image processing method. Comparison of the developed method in the present study for determination of ST and AI with the previously developed morphological indices shows that there is a reasonable correlation between them. In addition, the results obtained from the air void contents of aggregates in loose condition validate that the developed indices for the evaluation of morphological properties of aggregates can characterize the angularity and surface texture of each individual ballast particle properly.

Image processing-based analysis of interfacial phases in brazed stainless steel with Ni-based filler metal

This work presents an image processing method to identify the distribution of CrxBy in a brazed joint of SUS304/MBF20/SUS304. Although the chemical compositions at designated locations on such joints can be measured through electron-probe microanalysis (EPMA) and transmission electron microscopy (TEM), determining the overall distribution of CrxBy and quantitatively describing this phase is difficult. Therefore, an image-processing algorithm was developed using material-specific intensity differences in backscattered electron images. The image-processing algorithm was verified and validated by EPMA and TEM measurements. Based on the developed image processing method, the effects of the brazing temperature on the CrxBy layer thickness were quantitatively analyzed.

Biomarkers from in vivo molecular imaging of breast cancer: pretreatment 18F-FDG PET predicts patient prognosis, and pretreatment DWI-MR predicts response to neoadjuvant chemotherapy

ObjectiveHuman cancers display intra-tumor phenotypic heterogeneity and recent research has focused on developing image processing methods extracting imaging descriptors to characterize this heterogeneity. This work assesses the role of pretreatment 18F-FDG PET and DWI-MR with respect to the prognosis and prediction of neoadjuvant chemotherapy (NAC) outcomes when image features are used to characterize primitive lesions from breast cancer (BC).Materials and methodsA retrospective protocol included 38 adult women with biopsy-proven BC. Patients underwent a pre-therapy 18F-FDG PET/CT whole-body study and a pre-therapy breast multi-parametric MR study. Patients were then referred for NAC treatment and then for surgical resection, with an evaluation of the therapy response. Segmentation methods were developed in order to identify functional volumes both on 18F-FDG PET images and ADC maps. Macroscopic and histogram features were extracted from the defined functional volumes.ResultsOur work demonstrates that macroscopic and histogram features from 18F-FDG PET are able to biologically characterize primitive BC, and define the prognosis. In addition, histogram features from ADC maps are able to predict the response to NAC.ConclusionOur work suggests that pre-treatment 18F-FDG PET and pre-treatment DWI-MR provide useful complementary information for biological characterization and NAC response prediction in BC.

Infrared thermography with non-uniform heat flux boundary conditions on the rotor endwall of an axial turbine

It is technically challenging to measure heat fluxes on the rotating components of gas turbines, yet accurate knowledge of local heat loads under engine-representative conditions is crucial for ensuring the reliability of the designs. In this work, quantitative image processing tools were developed to perform fast and accurate infrared thermography measurements on 3D-shaped film-heaters directly deposited on the turbine endwalls. The newly developed image processing method and instrumentation were used to measure the heat load on the rotor endwalls of an axial turbine. A step-transient heat flux calibration technique is applied to measure the heat flux generated locally by the film heater, thus eliminating the need for a rigorously iso-energetic boundary condition. On-board electronics installed on the rotor record the temperature readings of RTDs installed in the substrate below the heaters in order to evaluate the conductive losses in the solid. Full maps of heat transfer coefficient and adiabatic wall temperature are produced for two different operating conditions, demonstrating the sensitivity of the technique to local flow features and variations in heat transfer due to Reynolds number effect.

Detecting defective electrical components in heterogeneous infra-red images by spatial control charts

Distribution network components connect machines and other loads to electrical sources. If resistance or current of any component is more than specified range, its temperature may exceed the operational limit which can cause major problems. Therefore, these defects should be found and eliminated according to their severity. Although infra-red cameras have been used for inspection of electrical components, maintenance prioritization of distribution cubicles is mostly based on personal perception and lack of training data prevents engineers from developing image processing methods. New research on the spatial control chart encouraged us to use statistical approaches instead of the pattern recognition for the image processing. In the present study, a new scanning pattern which can tolerate heavy autocorrelation among adjacent pixels within infra-red image was developed and for the first time combination of kernel smoothing, spatial control charts and local robust regression were used for finding defects within heterogeneous infra-red images of old distribution cubicles. This method does not need training data and this advantage is crucially important when the training data is not available. AimsDeveloping a new method to detect defective electrical components in the power distribution cubicles. Place and duration of studyTehran province, Iran, 2011–2013. MethodologyCombination of kernel smoothing, spatial control charts and local robust regression used for finding defects within heterogeneous infra-red image of old distribution cubicles. ResultsThis study showed that the IM-R control chart that plots forecasting residual of local robust regression and EWMA control chart with proper λ parameter with proper scan window size are powerful control charts which can be used to finding defected components in the power distribution cubicles. ConclusionIn some applications like analyzing thermal images of the old power distribution cubicles, it is not possible to train a sophisticated model like artificial neural network to identified defects. Therefore, spatial control chart that does not need training data is a valuable tool for these applications.

Validation of plant part measurements using a 3D reconstruction method suitable for high-throughput seedling phenotyping

In plant phenotyping, there is a demand for high-throughput, non-destructive systems that can accurately analyse various plant traits by measuring features such as plant volume, leaf area, and stem length. Existing vision-based systems either focus on speed using 2D imaging, which is consequently inaccurate, or on accuracy using time-consuming 3D methods. In this paper, we present a computer-vision system for seedling phenotyping that combines best of both approaches by utilizing a fast three-dimensional (3D) reconstruction method. We developed image processing methods for the identification and segmentation of plant organs (stem and leaf) from the 3D plant model. Various measurements of plant features such as plant volume, leaf area, and stem length are estimated based on these plant segments. We evaluate the accuracy of our system by comparing the measurements of our methods with ground truth measurements obtained destructively by hand. The results indicate that the proposed system is very promising.

Comparing the reliability and intermetallic layer of solder joints prepared with infrared and vapour phase soldering

Purpose – The purpose of this paper is to compare the reliability and intermetallic layer (IML) of solder joints prepared with infrared (IR) and vapour phase (VP) soldering. The reliability of 0603-sized resistors’ solder joints formed with IR and VP soldering was investigated. The IML of the joints was analysed based on image processing algorithm automatically. Design/methodology/approach – For the reliability analyses, the ageing method was a highly accelerated stress test (HAST) with +105°C maximum temperature, fully saturated (100 per cent) relative humidity at +0.5 atm overpressure. The joints were characterised based on the thickness of their IML and on their shear strength in as-reflowed stage, and after 400, 800, 1,200, 1,600 and 2,000 hours of HAST. An image processing algorithm was developed to measure the thickness of the IMLs on cross-sectional scanning electron microscopy (SEM) images automatically. Findings – The increase of the IML thickness is lower in the case of HAST ageing compared to other methods. The thickness increment of the Cu6Sn5 layer was higher for IR and lower for VP soldering; the Cu3Sn layer cannot be inspected even after 2,000 hours of HAST ageing. The results of shear strength measurements show better reliability for VP soldered joints. Practical implications – The developed image processing method is applicable to obtain quantitative results about the IMLs in an effective fast way. Originality/value – There is a lack of information in the literature regarding the reliability comparison of solder joints formed with VP and conventional reflow processes. Thus, we performed research about the lifetime of solder joints formed with VP and IR reflow method.

Practical methods for electrical and mechanical measurement of high speed elongated arc parameters

In this paper, we have presented measurement methods used to evaluate short circuit current interruption capability of a fast opening circuit breaker with opening velocities up to 36m/s. Such circuit breakers are the most critical components of future hybrid fault current limiting circuit breakers and therefore thorough understanding of fast elongating arcs is essential. The presented methods include measurement of cinematic parameters (displacement, speed and acceleration) and electrical parameters (arc voltage and current) as well as high speed optical measurement of arc appearance. Generated codes for sampling and wavelet de-noising of signals as well as developed image processing method for processing of digital arc images captured by high speed camera have been explained. Based on processed information gained by the measurements, arc starting time, arc ending time and arc temperature contours have also been calculated. Use of advanced simulation tools based on finite element method (FEM) equipped with moving mesh has been discussed to facilitate measurements and also to improve their accuracy. Practical measurements and simulation results prove each other and show good agreement with digital arc image processing output.