Image Processing Steps Research Articles

A generalised approach for high-throughput instance segmentation of stomata in microscope images

BackgroundStomata analysis using microscope imagery provides important insight into plant physiology, health and the surrounding environmental conditions. Plant scientists are now able to conduct automated high-throughput analysis of stomata in microscope data, however, existing detection methods are sensitive to the appearance of stomata in the training images, thereby limiting general applicability. In addition, existing methods only generate bounding-boxes around detected stomata, which require users to implement additional image processing steps to study stomata morphology. In this paper, we develop a fully automated, robust stomata detection algorithm which can also identify individual stomata boundaries regardless of the plant species, sample collection method, imaging technique and magnification level.ResultsThe proposed solution consists of three stages. First, the input image is pre-processed to remove any colour space biases occurring from different sample collection and imaging techniques. Then, a Mask R-CNN is applied to estimate individual stomata boundaries. The feature pyramid network embedded in the Mask R-CNN is utilised to identify stomata at different scales. Finally, a statistical filter is implemented at the Mask R-CNN output to reduce the number of false positive generated by the network. The algorithm was tested using 16 datasets from 12 sources, containing over 60,000 stomata. For the first time in this domain, the proposed solution was tested against 7 microscope datasets never seen by the algorithm to show the generalisability of the solution. Results indicated that the proposed approach can detect stomata with a precision, recall, and F-score of 95.10%, 83.34%, and 88.61%, respectively. A separate test conducted by comparing estimated stomata boundary values with manually measured data showed that the proposed method has an IoU score of 0.70; a 7% improvement over the bounding-box approach.ConclusionsThe proposed method shows robust performance across multiple microscope image datasets of different quality and scale. This generalised stomata detection algorithm allows plant scientists to conduct stomata analysis whilst eliminating the need to re-label and re-train for each new dataset. The open-source code shared with this project can be directly deployed in Google Colab or any other Tensorflow environment.

Non-Destructive Fast Estimation of Tree Stem Height and Volume Using Image Processing

Measuring biometric tree characteristics to estimate the volume of wood in a forest area is a time consuming task. It is usually performed by a team of two or more people, who measure the diameter and height of several trees in sampling plots. The results are then extrapolated for the forest stand. The present paper describes a method which facilitates estimating tree biometric parameters using computational techniques. A camera takes two pictures of each sample tree, with an especially designed target placed close to the tree, to facilitate image processing and camera calibration steps. Taking advantage of the trees’ natural shape and assuming a symmetric stem, the diameter and height of the tree stems are estimated from the images and the volumes of the tree stems are calculated. Experimental trials show promising results, exhibiting errors similar to the traditional methods used currently, in the range of 10%, showing that the method is suitable for forest inventory.

Pneumonia Identifikasi Pneumonia Pada Citra Rontgen Paru Menggunakan Metode Power-Law Trans

Pneumonia adalah proses infeksi akut yang mengenai jaringan paru-paru (Alveoli), yang dapat disebabkan oleh infeksi jasad renik atau bakteri. Deteksi penyakit Pneumonia dilakukan melalui tanda-tanda klinis uji laboratorium dan foto x-ray paru. Penelitian ini menggunakan beberapa langkah dari pengolahan citra, seperti Power-law trans, Gabor Waveletdan Boundary. Tujuan utama dari langkah tersebut adalah untuk mengidentifikasi infiltrate dari citra X-Ray paru–paru manusia dan menentukan klasifikasi infiltrate. Hasil penelitian mengindikasikan klasifikasi dari penyakit pneumonia menjadi normal, pneumonia ringan, dan pneumonia kronik. Pengujian dilakukan pada lima puluh citra dengan spesifikasi yang berbeda. Dari hasil pengujian tersebut, menunjukkan bahwa equivD dan perimeter rata-rata infiltrate ditiap citra yang bernilai dibawah 30 diidentifikasi sebagai penyakit pneumonia. Diidentifikasi pneumonia kronik apabila rata-rata equivD dan perimeter infiltrate diatas 30. Untuk identifikasi normal apabila centroid, equivD, perimeter dan roundness tidak ada. Validitas sistem dinilai dengan cara menghitung nilai TP, TN, FP, dan FN sehingga di dapatkan Sensitivity dari metode ini adalah 94,3% dan Specificity dari sistem ini adalah 100%.

Effective image visualization for publications - a workflow using open access tools and concepts.

Today, 25% of figures in biomedical publications contain images of various types, e.g. photos, light or electron microscopy images, x-rays, or even sketches or drawings. Despite being widely used, published images may be ineffective or illegible since details are not visible, information is missing or they have been inappropriately processed. The vast majority of such imperfect images can be attributed to the lack of experience of the authors as undergraduate and graduate curricula lack courses on image acquisition, ethical processing, and visualization. Here we present a step-by-step image processing workflow for effective and ethical image presentation. The workflow is aimed to allow novice users with little or no prior experience in image processing to implement the essential steps towards publishing images. The workflow is based on the open source software Fiji, but its principles can be applied with other software packages. All image processing steps discussed here, and complementary suggestions for image presentation, are shown in an accessible "cheat sheet"-style format, enabling wide distribution, use, and adoption to more specific needs.

Clustering polymorphs of tau and IAPP fibrils with the CHEP algorithm

Recent steps towards automation have improved the quality and efficiency of the entire cryo-electron microscopy workflow, from sample preparation to image processing. Most of the image processing steps are now quite automated, but there are still a few steps which need the specific intervention of researchers. One such step is the identification and separation of helical protein polymorphs at early stages of image processing. Here, we tested and evaluated our recent clustering approach on three datasets containing amyloid fibrils, demonstrating that the proposed unsupervised clustering method automatically and effectively identifies the polymorphs from cryo-EM images. As an automated polymorph separation method, it has the potential to complement automated helical picking, which typically cannot easily distinguish between polymorphs with subtle differences in morphology, and is therefore a useful tool for the image processing and structure determination of helical proteins.

Effective image visualization for publications – a workflow using open access tools and concepts

Today, 25% of figures in biomedical publications contain images of various types, e.g. photos, light or electron microscopy images, x-rays, or even sketches or drawings. Despite being widely used, published images may be ineffective or illegible since details are not visible, information is missing or they have been inappropriately processed. The vast majority of such imperfect images can be attributed to the lack of experience of the authors as undergraduate and graduate curricula lack courses on image acquisition, ethical processing, and visualization. Here we present a step-by-step image processing workflow for effective and ethical image presentation. The workflow is aimed to allow novice users with little or no prior experience in image processing to implement the essential steps towards publishing images. The workflow is based on the open source software Fiji, but its principles can be applied with other software packages. All image processing steps discussed here, and complementary suggestions for image presentation, are shown in an accessible “cheat sheet”-style format, enabling wide distribution, use, and adoption to more specific needs.

КОНВЕРТЕР ИЗОБРАЖЕНИЙ ГЕОЛОГО-ЛИТОЛОГИЧЕСКИХ ПРОФИЛЕЙ

The article is devoted to the program "Converter", which allows you to translate the geologic-lithological profile of a mineral field into a digital format in the form of a two-dimensional array. The object-oriented programming language Python was used to write the program. The NumPy, OpenCV, and MatPlotlib libraries are actively used. The implementation of this program is based on image segmentation and finding the prevailing colors in the OpenCV library. Image segmentation is a preliminary step in image processing. The obtained values allow you to find out the density distribution in the area under consideration. The program "Converter" has a good graphical representation of the results obtained using the MatPlotlib library. The program writes the final converted result as a two-dimensional array to a text file along the desired path. Thus, the matrix is easy to read for further use in conjunction with other programs. The purpose of this work was to create a program that converts the geologic-lithological profile of the field into a digital format in the form of a two-dimensional array, for further use of this matrix as the distribution density of the oil field. The "Converter" program converts any geologic-lithological profile into a two-dimensional array in a matter of minutes.

Hierarchical Residual Embedding Network for Real-Time De-focus Blur Detection

Defocus blur detection, as an important pre-processing step of image processing, has attracted more and more attention. Albeit great success has been made, there are still several challenges for accurate defocus blur detection, such as the interference of background clutter, sensitivity to scales, missing boundary details and large computational burden. For handling these issues, we present a deep neural network which hierarchically embeds residual learning blocks for defocus blur detection. Based on the feature pyramid structure, we extract deep features with varying scales via utilizing a backbone fully convolutional network and generate a coarse score map by using the last layer of feature maps. Then we design a hierarchical residual embedding module to fuse different levels of features in a layer-wise manner. By embedding different layer-wise features in the top-down pathway, coarse-level semantic information from the deep layers can be seamlessly propagated to shallow layers, while fine details in the shallow layers can be used to refine the boundary between out-of-focus and in-focus regions. For each layer, a side output is generated by using a residual learning block. For capturing multi-scale information, the multiple side outputs of different layers are fed into a designed fusion block for yielding the final blur map result. Experimental results on two commonly used datasets show that our proposed network can more accurately locate the defocus blur regions with sharpened details being well preserved when compared to other previous state-of-the-arts. In addition, our approach is fast as well and can run at a speed of more than 25 FPS when processing an image with size 427 x 640.

Accurate Liver Border Identification Model in CT Scan Images

The liver is an important organ in human body with certain variations in its edges, color, shape and pixel intensity distribution. These uncertainties may be because of various liver pathologies, hereditary or both. Along with it, liver has close proximity to its nearby organs. Hence, identifying liver in scanned images is a challenging step in image processing. This task becomes more imprecise when liver diseases are present at the edges. The liver segmentation is prerequisite for liver volumetry, computer-based surgery planning, liver surgery modelling, surgery training, 3D view generation, etc. The proposed hybrid segmentation method overcomes the problems and identifies liver boundary in Computed-Tomography (CT) scan images accurately. In this paper, the first step is to study statistics of pixel intensity distribution within liver image, and novel methodology is designed to obtain thresholds. Then, threshold-based segmentation is applied which separates the liver from abdominal CT scan images. In the second step, liver edge is corrected using improved chain code and Bresenham pixel interconnection methods. This provides a precise liver image. The initial points are located inside the liver region without user interventions. These initial points evolve outwardly using Fast Marching Method (FMM), identifying the liver boundary accurately in CT abdominal scan images.

CDAE: A Cascade of Denoising Autoencoders for Noise Reduction in the Clustering of Single-Particle Cryo-EM Images.

As an emerging technology, cryo-electron microscopy (cryo-EM) has attracted more and more research interests from both structural biology and computer science, because many challenging computational tasks are involved in the processing of cryo-EM images. An important image processing step is to cluster the 2D cryo-EM images according to their projection angles, then the cluster mean images are used for the subsequent 3D reconstruction. However, cryo-EM images are quite noisy and denoising them is not easy, because the noise is a complicated mixture from samples and hardware. In this study, we design an effective cryo-EM image denoising model, CDAE, i.e., a cascade of denoising autoencoders. The new model comprises stacked blocks of deep neural networks to reduce noise in a progressive manner. Each block contains a convolutional autoencoder, pre-trained by simulated data of different SNRs and fine-tuned by target data set. We assess this new model on three simulated test sets and a real data set. CDAE achieves very competitive PSNR (peak signal-to-noise ratio) in the comparison of the state-of-the-art image denoising methods. Moreover, the denoised images have significantly enhanced clustering results compared to original image features or high-level abstraction features obtained by other deep neural networks. Both quantitative and visualized results demonstrate the good performance of CDAE for the noise reduction in clustering single-particle cryo-EM images.

Sequential data assimilation for mechanical systems with complex image data: application to tagged-MRI in cardiac mechanics

Tagged Magnetic Resonance images (tagged-MRI) are generally considered to be the gold standard of medical imaging in cardiology. By imaging spatially-modulated magnetizations of the deforming tissue, indeed, this modality enables an assessment of intra-myocardial deformations over the heart cycle. The objective of the present work is to incorporate the most valuable information contained in tagged-MRI in a data assimilation framework, in order to perform joint state-parameter estimation for a complete biomechanical model of the heart. This type of estimation is the second major step, after initial anatomical personalization, for obtaining a genuinely patient-specific model that integrates the individual characteristics of the patient, an essential prerequisite for benefitting from the model predictive capabilities. Here, we focus our attention on proposing adequate means of quantitatively comparing the cardiac model with various types of data that can be extracted from tagged-MRI after an initial image processing step, namely, 3D displacements fields, deforming tag planes or grids, or apparent 2D displacements. This quantitative comparison—called discrepancy measure—is then used to feed a sequential data assimilation procedure. In the state estimation stage of this procedure, we also propose a new algorithm based on the prediction–correction paradigm, which provides increased flexibility and effectiveness in the solution process. The complete estimation chain is eventually assessed with synthetic data, produced by running a realistic model simulation representing an infarcted heart characterized by increased stiffness and reduced contractility in a given region of the myocardium. From this simulation we extract the 3D displacements, tag planes and grids, and apparent 2D displacements, and we assess the estimation with each corresponding discrepancy measure. We demonstrate that—via regional estimation of the above parameters—the data assimilation procedure allows to quantitatively estimate the biophysical parameters with good accuracy, thus simultaneously providing the location of the infarct and characterizing its seriousness. This shows great potential for combining a biomechanical heart model with tagged-MRI in order to extract valuable new indices in clinical diagnosis.

Turbidity Level Prediction Based on Suspended Particle Counting Through Image Processing Approach

Monitoring of pollutant concentrations in surface water becomes a concern, considering the utilization of surface water as the raw water for drinking water treatment plants (WTP). The fluctuation of pollutant concentrations in surface water can affect the performance of WTP. This research was conducted to assess the potential for turbidity level prediction based on the calculation of the number and surface area of suspended particles through a digital image processing approach. Measurements of the amount and surface area were carried out in the form of laboratory-scale experiments using the open source software ImageJ 1.46r. The algorithm in ImageJ can convert pixels into a number “value” and surface area through a series of digital image processing steps, henceforth compared with the existing measurement method. The results showed that there was a strong correlation between the number of particles and the concentration of formazine suspension (r = 0.9821), but does not apply to the surface area. Referring to the results of laboratory experiments, it can be concluded that the approach to measure the number of suspended particles can be the basis for predicting the turbidity level in the turbidity range 100-800 NTU, but does not apply to the turbidity range 0.02-20 NTU.

Optimizing and applying high-resolution, in-line laboratory phase-contrast X-ray imaging for low-density material samples.

In-line, or propagation-based phase-contrast X-ray imaging (PBI) is an attractive alternative to the attenuation-based modality for low-density, soft samples showing low attenuation contrast. With the growing availability of micro- and nano-focus X-ray tubes, the method is increasingly applied in the laboratory. Here, we discuss the technique and demonstrate its advantages for selected low-density, low attenuation material samples using a lab-based micro- and nano-computed tomography systems Easytom XL Ultra, providing micron and sub-micron range resolution PBI images. We demonstrate a multi-step optimization of the lab-based PBI technique on our scanner that includes choosing the optimal detector-source hardware combination available in the setup, then optimizing the imaging geometry and finally the phase retrieval process through a parametric study. We point out and elaborate on the effect of noise correlation and texturing due to phase retrieval. We demonstrate the overall benefits of using the phase image and the phase retrieval for the selected samples such as improved image quality, increased contrast-to-noise ratio while only marginally influencing the spatial resolution. The improvement in image quality also enables further image processing steps for detailed structural analysis of the samples, which would be much more complicated if not impossible based on the transmissionimage.

Técnicas de visão computacional para classificação de peças

Computer vision is an area of artificial intelligence that has a great impact on various sectors of society. The ability of the machine to see objects of interest in an image and produce a classification or detection response is very important in the context of automation. The computer vision techniques allow, through image processing steps and the use of classifiers, to provide answers to several problems that arise. The objective of this work is to analyze the responsiveness of a specific classifier, the K-nearest neighbors (KNN), for a group classification problem and analyze its performance through hit rate and accuracy parameters. First, four groups of parts were created in a three-dimension (3D) design software and cut on a laser cutting machine, then pictures were taken of each of the parts individually. Later, using the OpenCV libraries, we could carry out the image processing, such as changing the red-green-blue (RGB) pattern to grayscale, binarization, noise correction, and obtaining invariant moments; and in the Scikit-Learn library, the classifier was trained and tested. It was possible to conclude that the classifier, in tests 1 and 2, was able to classify properly the parts groups having recall and precision above 65 and 80%, while, in test 3, it had a recall of 42% and a precision of 55%, showing that, with more analyzed classes, the classifier decreases its efficiency.

Real Time Vision System for Autonomous Vehicles

With the increase in vehicle accidents regularly, there is a need to control these accidents and save precious lives. The main reason for accidents on roads are mainly observed by driver misconception, recklessness and over speeding. So, there is a need to develop a Vision system which has a ability to explore its surroundings and move accordingly. The Vision system is divided into 3 subsystems as Visual perception subsystem, Brake and Acceleration subsystem and Steering control subsystem. The Visual perception means the ability to interpret surrounding environment using light in the visual spectrum reflected by the objects in the environment. This subsystem uses distance measuring sensors such as Light Detection and Ranging (LiDAR) and Ultrasonic sensors for detecting objects and sends the data to brake and acceleration subsystem using Arduino IDE software. According to the data received either the brake or acceleration is initiated, it means that when the distance measuring sensor values reach the threshold values then the brakes are applied or else acceleration is implemented. In order to have a smooth ride the acceleration should be uniform without any jerks though speed changes. This is resolved by using Proportional-Integral- Derivative (PID) controller which reduces the gradual difference between the desired and input speed. The Steering control subsystem involves lane detection and path tracking. The lane detection is done using Python and OpenCv which uses various image processing steps, gives the steering angle by calculating the curvature radius of lanes. Therefore path tracking system is initialized taking the steering angle and direction as input for controlling the position of the vehicle.

Submersible Pump Vortex Detection Using Image Processing Technique and Neuro-Fuzzy

The vortex means the mass of air or water that spins around very fast that often faced in the agriculture irrigation systems used the pump. The undesired effects like loss of hydraulic performance, erosion, vibration and noise may occur because of the vortex in pump systems. It is important to detect and prevent vortex for the economic life and efficiency of the agriculture pump. The image processing and neuro-fuzzy based novel model is proposed for the detection of a vortex in the deep well pump used in the agriculture system with this paper. The used images and data -submergence, flow rate, the diameter of the pipe, power consumption, pressure values and noise values- is acquired from an experimental pump. The proposed approach consists of three steps; Neuro-Fuzzy Learning, Image Processing and Neuro-Fuzzy Testing. In the first step, the eighty-two data have employed for the training process of the Neuro-Fuzzy. Then, the images derived from a camera placed near the experimental pump are used to detect vortex in the image processing step. Finally, the relevant data to vortex cases have employed for the testing process of the Neuro-Fuzzy. The result of this study demonstrates that image processing and neuro-fuzzy based design can be successfully used to detect vortex formation. This paper has provided novel contributions in the vortex detection issue such as find out vortex cases by using image processing and Neuro-Fuzzy. The image processing method has shed light on the studies to be done in the classification of vortexes and the measurement of their strength.

COMPARATIVE FAULT LOCATION ESTIMATION BY USING IMAGE PROCESSING IN MIXED TRANSMISSION LINES

Overhead lines are generally used for electrical energy transmission. Also, XLPE underground cable lines are generally used in the city center and the crowded areas to provide electrical safety, so high voltage underground cable lines are used together with overhead line in the transmission lines, and these lines are called as the mixed lines. The distance protection relays are used to determine the impedance based fault location according to the current and voltage magnitudes in the transmission lines. However, the fault location cannot be correctly detected in mixed transmission lines due to different characteristic impedance per unit length because the characteristic impedance of high voltage cable line is significantly different from overhead line. Thus, determinations of the fault section and location with the distance protection relays are difficult in the mixed transmission lines. In this study, 154 kV overhead transmission line and underground cable line are examined as the mixed transmission line for the distance protection relays. Phase to ground faults are created in the mixed transmission line. overhead line section and underground cable section are simulated by using PSCAD/ EMTDC ™. The short circuit fault images are generated in the distance protection relay for the overhead transmission line and underground cable transmission line faults. The images include the R-X impedance diagram of the fault, and the R-X impedance diagram have been detected by applying image processing steps. Artificial neural network (ANN) and the regression methods are used for prediction of the fault location, and the results of image processing are used as the input parameters for the training process of ANN and the regression methods. The results of ANN and regression methods are compared to select the most suitable method at the end of this study for forecasting of the fault location in transmission lines.

Development of a machine vision system for rice seed inspection system

Rice seed production in Malaysia is greatly dependent on the purity of the cultivated paddy seed produced through the government certified paddy seed program. The seeds to be marketed by the seed processors must undergo quality control protocol where the seed lots are sampled from the seed farms and seed processing plants for purity analysis by the enforcing agency at the Seed Testing Laboratory of the Department of Agriculture (DoA). The current inspection conducted by the laboratory is based on a manual process, which is laborious and time-consuming. Therefore, a prototype (Patent ID: PI2018500018) of a machine vision-based rice seed inspection system (RiSe-IViS) was developed to explore the possibility of replacing the existing manual method in distinguishing the weedy rice and cultivated rice seeds under the Standard Jabatan Pertanian Malaysia (SJPM) standard protocol with a modern, effective and efficient technique using an image processing approach. The developed RiSe-IViS prototype consists of two parts i) hardware configuration and ii) software development. This paper discussed the criteria to be established, challenges and limitation encountered in developing the hardware prototype involving the image acquisition setup, lighting configuration and seed plate design. The importance of each criterion to ensure its reproducibility are also discussed. A software programme was developed to assist the user for image acquisition and analysis. The image processing steps undertaken in the programme are also discussed. The RiSe-IViS is expected to classify major rice seed varieties available in Malaysia against the weedy rice variants with superior accuracy.

The DICOM CT Image Compression Based On Enhanced Lossless Prediction And Multilevel Thresholding Based Hybrid Cuckoo Search With Hill Climbing (CS-HC) Algorithm Based Segmentation

In computer vision applications, image segmentation is a common image processing step. It is used to separate pixels into different groups. The rise in the threshold count would hinder the segmentation phase of images. At the same time, in the field of threshold implementation in the image, it becomes an NT concern. This thesis suggests a multilevel threshold based on optimization techniques to remove ROI and uses enhanced lossless prediction algorithm to compress DICOM images in telemedicine applications. The hybrid Cuckoo search with hill climbing (CS-HC) algorithm strengthens the process used by the search agent to update the optimal solution. This algorithm calculates the threshold value. The superior results are produced by the proposed multilevel level thresholding based on CS-HC, as seen by the simulation results. Optimization is efficient and it has a high degree of convergence. Effective results are provided by the proposed lossless compression algorithm based on classification and blending estimation as compared with JPEG lossless and lossy compression techniques. With various threshold values, the algorithm 's efficiency is checked. To apply this algorithm, Matlab2010a is used and DICOM photos are used to validate it.

Getting Started with In Situ Cryo-Electron Tomography.

Cryo-electron tomography (cryo-ET) is an extremely powerful tool which is used to image cellular features in their close-to-native environment at a resolution where both protein structure and membrane morphology can be revealed. Compared to conventional electron microscopy methods for biology, cryo-ET does not include the use of potentially artifact generating agents for sample fixation or visualization. Despite its obvious advantages, cryo-ET has not been widely adopted by cell biologists. This might originate from the overwhelming and constantly growing number of complex ways to record and process data as well as the numerous methods available for sample preparation. In this chapter, we will take one step back and guide the reader through the essential steps of sample preparation using mammalian cells, as well as the basic steps involved in data recording and processing. The described protocol will allow the reader to obtain data that can be used for morphological analysis and precise measurements of biological structures in their cellular environment. Furthermore, this data can be used for more elaborate structural analysis by applying further image processing steps like subtomogram averaging, which is required to determine the structure of proteins.