Search

The herbicide 2,4-dichlorophenoxyacetic acid (2,4-D) is widely used in agriculture to control various weeds. The objective of this study was to use the digital image processing method to identify alveolar lesions in the lungs of rats submitted to chronic 2,4-dichlorophenoxyacetic acid (2,4-D) inhalation exposure. We used forty adult male Wistar rats. The rats were divided into four groups: control group (CG), low concentration group (LCG), medium concentration group (MCG), and high concentration group (HCG). In a 6-month exposure period, we used two boxes connected to ultrasonic nebulizers for herbicide spraying. After this period, the rats were euthanized for the collection and study of lung tissue. For each image, counts of injuries and blisters were performed automatically using a methodology based on digital image processing techniques. For analysis of the results, an electronic database (Excel®) was created. We used the Pearson method for correlation analysis; values of p

This paper presents an acceleration method for an image processing algorithm from the RADIO EU project. The algorithm was profiled and the compute intensive tasks were then mapped on programmable hardware. The accelerator design was done with Vivado HLS. The accelerator implements the image processing algorithm as OpenCL kernel and optimizes its performance based on the analysis of the generated hardware. However, the OpenCL code does not reach acceptable speedups when implemented as is. For better performance, several optimizations steps have to be exceuted. The results show that software generated as hardware on programmable hardware can reach a speedup of up to 1.32. For this, further knowledge of the underlying hardware is required.

Modern medical image processing employs an ever widening array of tools on an ever larger pool of data. Development of the tools takes place on a variety of different platforms, determined by external circumstances, such as the availability of necessary functionality as libraries forcing the use of a specific programming language or interdependencies of third party tools requiring specific versions of specific operating systems. This problem itself is not unique to medical imaging[1] and solutions such as Docker have proven themselves useful in a variety of use cases.

Protective reflexes of the larynx help to avoid intrusion of foreign particles into the lower airways, which can lead to aspiration pneumonia. These protective mechanisms include the Laryngeal Adductor Reflex (LAR), a rapid adduction of the vocal folds. Up to now, the LAR latency could only be determined manually by visually assessing laryngoscopic high-speed video sequences obtained during and after stimulation of the larynx by water droplet impact. Here, we present a novel image processing algorithm based on difference image calculation and optical flow analysis for a more objective LAR latency determination. To evaluate our prototype algorithm, we compared the results obtained for a set of example sequences with the values given by two expert phoniatricians. The results show a very good LAR stimulation detection performance. LAR onset detection remains challenging for our algorithmic approach as well as for the human perceptive system, as demonstrated by a low inter-rater reliability.

The Medical Imaging Interaction Toolkit (MITK) is a powerful tool for image processing and application development with a long history [1, 2]. It provides an easy-to-use superbuild for a variety of development scenarios and a host of customization options. This very exibility can be intimidating to new users and even more experienced users might miss out on new developments due to the sheer size of the code base. In this tutorial we will give an overview on MITK, theunderlying concepts and the usage of the MITK Workbench. Afterwards we will show the attendees how to start their own software development with MITK and what pitfalls to look out for. Due to time constraints this will be in the form of a development demonstration, instead of a hands-on session. This will be followed by an introduction into more advanced usage scenarios, intended to provide a customized Workbench for special work ows or to conform to branding requirements. We will close with newly finished and ongoing developments and the new opportunities which arise based on them.

We present the concept of a perceptive motor in terms of a cyber-physical system (CPS). A model application monitoring a knitting process was developed, where the take-off of the produced fabric is controlled by an electric motor. The idea is to equip a synchronous motor with a smart camera and appropriate image processing hard- and software components. Subsequently, the characteristics of knitted fabric are analysed by machine-learning (ML) methods. Our concept includes motor-current analysis and image processing. The aim is to implement an assistance system for the industrial large circular knitting process. An assistance system will help to shorten the retrofitting process. The concept is based on a low cost hardware approach for a smart camera, and stems from the recent development of image processing applications for mobile devices [1–4].

Morphological methods used in the algebra of sets can be used for morphological image processing. They were introduced by Matheron and Serra under the term ‘Mathematical Morphology’ [12, 16, 17]. Here, image signals are considered to be point sets and morphological filters are operations manipulating these sets.

Nowadays, image processing products such as car black boxes and CCTV are sold in the market and offer convenient to users. Especially the black boxes helps determine the cause of the accidents while driving. However they can check only the front and the rear of vehicles so they can’t check for the driver’s blind spot and scenes of angle of view. To solve these problems, the Black box system was improved further and AVM(Around-View Monitoring) system was developed. AVM system gets images which has a bird’s-eye view of a sight on the top so it can obtain all directions, namely 360-degree images of vehicles. To obtain images, there is a condition attached to this system. Desktop should be installed in vehicles. AVM system that this article suggests can remedy the disadvantages such as installing PC in vehicles, this system was designed, using tablet equipment.

In the perspective of actual production, the paper presents the advances in the application of image processing fruit grading from several aspects, such as processing precision and processing speed of image processing technology. Furthermore, the different algorithms about detecting size, shape, color and defects are combined effectively to reduce the complexity of each algorithm and achieve a balance between the processing precision and processing speed are keys to automatic apple grading.

The image processing technique is an essential way to ensure an accurate infrared detection of faulty insulators. In this paper, we analyze the necessity of images processing techniques in infrared detection of faulty insulators, research the related image processing techniques applied in infrared detection of faulty insulators and provide the corresponding practical examples. The work have done in this paper can make a contribution to the application of image processing techniques in infrared detection of faulty insulators.

This volumeoffers a guide to the state of the art in the fast evolving field of biometric recognition to newcomers and experienced practitioners. Itis focused on the emerging strategies to perform biometric recognition under uncontrolled data acquisition conditions. The mainstream research work in this field is presented in an organized manner, so the reader can easily follow the trends that best suits her/his interests in this growing field. The book chapters cover the recent advances in less controlled / covert data acquisition frameworks, segmentation of poor quality biometric data, biometric data quality assessment, normalization of poor quality biometric data. contactless biometric recognition strategies, biometric recognition robustness, data resolution, illumination, distance, pose, motion, occlusions, multispectral biometric recognition, multimodal biometrics, fusion at different levels, high confidence automatic surveillance.

Speckle is caused by the illumination of an optically rough surface by coherent light [1] which can cause problems in digital holography. Speckle in a reconstruction reduces visibility of details and may impede important measurements of an object. Speckle can be reduced by capturing multiple holograms and summing the reconstructed intensities [2-4]. Digital signal processing methods, which are applied after capture, have also been proposed [5–8]. With respect to three-dimensional (3D) objects, we solve this problem by outof- plane rotating the reference mirror in discrete steps, capturing a hologram each time, and introducing image processing to rectify the resulting shifted diffraction fields. Each rotation amount need not be known and so can be generated by a very fast unstable device. This reference beam rotation is different from [4], where the object beam is rotated at different angles. Changing the angle of incidence of the reference beam changes the phase implicitly captured in the hologram, and results in a different speckle pattern in each reconstructed object. The positions of the object and the camera remain the same so there is no change in perspective between holograms, allowing integration of an arbitrary number of them using the full rotation range allowed by the space-bandwidth product of the camera. The intensities of numerical reconstructions are averaged after image processing registration steps, which produces speckle-reduced reconstructions that closely match theoretical predictions for statistically independent speckle fields.

Cervical Cancer is one of the ubiquitous forms of cancer afflicting the female population worldwide. A Digital Colposcope is a self-illuminated powerful microscope which acquires the image of the affected cervix. The raw cervix image acquired by the colposcope is known as a cervigram. The raw cervigram is preprocessed by removing the specular reflections and then the region of interest is sought. Different novel segmentation algorithms which were proposed in our earlier papers are applied to the cervigram to detect the acetowhite tissues. In the current paper, we try to draw a correlation between Pap smear results, colposcopic findings, histopathologic biopsy results and our proposed algorithmic analysis. The significance of association is assessed by chi-square testing and the strength of association by kappa statistic. The association between impression and histology was significant, the strength of correlation was also significant. The overall kappa statistic for the concordance of the algorithm with the human experts was 0.809, while that among raters, excluding the algorithm was 0.804. The proposed algorithm had better agreement with the expert decision.

As newer active and passive safety systems are developed, new testing requirements have appeared along with constraints and requirements that must be overcome while at the same time maintaining higher safety and quality standards. This paper presents a modular system that makes it possible to automate hazardous tests for drivers by using path following by means of a low-cost camera or defined GPS trajectories. This project provides a solution to tests where the driver cannot be inside the vehicle due to the inherent risk and complex methodology that must be followed. The developed system, which can be installed in any vehicle, is mounted on a small pickup truck, which is used as a test vehicle. Once this control architecture has been implemented, installed and tuned, the resulting steering manoeuvring allows tests required for recently developed and future safety systems to be performed. The experimental results show that the combination of artificial vision algorithms and steering wheel controller are capable of managing the lateral guidance of a vehicle as a human driver would do.

Humans have the subconscious ability to create simple abstractions from observations of their physical environment. The ability to consider the colour of an object in terms of “red” or “blue”, rather than spatial distributions of reflected light wavelengths, is vital in processing and communicating information about important features within our local environment. The real-time identification of such features in image processing necessitates the software implementation of such a process; segmenting an image into regions of salient colour, and in doing so reducing the information stored and processed from 3-dimensional pixel values to a simple colour class label. This paper details a method by which colour segmentation may be performed offline and stored in a static look-up table, allowing for constant time dimensionality reduction in an arbitrary environment of coloured features. The machine learning framework requires no human supervision, and its performance is evaluated in terms of feature classification performance within a RoboCup robot soccer environment. The developed system is demonstrated to yield an 8% improvement over slower traditional methods of manual colour mapping.

It has been a while since image processing has been introduced to RoboCupJunior. Since then, computational power has become cheaper and tools have become more mature. It is time to evolve again.

The paper proposes a recognition algorithm based on image processing for tunnel crack by collecting the subway tunnel images and makes the tunnel surface cracks recognition and information extraction come true. Meanwhile, according to the extracted information of tunnel surface cracks, we can take some corresponding maintenance and repair measures to meet the need of quick and safe detection for cracks, which can ensure the safety of subway operation.

Parameter estimation plays a dominant role in a wide number of image processing and computer vision tasks. In these settings, parameterizations can be as diverse as the application areas. Examples of such parameters are the entries of filter kernels optimized for a certain criterion, image features such as the velocity field, or part descriptors or compositions thereof. Subsequently, approaches for estimating these parameters encompass a wide range of techniques, often tuned to the application, the underlying data and viable assumptions. Here, an overview of parameter estimation in image processing and computer vision will be given. Due to the wide and diverse areas in which parameter estimation is applicable, this review does not claim completeness. Based on selected key topics in image processing and computer vision we will discuss parameter estimation, its relevance, and give an overview over the techniques involved.

This paper introduces a kind of intelligent cigarette length measurement apparatus based on digital image processing techniques, and presents the structural method of measurement system as well as the related algorithm of image processing of cigarette ends. In the end the method’s feasibility and superiority is proved through comparing experiment data and analyzing the quality of this method and the traditional methods.

The usual embedded image processing platform occupies mass storage space, lacks configurability, and the feature of real-time is not hard. This paper provides a method of designing digital image processing platform based on Qt. The method can improve the capacity of acquisition, analysis and processing image data to realize real-time and rapidity of the image processing. The work of software is based on the hardware, which completes the video driver firstly, and then achieves a variety of image processing methods involving transform domain and spatial domain, such as orthogonal transform, smoothing, sharpening, edge detection, emboss algorithm and so on.

The book puts special stress on the contemporary techniques for reasoning-based image processing and analysis: learning based image representation and advanced video coding; intelligent image processing and analysis in medical vision systems; similarity learning models for image reconstruction; visual perception for mobile robot motion control, simulation of human brain activity in the analysis of video sequences; shape-based invariant features extraction; essential of paraconsistent neural networks, creativity and intelligent representation in computational systems.

This paper introduces an architecture of parallel remote sensing image processing software, with advantages including high scalability, platform-independence, language-independence, and so on. It helps achieve high-performance computing in this field. MPI is used as the fundamental distributed message passing protocol. An object-oriented wrapper, Boost.MPI library, is used in the software to manipulate MPI. Open Source libraries such as GDAL and Open-CV are studied in this paper to help develop detailed image processing programs and implement classification algorithms. A number of experiments are conducted to test the parallel classification programs. The results indicate that in most cases the performance is significantly improved, especially for multi-spectral remote sensing image classification, in which a highest speed-up of 3.92 is reached.

International audience; Over the past 15 years, we have developed software image processing systems that attempt to reproduce the sorts of spike-based processing strategies used in biological vision. The basic idea is that sophisticated visual processing can be achieved with a single wave of spikes by using the relative timing of spikes in different neurons as an efficient code. While software simulations are certainly an option, it is now becoming clear that it may well be possible to reproduce the same sorts of ideas in specific hardware. Firstly, several groups have now developed spiking retina chips in which the pixel elements send the equivalent of spikes in response to particular events such as increases or a decreases in local luminance. Importantly, such chips are fully asynchronous, allowing image processing to break free of the standard frame based approach. We have recently shown how simple neural network architectures can use the output of such dynamic spiking retinas to perform sophisticated tasks by using a biologically inspired learning rule based on Spike- Time Dependent Plasticity (STDP). Such systems can learn to detect meaningful patterns that repeat in a purely unsupervised way. For example, after just a few minutes of training, a network composed of a first layer of 60 neurons and a second layer of 10 neurons was able to form neurons that could effectively count the number of cars going by on the different lanes of a freeway. For the moment, this work has just used simulations. However, there is a real possibility that the same processing strategies could be implemented in memristor-based hardware devices. If so, it will become possible to build intelligent image processing systems capable of learning to recognize significant events without the need for conventional computational hardware.

The CT and MRI image processing is a task with high requirement of computation time and computation speed. The calculation process in the most cases consists of various steps that are inherently parallel. There is opportunity to use parallel programming implemented in standard computer with more than one core. The more efficient way is to use real parallel signal processing. The only hardware that allows parallel data processing is FPGA. This article deals about this possibility. It is shown in the application on real problem in the image processing field. The first there is described the methodology of image processing in the application on CT (MRI) images of the head. The task is to count the ratio of intracranial fluid in the skull. It is important for child neurology diagnostic. The second part deals about the FPGA and its contribution to solving this task in the real parallel hardware system.

Infrared Non–Destructive Testing (IRNDT) uses several image processing techniques to enhance visual contrast and visibility of defects in inspected materials. The benchmarking of these techniques is often too qualitative due to a lack of quantitative criteria allowing to assess the qualities of the compared methods. In this work, we compare image processing techniques in IRNDT with a non–referenced (NR) image quality assessment (IQA) algorithm. Furthermore, we validate the NR IQA approach through a human–based quality evaluation and analyze statistical properties of IRNDT images. The results show a high correlation between NR IQA measure quality predictions and subjective evaluation. Moreover, the analysis evidenced a relationship of perceived image quality with 1) the spatial power spectral density, and 2) marginal and joint distributions of wavelet coefficients. This analysis provides a quantitative alternative when comparing image processing methods in IRNDT and can be used to develop specific IQA measure for IRNDT.

This paper studies the Fractional Kalman Filter and its applications to the extraction of image texture in electronic image processing. Firstly, with the introduction of fractional calculus, Fractional recursive equation is presented. Next, a state space model of a given image and, based on this, the Fractional Kalman Filter algorithm are proposed. Finally, an example of electronic image processing is given to demonstrate the effectiveness of proposed algorithm and the simulation result shows that the details of the image are enhanced, while the background noise of the image is attenuated efficiently.

In this paper, we proposed an electronic image processing waveguide with a special structure at the intersection based on triangular lattice photonic crystal. The effect of the radius of the innermost air holes and the electronic image processing waveguide are investigated. With the change of the radius of the electronic image waveguide, we can get when rwg equals to 0.25a, the structure presented can be applied as a time recorder in precised calculation.

With the development of information technology and the popularity of computer applications, ARM-based embedded operating systems become widely applied in the field of electronic technology. This paper mainly discussed the image processing system based on the design and implementation of ARM embedded system architecture, which included a series of problems in image acquisition, image storage, and image processing, and also provided a new research platform for image processing.

Visual C + + is object-oriented visual programming language. This article discusses the use of Visual C + + development tools to quickly build a digital image processing system, and the related issues on the input, display and processing of the digital image. Practice has proved that the system has real time, friendly interface and simple operation, suitable for building experimental platform of digital image processing for the continuous development of digital image processing technology and universities.

Digital image processing software refers to the use of a computer or other digital equipment to carry on a variety of processing and treatment for image information, and to meet people’s visual and application requirements’ application software. Through the digital process principle of digital processing software and the number of objects to indicate digital processing software in the application of art design, and to further explain the digital image processing software that is used in art design advantages, it will be artistic inspiration of the human and the combination of rational thinking and digital image processing software, to create a form more, effect more distinct, esthetic sense more independent art works.

The paper is focused on a description of modern image processing methods in intelligent vehicles with emphasis on an LDWS (Lane Departure Warning System). The authors describe possible solutions for finding the horizontal road marking using a segmentation method based on a Hough’s transformation. In practical realisation the image data have been recorded in the. AVI format using a camera located near the inner rear mirror of the vehicle. A Sobel’s detector is used for the edge detection, which obtains a binary image containing pixels representing the borders of objects.

According to the motion characteristics of the trees in the wind, the paper builds a realistic virtual simulation of three-dimensional plant movement on Maya with electronic image processing. The main purpose is to provide realistic effect for many applications fields, such as games, movies and so on. Firstly, the tree model is established on basis of polygon modeling tools with electronic image processing. Secondly, the force is analyzed and bone is created so as to set reasonable bone controller to drive the movement of the tree model. Finally, we realized the swing and fracture based on the principle of dynamic and cloth solver is adopted to make the swing and falling of the tree leafs more natural. The whole process mainly includes the gravity field; the wind field and the key frame technology. Experiments show that the method not only reduces the development time and work, but also makes the movement of trees more realistic.

Orientational planting cannot only make maize leaf growing consistently, but also improve the leaf photosynthetic capacity of unit area and yield of maize. The “tip” direction was detected and the angle of deflection was measured by using contour curvature analysis method of maize seed, the S component of HSV channel was preprocessed by Otsu method, the automatic extracting maize seeds embryo and orientation information have been realized through image color channel conversion, segmentation, preprocessing, and its contour characteristic analysis. A rectangular region ROI in the image was defined and counts up pixels within the region, the region-specific positive and negative ROI pixels were compared by TM threshold and the embryo side towards was identified. This paper adopted Zheng-958, Jundan-20 and Zhongke-11 maize seed for research object, each variety was repeated three times by using the above methods. The results showed that the average accuracy of embryo inspection was more than 95%; the direction average angle was 2.2 °.

This work presents a framework for diagnosing sub-clinical endometritis, a common uterine disease in dairy cattle, based in the analysis of ultrasound images of the uterine horn. The main contribution consists in the feature extraction proposal, based on the characteristics that the expert takes into account for diagnosing, such as statistics measures, image textures, shape, custom thickness measures and histogram, among others. Given the segmentation of the different regions of the uterine horn, a fully automatic supervised classification is performed, using a model based on C-SVM. Two different datasets of ultrasound images were used, acquired and tagged by an expert. The proposed framework shows promising results, allowing to consider the development of a complete automatic procedure to measure morphological features of the uterine horn that may contribute in the diagnosis of the pathology.

This paper reviews 80 out of 130 bio-inspired Algorithm (BIAs) researches published in google scholar and IEEExplore between the periods of 1995 to 2010 used to solve image processing problems. BIAs has been successfully applied in many sciences, medical and engineering fields. The evolving, dynamic and meta-heuristics nature of BIAs makes it more robust, accurate and efficient in solving image processing problems. However finding the appropriate BIAs that matches the problem at hand is a tedious and difficult task. The BIAs investigated in this study are Genetic Algorithms, Evolutionary strategies, Genetic programming, memetic algorithms, swarm intelligence and artificial immune system. The publications are categorized by year of publication, by specific BIAs and by application. The statistics shows exponential increases in the application of BIAs to solve image processing problems and some algorithms have yet to be explored.

For laser stripe sensors there are two types of image processing tasks. One is to find locations of the control points in the calibration target. This is usually for the calibration procedure. The other is to find the center position of the laser line, which is used for the reconstruction procedure. For the first task, accuracy of the algorithm is essential. And for the second task, reliability, insensitivity to the ambient light, accuracy as well as speed need to be addressed. In applications associated with reconstructed range images, the registration algorithm is a very powerful tool used in workpiece calibration, localization, and shape inspection, especially for free form surface. In this chapter we will review 2D image processing techniques as well as range image registration algorithms associated with laser stripe sensors and robot vision systems. These techniques are widely used in visual sensing applications as described in Chapter 7.

This paper presents a real-time robot vision system integrating adequate image processing and pan-tilt motion control which is implemented by FPGA reconfigurable logic device. The digital image processing acquired by CMOS image sensor is performed on the embedded FPGA board and Linux real-time video communication module. The integrated robot vision system aims to achieve a suitable platform available from both hardware and software. In addition, we also present spatial recognition by edge detection and tracking function of moving objects by determining color which are necessary for autonomous mobile robots.

In recent years, three-dimensions medical image processing has been considering as a large field, which is not only a big interest of bio-medical researchers and physicians, but also a challenge in processing and making three-dimensions images useful to bio-medical researches and practically clinical applications. This thesis consists of a detailed survey of three-dimension medical images with processing methods, which are followed by several of special algorithms. Through this survey, some of algorithms are usefully applied into designing a Java 3D medical image processing software. After validation and evaluation, the results of this software are found to be significantly useful in medical research and education. By taking the advantages of multi-platform property and advanced packages of Java, this software not only work well with different platforms, but also potentially have image processing methods to be extended.

This chapter gives an introduction to the methods of biomedical image processing. After some fundamental preliminary remarks to the terminology used, medical imaging modalities are introduced (Sect. 1.2). Sections 1.3 and 1.4 deal with low-level image processing and visualization, respectively, as far as necessary to understand the following chapters. Subsequently, the core steps of image analysis, namely: feature extraction, segmentation, classification, quantitative measurements, and interpretation are presented in separate sections. On account of its high relevance, the focus is on segmentation of biomedical images. Special segmentation methods and techniques have been developed in the medical application domain. Section 1.9 provides a brief summary of image communication. The electronic transmission and exchange of medical images will become more important in future for multimedia applications such as electronic patient records in health telematics and integrated care. Section 1.10 completes this chapter with an overview of past, present, and future challenges to biomedical image processing.

This chapter presents the main concepts of morphological image processing. Mathematical morphology has application in diverse areas of image processing such as filtering, segmentation and pattern recognition, applied both to binary and gray-scale images. Section 4.2 addresses the basic binary morphological operations: erosion, dilation, opening and closing. We also present applications of the primary operators, paying particular attention to morphological reconstruction because of its importance and since it is still not widely known. In Sect. 4.3, the same concepts are extended to gray-scale images. Section 4.4 is devoted to watershed-based segmentation. There are many variants of the watershed transform. We introduce the watershed principles with real-world applications. The key to successful segmentation is the design of the marker to eliminate the over-segmentation problem. Finally, Sect. 4.5 presents the multi-scale watershed to segment brain structures from diffusion tensor imaging, a relatively recent imaging modality that is based on magnetic resonance.

The test platform of wheat precision seeding based on image processing techniques is designed to develop the wheat precision seed metering device with high efficiency and precision. Using image processing techniques, this platform gathers images of seeds (wheat) on the conveyer belt which are falling from seed metering device. Then these data are processed and analyzed to calculate the qualified rate, reseeding rate and leakage sowing rate, etc. This paper introduces the whole structure, design parameters of the platform and hardware & software of the image acquisition system were introduced, as well as the method of seed identification and seed-space measurement using image’s threshold and counting the seed’s center. By analyzing the experimental result, the measurement error is less than ± 1mm.

ETC (Electronic Toll Collection) system is used in tollgate of highway. ETC system can automatically complete toll transaction. And, ETC can effectively settle and improves lots of problem in current traffic system. ETC system contains RSU, OBU, road controller unit, collection management center, and other auxiliary unit [1]. PCNN (Pulse coupled neural network) is a principle which describes ocular neural cell activity of mammal visual cortex. And this principle is widely applied to image processing, voice recognition, fault diagnosis, pattern recognition, and decision optimization. Recently, ETC system just save vehicle image to data server. But, in ETC system, vehicle image processing is necessary, and is a key part. While, the time of vehicle image processing is limited. This paper describes a design of vehicle image processing based on PCNN model. Though the test in laboratory, the authors prove that PCNN can be effectively used in vehicle image processing.

In the process of quality analysis of grains, number counting is one of the key steps for agricultural production. After the introduction of the traditional counting methods, an approach based on computer version and image processing technique is proposed in this paper. The overall structure including hardware and software of system is introduced firstly. Then, the image processing methods are described in details, which are mainly composed of gray transformation, denoising, binary conversion, mathematical morphology analysis, et al.. Finally, an experiment is conducted to test the validity of the algorithm, and the result shows that this method is effective and can realize the automatic grain counting.

International audience; The paper presents a collaborative project that offers stand-alone software applications for end-users and a complete open-source platform to rapidly develop/prototype medical image processing work-flows with sophisticated visualization and user interactions. It builds on top of a flexible cross-platform framework (Linux, Windows and MacOS) developed in C++, which guarantees an easy connection of heterogeneous C++ modules and provides the user with libraries of high-level components to construct graphical user interfaces (GUI) including input/output (file management), display, interaction, data processing, etc. In this article, we illustrate the usefulness of this framework through a research project dealing with the study of thrombosis in intra-cranial aneurysms. Algorithms developed by the researchers, such as image segmentation, stent model generation, its interactive virtual deployment in the segmented vessels, as well as the generation of meshes necessary to simulate the blood flow through thus stented vessels, have been implemented in a user-friendly GUI with 3D visualization and interaction.