As a machining technology, welding can cause serious accidents by overloading or operation mistakes. Through analyzing the causes of various welding accidents, we found that the major cause for damage imposed after welding parts are loaded is the fracture of materials. Therefore, studying the influence of welding residual stress on the fracture property of materials is of great significance. This paper applied the digital image correlation technique to study the fracture property of welding parts under the influence of welding residual stress. In addition, standard parts and welding parts were selected to carry out a contrast experiment. Room temperature tensile tests were performed on both standard parts and test pieces after residual stress measurement. Using displacement field and strain field data obtained through VIC-2D software, the stress intensity factor around the crack tip of each specimen under the conditions of small load was calculated and corresponding analysis was carried out.

In order to achieve extended life of asphalt pavement, one of key points is to achieve a good bonding between it’s components. This research paper presents findings on the topic of influence of polyethylene bitumen modification on the adhesion between bitumen and aggregate. A novel method of quantifying the bitumen coated area, based on computer image analysis, has been developed for this study. Two different methods of adhesion testing were employed, namely boiling water method and the rolling bottle method. Aggregates used in this study were granite and limestone. Based on 108 measurements, it was concluded that polyethylene modification has a negative impact on binder aggregate adhesion.

This paper presents application of optical microscope for evaluation of microtexture changes of coarse aggregate during simulated polishing in laboratory. Observations of the apparent changes on surfaces of seven different aggregates are presented. Simulation polishing of aggregate was performed in accordance with PN-EN 1097-8:2009. lmages of the aggregate surface were taken with the optical microscope in the reflection mode in particular stages of polishing. Digital images were analyzed. Standard deviation was determined on the basis of the histogram of intensities from digital images of the surfaces of aggregate grains which was assurned as the measure of changes in microtexture during simulated polishing (namely the σh parameter). Statistical analysis has shown that the changes of the σh parameter between the particular stages of polishing confirm certain trends related to the petrographic characteristic of the rocks. Aggregates which included minerals of similar hardness (granodiorite, dolomile, basalt) were more prone to polishing than gabbro and postglacial. Regeneration of the microtexture, the recovery to its original asperity, occurred in the case of quartz sandstone and steelmaking slag.

A technology that utilizes penetrating rays is one of the oldest nondestructive testing methods. Nowadays, the process of radiogram analysis is performed by qualified human operators and automatic systems are still under development. In this work we present advanced algorithms for automatic segmentation of radiographic images of welded joints. The goal of segmentation of a radiogram is to change and simplify representation of the image into a form that is more meaningful and easier to analyse automatically. The radiogram is divided into parts containing the weld line, image quality indicators, lead characters, and possible defects. Then, each part is analysed separately by specialized algorithms within the framework of the Intelligent System for Radiogram Analysis.

This research proposes a method to enhance the payload message by embedding messages on the dilated edge areas by the Least Significant Bit (LSB) method. To add security aspects to messages, messages are not embedded directly on the LSB but encrypted with XOR operations with Most Significant Bit (MSB). The experimental results of the test in this study showed that the dilation process to some extent can increase the payload of 18.65% and the average bpp is 1.42 while maintaining the imperceptibilty quality of stego image with an average PSNR value of about 47 dB, SSIM is 0.9977 and MSE is 1.13.

Testing of image intensifier tubes is still done using mostly manual methods due to a series of both technical and legal problems with test automation. Computerized stations for semi-automated testing of IITs are considered as novelty and are under continuous improvements. This paper presents a novel test station that enables semi-automated measurement of image intensifier tubes. Wide test capabilities and advanced design solutions rise the developed test station significantly above the current level of night vision metrology.

Super-resolution image reconstruction utilizes two algorithms, where one is for single-frame image reconstruction, and the other is for multi-frame image reconstruction. Singleframe image reconstruction generally takes the first degradation and is followed by reconstruction, which essentially creates a problem of insufficient characterization. Multi-frame images provide additional information for image reconstruction relative to single frame images due to the slight differences between sequential frames. However, the existing super-resolution algorithm for multi-frame images do not take advantage of this key factor, either because of loose structure and complexity, or because the individual frames are restored poorly. This paper proposes a new SR reconstruction algorithm for images using Multi-grained Cascade Forest. Multi-frame image reconstruction is processed sequentially. Firstly, the image registration algorithm uses a convolutional neural network to register low-resolution image sequences, and then the images are reconstructed after registration by the Multi-grained Cascade Forest reconstruction algorithm. Finally, the reconstructed images are fused. The optimal algorithm is selected for each step to get the most out of the details and tightly connect the internal logic of each sequential step. This novel approach proposed in this paper, in which the depth of the cascade forest is procedurally generated for recovered images, rather than being a constant. After training each layer, the recovered image is automatically evaluated, and new layers are constructed for training until an optimal restored image is obtained. Experiments show that this method improves the quality of image reconstruction while preserving the details of the image.

Image segmentation is a typical operation in many image analysis and computer vision applications. However, hyperspectral image segmentation is a field which have not been fully investigated. In this study an analogue- digital image segmentation technique is presented. The system uses an acousto-optic tuneable filter, and a CCD camera to capture hyperspectral images that are stored in a digital grey scale format. The data set was built considering several objects with remarkable differences in the reflectance and brightness components. In addition, the work presents a semi-supervised segmentation technique to deal with the complex problem of hyperspectral image segmentation, with its corresponding quantitative and qualitative evaluation. Particularly, the developed acousto-optic system is capable to acquire 120 frames through the whole visible light spectrum. Moreover, the analysis of the spectral images of a given object enables its segmentation using a simple subtraction operation. Experimental results showed that it is possible to segment any region of interest with a good performance rate by using the proposed analogue-digital segmentation technique.

This study examines the pyrolysis of a single cylindrical wood particle using particle image velocimetry (PIV). The pyrolysis was conducted inside a pyrolysis reactor designed for this purpose. The experimental setup presented in this paper is capable of effectively characterizing the intensity of pyrolysis based on velocity distribution in the vicinity of wood particles. The results of the gas velocity distribution show that evaporation of moisture has as a major impact on the formation of the gas cushion as devolatilization.

The paper presents test results for the assessment of the tracer content in a three-component (green peas, sorghum, maize) feed mixture that is based on the fluorescent method. The homogeneity of mixtures was determined on the basis of the maize content (as the key component), which was treated with fluorescent substance: tinopal, rhodamine B, uranine and eosin. The key components were wet-treated with fluorescent substances with different concentrations. Feed components were mixed in a vertical funnel-flow mixer. 10 samples were collected from each mixed batch. Samples were placed in a chamber equipped with UV light and, then, an image recorded as BMP file was generated. The image was analysed by means of the software programme Patan. On the basis of the analyses conducted, data on the maize content marked with a fluorescent marker were obtained. Additionally, the content of the key component was determined in a conventional manner – using an analytical scale. Results indicate the possibility of using this method for homogeneity assessment of the three-component grain mixture. From these tests, fluorescent substances that can be applied in the case of maize as a key component, together with their minimum concentrations, were identified: tinopal 0.3%, rhodamine B 0.001%.

The micro-Particle Image Velocimetry (micro-PIV) was used to measure flow velocities in micro-channels

in two passive micromixers: a microfluidic Venturi mixer and a microfluidic spiral mixer, both preceded

by standard “Y” micromixers. The micro-devices were made of borosilicate glass, with micro-engineering

techniques dedicated to micro-PIV measurements. The obtained velocity profiles show differences in the

flow structure in both cases. The micro-PIV enables understanding the micro-flow phenomena and can help

to increase reproducibility of micromixers in mass production.

A modification of the descriptor in a human detector using Histogram of Oriented Gradients (HOG) and Support Vector Machine (SVM) is presented. The proposed modification requires inserting the values of average cell brightness resulting in the increase of the descriptor length from 3780 to 3908 values, but it is easy to compute and instantly gives ≈ 25% improvement of the miss rate at 10‒4 False Positives Per Window (FPPW). The modification has been tested on two versions of HOG-based descriptors: the classic Dalal-Triggs and the modified one, where, instead of spatial Gaussian masks for blocks, an additional central cell has been used. The proposed modification is suitable for hardware implementations of HOG-based detectors, enabling an increase of the detection accuracy or resignation from the use of some hardware-unfriendly operations, such as a spatial Gaussian mask. The results of testing its influence on the brightness changes of test images are also presented. The descriptor may be used in sensor networks equipped with hardware acceleration of image processing to detect humans in the images.

This paper presents an algorithm for restoring telescope images corrupted by turbulence effects and readout noise of a telescope system in order to determine centroid positions of stars, especially the position of a reference star. A computation method employing an accurate centroid estimation algorithm reconstructing a point spread function (PSF) from the recorded astronomical images has been used. Minimisation of turbulence effects and telescope control system noise in long exposure images acquired and recorded by the ground telescope is proposed. As a solution of the distortion error a minimisation signal is dedicated to GoTo calibration procedures built in control mechanisms of the electromechanical telescope system. The proposed method has been verified in the Matlab environment for real deep sky images recorded by the ground telescope system.

The article proposes a method for measuring discomfort glare which uses numerical description of the phenomenon in the form of a digital luminance distribution map recorded on a CCD array. Essential procedures for determining partial quantities which are necessary for calculation of UGR index are discussed in detail, along with techniques for measuring position index and size of light sources, with regard to the parameters of the registering system and coordinates of the images of the sources on the array.

This paper presents the improved version of the classification system for supporting glaucoma diagnosis in ophthalmology. In this

paper we propose the new segmentation step based on the support vector clustering algorithm which enables better classification performance.

An automated method for crack identification and quantitative description of crack systems in concrete was developed in order to aid a service life assessment of concrete elements in structures. Flat polished specimens for crack analysis were impregnated with epoxy resin containing fluorescent dye. The examination of the crack system was performed in ultraviolet light using a stereomicroscope and an Image Pro Plus image analysis system on specimens cored out of several concrete structures. The laboratory tests were performed on cast specimens to establish correlations between water penetration and chloride diffusion and crack system parameters. The analysis of cracks in concrete cores taken from structures resulted in interesting conclusions based on the crack width distribution and crack localization with respect to steel reinforcement. The method was found very effective to support standard concrete diagnostics methods.

The article describes the process of creating 3D models of architectural objects on the basis of video images, which had been acquired by a Sony NEX-VG10E fixed focal length video camera. It was assumed, that based on video and Terrestrial Laser Scanning data it is possible to develop 3D models of architectural objects. The acquisition of video data was preceded by the calibration of video camera. The process of creating 3D models from video data involves the following steps: video frames selection for the orientation process, orientation of video frames using points with known coordinates from Terrestrial Laser Scanning (TLS), generating a TIN model using automatic matching methods. The above objects have been measured with an impulse laser scanner, Leica ScanStation 2. Created 3D models of architectural objects were compared with 3D models of the same objects for which the self-calibration bundle adjustment process was performed. In this order a PhotoModeler Software was used. In order to assess the accuracy of the developed 3D models of architectural objects, points with known coordinates from Terrestrial Laser Scanning were used. To assess the accuracy a shortest distance method was used. Analysis of the accuracy showed that 3D models generated from video images differ by about 0.06 ÷ 0.13 m compared to TLS data.

Qualitative and quantitative results of high terrain elevation effect on spectral radiance of optical satellite image which affect the accuracy in retrieving of land surface cover changes is given. The paper includes two main parts: correction model of spectral radiance of satellite image affected by high terrain elevation and assessment of impacts and variation of land cover changes before and after correcting influence of high terrain elevation to the spectral radiance of the image. Study has been carried out with SPOT 5 in Hoa Binh mountain area of two periods: 2007 and 2010. Results showed that appropriate correction model is the Meyer’s one. The impacts of correction spectral radiance to 7 classes of classified images fluctuate from 15% to 400%. The varying changes before and after correction of image radiation fluctuate over 7 classes from 5% to 100%.

Image registration is a key component of various image processing operations which involve the analysis of different image data sets. Automatic image registration domains have witnessed the application of many intelligent methodologies over the past decade; however inability to properly model object shape as well as contextual information had limited the attainable accuracy. In this paper, we propose a framework for accurate feature shape modeling and adaptive resampling using advanced techniques such as Vector Machines, Cellular Neural Network (CNN), SIFT, coreset, and Cellular Automata. CNN has found to be effective in improving feature matching as well as resampling stages of registration and complexity of the approach has been considerably reduced using corset optimization The salient features of this work are cellular neural network approach based SIFT feature point optimisation, adaptive resampling and intelligent object modelling. Developed methodology has been compared with contemporary methods using different statistical measures. Investigations over various satellite images revealed that considerable success was achieved with the approach. System has dynamically used spectral and spatial information for representing contextual knowledge using CNN-prolog approach. Methodology also illustrated to be effective in providing intelligent interpretation and adaptive resampling.

The water’s edge is the most iconic and identifiable image related to the city of Durban and in seeking an ‘authenticity’ that typifies the built fabric of the city, the image that this place creates is arguably the answer. Since its formal establishment as a settlement in 1824, this edge has been a primary element in the urban fabric. Development of the space has been fairly incremental over the last two centuries, starting with colonial infl uenced built interventions, but much of what is there currently stems from the 1930’s onwards, leading to a Modernist and later Contemporary sense of place that is moderated by regionalist infl uences, lending itself to creating a somewhat contextually relevant image. This ‘international yet local’ sense of place is however under threat from the increasingly prominent ‘global’ image of a-contextual glass high-rise towers placed along a non-descript public realm typical of global capital interests that is a hallmark of the turnkey project trends by developers from the East currently sweeping the African continent.

Evaluating the image quality is a very important problem in image and video processing. Numerous methods have been proposed over the past years to automatically evaluate the quality of images in agreement with human quality judgments. The purpose of this work is to present subjective and objective quality assessment methods and their classification. Eleven widely used and recommended by International Telecommunication Union (ITU) subjective methods are compared and described. Thirteen objective method is briefly presented (including MSE, MD, PCC, EPSNR, SSIM, MS-SSIM, FSIM, MAD, VSNR, VQM, NQM, DM, and 3D-GSM). Furthermore the list of widely used subjective quality data set is provided.

For brain tumour treatment plans, the diagnoses and predictions made by medical doctors and radiologists are dependent on medical imaging. Obtaining clinically meaningful information from various imaging modalities such as computerized tomography (CT), positron emission tomography (PET) and magnetic resonance (MR) scans are the core methods in software and advanced screening utilized by radiologists. In this paper, a universal and complex framework for two parts of the dose control process – tumours detection and tumours area segmentation from medical images is introduced. The framework formed the implementation of methods to detect glioma tumour from CT and PET scans. Two deep learning pre-trained models: VGG19 and VGG19-BN were investigated and utilized to fuse CT and PET examinations results. Mask R-CNN (region-based convolutional neural network) was used for tumour detection – output of the model is bounding box coordinates for each object in the image – tumour. U-Net was used to perform semantic segmentation – segment malignant cells and tumour area. Transfer learning technique was used to increase the accuracy of models while having a limited collection of the dataset. Data augmentation methods were applied to generate and increase the number of training samples. The implemented framework can be utilized for other use-cases that combine object detection and area segmentation from grayscale and RGB images, especially to shape computer-aided diagnosis (CADx) and computer-aided detection (CADe) systems in the healthcare industry to facilitate and assist doctors and medical care providers.