Wyniki wyszukiwania - Biblioteka Nauki

1

FPGA implementations of image processing algorithms for real-time computer vision systems

100%

Kraft M.

Studia z Automatyki i Informatyki

|

2007

|

tom T. 32

103-116

EN

This paper describes complete implementations of image processing algorithms using FPGAs. Implemented algorithms include convolution, morphological operations, edge detection and feature point (corner) detection. The described processors are capable of processing image data stream with the speed of houndreds of frames per second for a 512x512, 8-bit gray-scale image. The implemented modules can be connected to form a complete, low level image processing system. Resource usage summary, resulting images, as well as block diagrams of processors' architectures are included in the paper.

PL

Artykuł opisuje kompletne implementacje algorytmów przetwarzania obrazu w układzie FPGA. Zaimplementowane zostały algorytmy przetwarzania za pomocą operacji konwolucji, operacji morfologicznych, algorytm wykrywania krawędzi oraz algorytm wykrywania cech punktowych (narożników). Opisywane procesory umożliwiają przetwarzanie strumienia danych obrazowych z prędkością setek klatek na sekundę dla obrazu o rozdzielczości 512x512, w 8-bitowej skali szarości. Moduły można łączyć tak, aby utworzyły kompletny system niskopoziomowego przetwarzania obrazów. W artykule zamieszczono informacje o schematy blokowe, informacje o użyciu zasobów przez poszczególne moduły oraz obrazy wynikowe.

2

Preprocessing algorithms of vision research damage to concrete railway sleepers

100%

Lesiak P. , Sokołowski A.

Problemy Kolejnictwa

|

2018

|

tom Z. 180

93--99

EN

The paper presents algorithms for the preprocessing of the visual method of detecting damages of concrete railway sleepers. It starts with acquiring images of the surface of the sleepers, by selecting the recorded frames of the images. Then, the color image is transformed into monochrome, so as to obtain the highest contrast possible. The Kanan and Cottrell algorithms were used for this purpose. A simple way is to segment the damage images of the sleepers, by thresholding, in order to binarize them. However, more elaborate algorithms are recommended. For this purpose, images are denoted using a median filter and further morphological operations to extract the edge of damage. For this purpose, noise is removed from images using a median filter, and morphological operations are carried out, to extract the edge of damage. In addition, texture images of the surface of the sleepers are used, removing them from the visual content. As the criterion for selecting the preprocessing algorithm, the shape of the image histogram and its standard deviation were assumed. Such prepared images form the basis for further assessment of the size of damages (cracks and voids) and classification of concrete sleepers.

3

Silhouette Processing Via Mathematical Morphology with Pose-Aware Structuring Elements Based on 3D Model

100%

Jabłoński M.

Image Processing & Communications

|

2012

|

tom Vol. 17, no. 4

71--78

EN

In the paper, the method of poseaware silhouette processing is presented. Morphological closing is proposed to enhance segmented silhouette object. The contribution of the work is adaptation of structuring element used for mathematical morphology erosions and dilations. It is proposed to use camera parameters, 3D model of the scene, model of the silhouette and its position to compute structuring element adequate to the individual projected to the camera image. Structuring element computation and basic morphology operators were implemented in OpenCL environment and tested on parallel GPU platform. Comparison with utility software packages is provided and results are briefly discussed.

4

Image processing algorithms application for 3D multi phase flow model reconstruction

75%

Nowakowski J. , Kaczorowski D. , Tomczak Ł.

Automatyka / Akademia Górniczo-Hutnicza im. Stanisława Staszica w Krakowie

|

2006

|

tom T. 10, z. 3

395-398

EN

This article presents the problem of creation of three dimensional model which can visualize results of the flow measurement in 3D graphics. Firstly the algorithm prepares the data for proposed module. This preparation consists of sequences of processing images algorithms. The tests were conducted for series of USG images. These images represent the multi-phase flow of water and oil in the pipe.

PL

Artykuł przedstawia program do reprezentowania wyników w grafice trójwymiarowej. Proces tworzenia wyników rozpoczyna się od sekwencji operacji przetwarzania obrazów dwuwymiarowych, a następnie przedstawienie otrzymanych wyników w grafice 3D. Testy prowadzone były dla serii obrazów przedstawiających przepływ wody i oleju w rurze PCV. Obrazy te otrzymano z ultrasonografu.

5

Determination of the optimal scanning step for evaluation of image reconstruction quality in magnetoacoustic tomography with magnetic induction

63%

Zywica A. R. , Ziolkowski M.

Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska

|

2019

|

tom T. 9, nr 4

38--42

EN

Magnetoacoustic Tomography with Magnetic Induction (MAT-MI) is a new hybrid imaging modality especially dedicated for non-invasive electrical conductivity imaging of low-conductivity objects such as e.g. biological tissues. The purpose of the present paper is to determine the optimal scanning step assuring the best quality of image reconstruction. In order to resolve this problem a special image reconstruction quality indicator based on binarisation has been applied. Taking into account different numbers of measuring points and various image processing algorithms, the conditions allowing successful image reconstruction have been provided in the paper. Finally, the image reconstruction examples for objects’ complex shapes have been analysed.

PL

Tomografia magnetoakustyczna ze wzbudzeniem indukcyjnym (MAT-MI) to nowa hybrydowa technika obrazowania dedykowana szczególnie do nieinwazyjnego obrazowania obiektów o niskiej konduktywności elektrycznej, takich jak na przykład tkanki biologiczne. Celem niniejszej pracy jest określenie optymalnego kroku skanowania zapewniającego najlepszą jakość rekonstrukcji obrazu. W celu rozwiązania tego problemu zastosowano specjalny wskaźnik jakości rekonstrukcji obrazu bazujący na binaryzacji. W artykule przedstawiono warunki umożliwiające pomyślne zrekonstruowanie obrazu biorąc pod uwagę różną liczbę punktów pomiarowych oraz różne algorytmy przetwarzania obrazu. W końcowym etapie pracy przeanalizowano przykłady rekonstrukcji obrazu dla obiektów o bardziej złożonych kształtach.

6

Surface casting defects inspection using vision system and neural network techniques

63%

Świłło S. J. , Perzyk M.

Archives of Foundry Engineering

|

2013

|

tom Vol. 13, iss. 4

103--106

EN

The paper presents a vision based approach and neural network techniques in surface defects inspection and categorization. Depending on part design and processing techniques, castings may develop surface discontinuities such as cracks and pores that greatly influence the material’s properties Since the human visual inspection for the surface is slow and expensive, a computer vision system is an alternative solution for the online inspection. The authors present the developed vision system uses an advanced image processing algorithm based on modified Laplacian of Gaussian edge detection method and advanced lighting system. The defect inspection algorithm consists of several parameters that allow the user to specify the sensitivity level at which he can accept the defects in the casting. In addition to the developed image processing algorithm and vision system apparatus, an advanced learning process has been developed, based on neural network techniques. Finally, as an example three groups of defects were investigated demonstrates automatic selection and categorization of the measured defects, such as blowholes, shrinkage porosity and shrinkage cavity.

7

Study of structure and morphology of surface layers formed on TRIP steel by the femtosecond laser treatment

63%

Duriagina Z. A. , Tepla T. L. , Kulyk V. V. , Kosarevych R. Y. , Vira V. V. , Semeniuk O. A.

Journal of Achievements in Materials and Manufacturing Engineering

|

2019

|

tom Vol. 93, nr 1-2

5--19

EN

Purpose: The purpose of the work is to demonstrate the possibility of using a femtosecond laser for forming surface layers with an adjustable microstructure on the surface of TRIP steel 03X13AG19, and processing the obtained images using digital complexes. Design/methodology/approach: A laser treatment of TRIP steel (03X13AG19) with pulses of femtosecond duration was carried out in a melting mode. The source of the radiation is a femtosecond titanium-sapphire Ti:Al2O3 complex consisting of a predefining femtosecond generator “Mira Optima 900-F” and regenerative amplifier Legend F-1K-HE. Peculiarities of the surface structure of irradiated samples were studied using a Solver P47-PRO atomic force microscope. The structural-geometric parameters of the surface of the investigated steel treated with the femtosecond laser were determined using the software package Nova 1.0.26.1443 and the functions of the Image Analysis. Microstructural analysis was performed using a raster electron microscope JSM 6700F and a METAM-1P microscope. In this work, the digitization of images of microstructures obtained as a result of surface irradiation by highly concentrated energy streams of femtosecond duration has been carried out. The analysis of the surface structure of laser-structured materials was carried out using a metallographic complex with the software ImProcQCV. Findings: It has been revealed that the predetermined change of the laser treatment mode changes the microrelief and the shape and size of the fragments of the surface structure of the investigated steel. The use of digital image processing allowed to generalize the morphological features of the surface structure, to assess in detail the character of the microrelief, and to monitor under in-situ mode the structure and properties of the surface of the material being studied. Research limitations/implications: The obtained research results can be applied to stainless steels of various structural classes. Practical implications: Surface digitization significantly reduces the time for research, improves the quality and accuracy of the data obtained, makes it possible to conduct in-situ researches with the further implementation of the results using the Internet of Things technologies. Originality/value: A comprehensive approach is proposed for the estimation of parameters of laser-induced periodic surface structures (LIPSS) using a metallographic complex with the software ImProcQCV.

8

Automatic inspection of surface defects in die castings after machining

51%

Świłło S. J. , Perzyk M.

Archives of Foundry Engineering

|

2011

|

tom Vol. 11, iss. 3 spec.

231--236

EN

A new camera based machine vision system for the automatic inspection of surface defects in aluminum die casting was developed by the authors. The problem of surface defects in aluminum die casting is widespread throughout the foundry industry and their detection is o f paramount importance in maintaining product quality. The casting surfaces are the most highly loaded regions of materials and components. Mechanical and thermal loads as well as corrosion or irradiation attacks are directed primarily at the surface of the castings. Depending on part design and processing techniques, castings may develop surface discontinuities such as cracks or tears, inclusions due to chemical reactions or foreign material in the molten metal, and pores that greatly influence the material ability to withs tand these loads. Surface defects may act as a stress concentrator initiating a fracture point. If a pressure is applied in this area, the casting can fracture. The human visual system is well adapted to perform in areas of variety and change; the visual inspection processes, on the other hand, require observing the same type of image repeatedly to detect anomalies. Slow, expensive, erratic inspection usually is the result. Computer based visual inspection provides a viable alternative to human inspectors. Developed by authors machine vision system uses an image processing algorithm based on modified Laplacian of Gaussian edge detection method to detect defects with different sizes and shapes. The defect inspection algorithm consists of three parameters. One is a parameter of defects sensitivity, the second parameter is a thres hold level and the third parameter is to identify the detected defects size and shape. The machine vision system has been successfully tested for the different types of defects on the surface of castings.