Wyniki wyszukiwania - BazTech

1

Adaptive Hough Transform Circle Detection Application in Developed 2D Coordinate Measuring System

Zięba Przemysław, Gąska Adam, Harmatys Wiktor, Krawczyk Marcin

Advances in Science and Technology. Research Journal

|

2023

|

Vol. 17, no 6

185--191

EN

This paper describes a cheap, portable coordinate system for measuring circular geometries. The developed software can measure diameters, circle center coordinates, and distances between them. The circle detector uses the Adaptive Hough Transform implemented in the OpenCV library. For image rectification, the system uses reference circle positions on the plane parallel to the plane of the measured ones. Pixel size is determined by the distances between the reference circle positions on the same plane. The mean measurement value from a series of photos was found efficient estimation of accurate value, significantly improving overall system accuracy.

2

Projekt rozpoznawania krawędzi w obrazie na podstawie algorytmów detekcji krawędzi

Kucharski Robert, Matuszewski Jan

Elektronika : konstrukcje, technologie, zastosowania

|

2022

|

Vol. 63, Nr 7

5--10

PL

W artykule przedstawiono aplikację komputerową opracowaną w środowisku programowym MATLAB do obliczania krawędzi w obrazie, wykorzystującą algorytmy detekcji krawędzi. Do stworzenia aplikacji wykorzystano obraz barwnego ptaka, w celu wyodrębnienia jak największej ilości krawędzi. Dla każdego algorytmu przedstawiony został histogram obrazu reprezentujący rozkład liczbowy występowania w obrazie różnych poziomów jasności. Wyniki obliczeń dały możliwość porównania algorytmów względem błędu średniokwadratowego (MSE) i stosunku sygnału do szumu (PSNR).

EN

The article presents a computer application developed in the MATLAB software environment to calculate edges in an image, using edge detection algorithms. The image of a colorful bird was used to create the application in order to extract as many edges as possible. For each algorithm, an image of histogram was presented representing the numerical distribution of the occurrence of different brightness levels in the image. The results of the calculations made it possible to compare the algorithms based on the mean square error (MSE) and the peak signal-to-noise ratio (PSNR).

3

Intelligent agrobots for crop yield estimation using computer vision

Bini D., Pamela D., Mary Thusnavis Bella I., Shamia D., Prince Shajin

Computer Assisted Methods in Engineering and Science

|

2022

|

Vol. 29, no. 1-2 spec.

161--175

EN

The machine vision-based autonomous intelligent robots perform precise farm tasks suchas robot harvesting, weeding, pest or fertilizer spraying, monitoring, and pruning. Estimating crop yield is an essential assignment on a regional or federal scale. For a long timethe estimation measures were based on the statistics from manual counting of plants ina specific zone. The computer vision algorithms have addressed the technical drawbacksof the conventional image processing techniques and established an autonomous disciplineand yielded new approaches to crop planning. A method for quantitative assessment ofa tomato crop has been developed in this research using color thresholding in MATLAB using the RGB color model. Converting an RGB image to a grayscale image is one of thesteps involved in detecting red color in a taken image. After subtracting the two images,a median filter is employed to filter the noisy pixels to produce a two-dimensional blackand white image. The bounding boxes are used to label the binary digital images to detectrelated components, and the parameters of the labeled regions are computed to measurethe number of tomatoes in a crop. The obtained R2 correlation coefficient between thetomato berry counting algorithm and human counting was 0.98. Furthermore, the color ofeach pixel in the acquired image is evaluated by examining RGB values for pixel intensitiesin the obtained image. The performance of the berry counting algorithm was evaluated,and the technique was determined to have a high precision and recognition ratio of 96%.The research indicates that this technique may be used to estimate the crop yield, whichis helpful information for forecasting yields, planning harvest plans, and generating prescription maps for field-specific management strategies. The proposed model performedexceptionally well in estimating yield with each tomato (Solanum lycopersicum) crop.

4

Enhanced of Tool Management Based on Machine Vision in the Field of Metal Forming Technology

Świłło Sławomir, Cacko Robert

Archives of Metallurgy and Materials

|

2022

|

Vol. 67, iss. 4

1419--1425

EN

In this article, the authors focused on the widely used aluminium extrusion technology, where the die quality and durability are the essential factors. In this study, detailed solutions in the three-key area have been presented. First is applying marking technology, where a laser technique was proposed as a consistent light source of high power in a selected, narrow spectral range. In the second, an automated and reliable identification method of alphanumeric characters was investigated using an advanced machine vision system and digital image processing adopted to the industrial conditions. Third, a proposed concept of online tool management was introduced as an efficient process for properly planning the production process, cost estimation and risk assessment. In this research, the authors pay attention to the designed vision system’s speed, reliability, and mobility. This leads to the practical, industrial application of the proposed solutions, where the influence of external factors is not negligible.

5

Mobilny system przetwarzania obrazu oparty na platformie Raspberry Pi 4

Chlastawa Łukasz

Science, Technology and Innovation

|

2021

|

Vol. 12, no. 1

16--25

PL

W artykule zaprezentowano system przetwarzania obrazu oparty na platformie Raspberry Pi (RPi). Na początku artykułu omówiono podstawowe założenia oraz cel wykonania systemu. W dalszej części przedstawiono strukturę i sposób działania systemu. Zaprezentowano aplikację okienkową zarządzającą systemem oraz pozwalającą na wykonanie przekształceń kontekstowych oraz widmowych na obrazach, jak również pomiar parametrów, takich jak: czas przetwarzania obrazu oraz błąd średniokwadratowy (ang. Mean Square Error – MSE). Wykonywane przekształcenia oparto zarówno na gotowych formułach zawartych w bibliotece OpenCV, jak również własnych implementacjach, a wśród nich na funkcji realizującej algorytm szybkiej transformacji Fouriera FFT (ang. Fast Fourier Transform) radix-2. Zaprezentowano przykłady przekształceń wraz ze wskazaniem ich użyteczności. Na końcu przedstawiono potencjał rozwojowy utworzonego systemu oraz zaproponowano zastosowanie w konkretnych rozwiązaniach.

EN

The article presents an image processing system based on the Raspberry Pi (RPi) platform. At the beginning of the article, the basic assumptions and purpose of the system are discussed. The following section presents the structure and operation of the system. The window application managing the system and allowing to perform contextual and spectral transformations on images as well as the measurement of parameters such as image processing time and mean square error (MSE) was discussed. The transformations performed were based both on ready formulas contained in the OpenCV library and the author’s implementations, including the function implementing the Fast Fourier Transform algorithm radix-2. Examples of transformations were presented along with their usefulness. In the end, the development potential of the created system is presented and its application in specific solutions is proposed.

6

An enhancement in accuracy of vehicle detection in parking areas employing Haar-like features and AdaBoost algorithm

Tamim Tiabur Rahman, Alam Shariful, Asraf Amanullah

Przegląd Elektrotechniczny

|

2021

|

R. 97, nr 9

135--138

EN

With the increasing number of vehicles on the road, often it is difficult to find suitable parking spaces in metropolitan cities. It may cause wastage of time as well as traffic congestion if proper parking spaces haven’t been preserved. An autonomous parking system can detect empty parking spaces and allow drivers to effectively park in empty parking spaces which require less time and less fuel. This paper has presented an intelligent vision-based approach that discovers vehicles and empty spaces autonomously. We have introduced Haar-like feature cascade classifier trained by a machine learning technique for the vehicle detection process. The proposed system has delivered promising results to the detection accuracy of the vehicles to allow parking places. The vehicle detection accuracy of the proposed system has been validated through simulation. Besides, the proposed approach has made available the optimum threshold value to acquire the best possible detection accuracy. The advantages of the proposed scheme are a) it saves time to get the vehicles parked; b) it provides to get rid of traffic congestion; c) as the driver gets the space immediately, so less energy is required with the proposed approach. Later, a brief comparison of performance metrics among various classifiers is provided.

PL

Przy rosnącej liczbie pojazdów poruszających się po drogach często trudno jest znaleźć odpowiednie miejsca parkingowe w metropoliach. Może to spowodować stratę czasu, a także zatory drogowe, jeśli nie zostaną zachowane odpowiednie miejsca parkingowe. Autonomiczny system parkowania może wykrywać puste miejsca parkingowe i umożliwiać kierowcom efektywne parkowanie na pustych miejscach, które wymagają mniej czasu i mniej paliwa. W artykule przedstawiono inteligentne podejście oparte na wizji, które autonomicznie wykrywa pojazdy i puste przestrzenie. Wprowadziliśmy kaskadowy klasyfikator cech podobny do Haara, wyszkolony techniką uczenia maszynowego dla procesu wykrywania pojazdów. Zaproponowany system przyniósł obiecujące wyniki w zakresie dokładności wykrywania pojazdów w celu umożliwienia parkowania. Dokładność wykrywania pojazdów proponowanego systemu została zweryfikowana poprzez symulację. Ponadto zaproponowane podejście umożliwiło uzyskanie optymalnej wartości progowej w celu uzyskania najlepszej możliwej dokładności wykrywania. Zaletami proponowanego schematu są: a) oszczędność czasu na zaparkowanie pojazdów; b) zapewnia pozbycie się zatorów komunikacyjnych; c) ponieważ kierowca natychmiast otrzymuje miejsce, więc przy proponowanym podejściu potrzeba mniej energii. Później przedstawiono krótkie porównanie metryk wydajności między różnymi klasyfikatorami.

7

Single-camera system for measuring paper deformations based on image analysis

Pełczyński Paweł, Szewczyk Włodzimierz, Bieńkowska Maria

Metrology and Measurement Systems

|

2021

|

Vol. 28, nr 3

509--522

EN

The article presents a new technique for measuring paper deformation in unidirectional tensile tests, based on recording and analysis of a series of specimen images. The proposed technique differs from the DIC-based deformation measurement in that the cross-correlation of image data has been replaced with linear filtering. For this purpose, a regular grid of markers is printed on the sample. Filtering the image creates local maxima in the places where markers occur. The developed algorithm finds their location with sub-pixel accuracy. Printing a grid of markers on tested paper and use of reference objects visible in the same image as the paper sample, freed from the need to mechanically connect the camera and the universal testing machine and from the necessity to electronically synchronize their work. The obtained deformation distributions and Poisson’s ratios are in accordance with the literature data which confirms the correctness of the developed measurement technique.

8

Badanie możliwości realizacji steganografii w języku C#

Pawlak Piotr, Podgórniak Jakub Bogdan, Kozieł Grzegorz

Journal of Computer Sciences Institute

|

2021

|

Vol. 21

383--390

PL

Moc obliczeniowa współczesnych komputerów jest wystarczająca do łamania wielu zabezpieczeń kryptograficznych, w związku z powyższym konieczne jest utworzenie dodatkowej warstwy bezpieczeństwa polegającej na ukryciu same-go faktu przekazywania tajnej wiadomości. W tym celu mogą zostać wykorzystane metody steganograficzne. Artykuł poświęcono analizie możliwości realizacji steganografii w obrazach cyfrowych przy wykorzystaniu języka programo-wania C#. Wytypowane zostały istniejące biblioteki, przekształcenia matematyczne, a także zaimplementowane zostały własne rozwiązania. W celu dokonania obiektywnej oceny metod ukrywania danych obliczono parametry opisujące stopień zniekształceń transformat oraz ukrywanych obrazów. Następnie wyłoniono optymalne rozwiązania dla konkretnych problemów oraz przeprowadzono demonstracyjne ukrycie danych. Na podstawie otrzymanych rezultatów można stwierdzić, że możliwe jest kompleksowe zrealizowanie steganografii w języku C#. Istnieje wiele gotowych bibliotek i narzędzi, których skuteczność została zweryfikowana w przeprowadzonej analizie. Z racji sprzeczności wymagań stenograficznych nie jest możliwe optymalne spełnienie ich wszystkich tj.: niewykrywalności, odporności na zniszczenie i pojemności informacyjnej. Z tego powodu nie jest możliwe jednoznaczne wskazanie najlepszych rozwiązań. Aby osiągnąć zadowalające rezultaty należy szukać kompromisów pomiędzy stawianymi wymaganiami.

EN

The computing power of modern computers is sufficient to break many cryptographic keys, therefore it is necessary to create an additional security layer which hides the very fact of transmitting a secret message. For this purpose, ste-ganographic methods can be used. The article is devoted to the analysis of the possibility of implementing digital imag-es steganography with the use of the C # programming language. Firstly, existing libraries and mathematical transfor-mations which can help with performing steganography were found. Also, own code solutions were implemented. In order to objectively evaluate the methods of data hiding, the parameters describing the degree of distortion of trans-forms and hidden images were calculated. Subsequently, optimal solutions for specific problems were identified and demonstrational data hiding was performed. Based on the obtained results, it can be concluded that it is possible to successfully implement steganography in the C # language. There are many ready-made libraries and tools, the effec-tiveness of which has been verified in the conducted analysis. Due to the contradictory of stenographic requirements, it is not possible to meet all of them optimally, i.e. undetectability, resistance to destruction and information capacity. For this reason, it is not possible to clearly indicate the best solutions. In order to achieve satisfactory results, one should look for compromises between the set requirements.

9

Experimental investigation into material characteristics of pea gravel

Zhang Jinliang, Huang Qiuxiang, Hu Chao, Wang Zhiqiang

Archives of Civil Engineering

|

2021

|

Vol. 67, nr 3

415--435

EN

Pea gravel is a kind of a coarse aggregate with a specific particle size used to fill the annular gap between the lining segments and the surrounding ground when tunnel construction with shield machines is performed in hard rock. The main purpose of the present study is to propose quantitative morphological indices of the pea gravel and to establish their relations with the void content of the aggregate and the compressive strength of the mixture of pea gravel and slurry (MPS). Results indicate that the pea gravel of the crushed rock generally have a larger void content than that of the river pebble, and the grain size has the highest influence on the void ratio. Elongation, roughness and angularity have moderate influences on the void ratio. The content of the oversize or undersize particles in the sample affects the void ratio of the granular assembly in a contrary way. The compressive strength of the MPS made with the river pebble is obviously smaller than that of the MPS made with the crushed rock. In the crushed rock samples, the compressive strength increases with the increase of the oversize particle content. The relations between the morphological properties and the void content, and the morphological properties and the compressive strength of the MPS are expressed as regression functions. The outcomes of this study would assist with quality assessments in TBM engineering for the selection of the pea gravel material and the prediction of the compressive strength of the MPS.

10

Ekstrakcja danych numerycznych z wykresów słuchowych potencjałów wywołanych

Mały Dominik, Dobrowolski Andrzej

Elektronika : konstrukcje, technologie, zastosowania

|

2020

|

Vol. 61, nr 3

4--7

PL

W artykule przedstawiono projekt aplikacji opracowanej w środowisku Matlab, umożliwiającej ekstrakcję danych liczbowych z wykresów słuchowych potencjałów wywołanych z zachowaniem wszelkich charakterystycznych cech przetwarzanej krzywej. Opracowany kod podzielony został na cztery zasadnicze moduły: moduł wczytania pliku graficznego zawierającego wykres słuchowego potencjału wywołanego, moduł wstępnego przetwarzania obrazu, moduł ekstrakcji danych oraz moduł skalowania.

EN

This article shows application project developed in Matlab, allowing data extraction form auditory evoked potential charts with keeping the characteristic features of processed curve. Designed Matlab script was divided into four fundamental modules: module for loading a graphic file containing a graph of auditory evoked potential, image preprocessing module, data extraction module and scaling module.

11

Salt and pepper noise reduction and edge detection algorithm based on neutrosophic logic

Arulpandy P., Trinita Pricilla M.

Computer Science

|

2020

|

T. 21 (2)

193--209

EN

Noise reduction of images is a challenging task in image processing. Salt and pepper noise is one kind of noise that affects a gray-scale image significantly.Generally, the median filter is used to reduce salt and pepper noise; it gives optimum results while compared to other image filters. Median filter works only up to a certain level of noise intensity. Here we proposed a neighborhoodbased image filter called nbd-filter, it works perfectly for gray image regardless of noise intensity. It reduces salt and pepper noise significantly at any noise level and produces a noise-free image. Further, we proposed an edge detection algorithm based on the neutrosophic set, it detects edges efficiently for images corrupted by noise and noise-free images. Neutrosophic set (NS) is a powerful tool to deal with indeterminacy. Since most of the real-life images consists of indeterminate regions, Neutrosophy is a perfect tool for edge detection. In this paper, the neutrosophic set is applied to the image domain and a novel edge detection technique is proposed.

12

Simple Optical Coordinate Measuring System, Based on Fiducial Markers Detection, and its Accuracy Assessment

Gąska Piotr, Harmatys Wiktor, Gruza Maciej, Gąska Adam, Sładek Jerzy

Advances in Science and Technology. Research Journal

|

2020

|

Vol. 14, no 4

213--219

EN

The area of application of contactless measuring systems has been rapidly growing over the past two decades. Development of contactless measuring methods can also be observed in Coordinate Metrology. Due to the growing number of contactless systems found in industry, there is also a growing interest in the issue of their accuracy among research centres. The interesting new solution which can be applied in contactless measurements is the usage of fiducial markers in dimensional metrology. In this paper, the authors present a simple and cheap optical system and try to assess its accuracy. A calibration process of a reference plate is described as well. Research was conducted for basic measuring tasks met in Coordinate Measuring Technique. Markers are attached to the z-axis ram of Coordinate Measuring Machine which is used as a reference system. The article presents the results obtained for basic measuring tasks, which can be a basis for further research aimed at improving the accuracy of measurements performed using fiducial markers.

13

Algorytm SLAM z pominięciem czujników odometrycznych w kontekście różnych typów procesorów obliczeniowych

Fiedeń Mateusz, Miotk Michał, Dąbek Przemysław, Muraszkowski Artur

Interdisciplinary Journal of Engineering Sciences

|

2019

|

Vol. 7, no. 1

28--37

PL

SLAM jest to algorytm równoczesnego mapowania otoczenia i lokalizowania się na tworzonej mapie. Wykorzystywany jest w robotach autonomicznych przeznaczonych do pracy w nieznanym bądź dynamicznie zmieniającym się otoczeniu. W swojej podstawowej formie wykorzystuje czujnik odległości, taki jak lidar bądź radar oraz dane o przesunięciu pozyskiwane z enkoderów. Dzięki zastosowaniu odpowiednich strategii dodawania kolejnych skanów oraz filtracji pobieranych danych uzyskuje się dokładne mapy, jednak użycie enkoderów, nie zawsze jest możliwe. W artykule poruszony zostaje temat pozycjonowania i mapowania przy użyciu lidaru bez wykorzystywania dodatkowych czujników zapewniających dane odometryczne. Zaproponowany zostaje odpowiedni algorytm oraz dyskusja dotycząca zastosowanych procesorów obliczeniowych, na których jest uruchamiany (wyłącznie CPU oraz z wykorzystaniem GPU wspierającego technologię CUDA). Zaprezentowane są wyniki w formie wykresów zależności czasu od iteracji, uzyskanych chmur punktów, a także parametrów sprzętowych obserwowanych w trakcie działania algorytmu.

EN

SLAM stands for a simultaneous localization and mapping. It’s used in construction of autonomic robots, designed for work in topographically unknown areas or dynamically changing environment. In its simplest form it utilizes distance sensor, lidar for example, and displacement data obtained from encoders. Thanks to application of appropriate strategies of adding next scan iterations and filtration of obtained data, it allows to create accurate maps with minimal computing power required. However, usage of encoders is not always possible, as in case of boats, legged robots or drones. To solve this problem, there’s proposed an algorithm that allows for localization and mapping in described situation, with a discussion on type of processors used by program. Because of the task specifics, it’s necessary to match many obtained simultaneously measurements with created map. For this purpose, the differences between algorithm version using only CPU, by spreading the task between different processor threads, and algorithm version that utilize graphical computing acceleration, that make calculations on many parallel CUDA cores, were checked. Both implementations were tested on the corridor inside building with results in the form of charts comparing time needed for separated iterations to complete.

14

Aggregate segmentation of asphaltic mixes using digital image processing

Reyes-Ortiz Oscar R., Mejía M., Useche-Castelblanco J. S.

Bulletin of the Polish Academy of Sciences. Technical Sciences

|

2019

|

Vol. 67, nr 2

279--287

EN

The study of the different engineering materials according to their mechanical and dynamic characteristics has become an area of research interest in recent years. Several studies have verified that the mechanical properties of the material are directly affected by the distribution and size of the particles that compose it. Such is the case of asphalt mixtures. For this reason, different digital tools have been developed in order to be able to detect the structural components of the elements in a precise, clear and efficient manner. In this work, a segmentation model is developed for different types of dense-graded asphalt mixtures with grain sizes from 9.5 mm to 0.0075 mm, using sieve size reconstruction of the laboratory production curve. The laboratory curve is used to validate the particles detection model that uses morphological operations for elements separation. All this with the objective of developing a versatile tool for the analysis and study of pavement structures in a non-destructive test. The results show that the model presented in this work is able to segment elements with an area greater than 0.0324 mm2 and reproduce the sieve size curves of the mixtures with a high percentage of precision.

15

A fast dehazing method with high color fidelity

Shan Y., Ge P.

Optica Applicata

|

2018

|

Vol. 48, nr 3

515--527

EN

In this paper, we present a fog image degradation model with the combination of HSI color space and the atmosphere scattering model. Based on the model, a fast dehazing method with high color fidelity has been proposed. The main advantage of the proposed method compared with others is its speed. This speed allows the method to be applied within real-time processing applications as a step of preprocessing. Another advantage is the possibility to handle both color images and gray level images. The algorithm depends only on on two parameters, and both are easy to set. Experiments on haze images demonstrate that the proposed method can achieve wonderful image visibility with a higher computing speed.

16

Time performance of RGB to HSI colour space transformation methods

Ziemba A., Fornalik-Wajs E.

Archives of Thermodynamics

|

2018

|

Vol. 39, no 1

111--128

EN

Present paper is a continuation of works on evaluation of red, green, blue (RGB) to hue, saturation, intensity (HSI) colour space transformation in regard to digital image processing application in optical measurements methods. HSI colour space seems to be the most suitable domain for engineering applications due to its immunity to non-uniform lightning. Previous stages referred to the analysis of various RGB to HSI colour space transformations equivalence and programming platform configuration influence on the algorithms execution. The main purpose of this step is to understand the influence of computer processor architecture on the computing time, since analysis of images requires considerable computer resources. The technical development of computer components is very fast and selection of particular processor architecture can be an advantage for fastening the image analysis and then the measurements results. In this paper the colour space transformation algorithms, their complexity and execution time are discussed. The most common algorithms were compared with the authors own one. Computing time was considered as the main criterion taking into account a technical advancement of two computer processor architectures. It was shown that proposed algorithm was characterized by shorter execution time than in reported previously results.

17

Preprocessing Photos of Receipts for Recognition

Korobacz W., Tabędzki M.

Advances in Computer Science Research

|

2018

|

Nr 14

87--103

EN

The subject of this work is methods of image pre-processing, applied to receipts photos. The purpose is to improve their quality, allowing to increase the efficiency of the conventional text recognition software (OCR). The authors had mainly difficult cases in mind – photos taken freehand in unfavorable lighting conditions. The work describes the analyzed methods of filtering, binarization, searching for the edge of the image, image straightening, marking the area of interest, thinning. The preliminary results with OCR software on a small data set were also presented. Thanks to pre-processing, character recognition efficiency has been improved by 25%. The final part presents conclusions and plans for future work.

PL

Tematem tej pracy są metody przetwarzania wstępnego obrazów, zastosowane do zdjęć przedstawiających paragony. Celem jest poprawa ich jakości, pozwalająca zwiększyć skuteczność działania oprogramowania do rozpoznawania tekstu. Autorzy mieli na uwadze głównie trudne przypadki – zdjęć robionych „z ręki”, przy słabym oświetleniu. Praca opisuje przeanalizowane metody filtrowania, binaryzacji, wyszukiwania krawędzi, prostowania obrazu, oznaczania obszaru zainteresowania, ścieniania. Przedstawiono również wstępne wyniki testów z oprogramowaniem OCR na niewielkiej bazie obrazów. Przetwarzanie wstępne pozwoliło na poprawę identyfikacji znaków o 25%. W końcowej części przedstawiono wnioski oraz plany przyszłej pracy.

18

Adaptacyjna metoda poprawy kontrastu dla cyfrowych obrazów rozmazów cytologicznych

Oszutowska-Mazurek D. A., Waker-Wójciuk G, Sycz K.

Problemy Nauk Stosowanych

|

2016

|

T. 5

163--170

PL

Wstęp i cel: Zwiększenie kontrastu między jądrem komórkowym a cytoplazmą zapewnia poprawę wizualizacji cytologicznych cech komórki. Celem pracy jest poprawa wizualizacji jądra komórkowego. Materiał i metody: Automatyzacja doboru progu z wykorzystaniem algorytmu adaptacyjnego progowania dla rozkładów dwumodalnych została przeprowadzona dla obrazów rozmazów cytologicznych. Wyniki: Uzyskano zwiększony kontrast dla jądra komórkowego, dzięki czemu osiągnięto poprawę wizualizacji struktury chromatyny. Wniosek: Adaptacyjna metoda poprawy kontrastu może być użyteczna w diagnostyce cytologicznej, ale potrzebna jest weryfikacja w oparciu o większą bazę danych obrazów cytologicznych.

EN

Introduction and aim: Contrast enhancement between nucleus and cytoplasm ensures improvement of cytological features visualisation. The aim of study is improvement of nucleus visualisation. Material and methods: Automation of threshold estimation with the use of adaptive tresholding algorithm for bimodal distributions was provided for images of cytological smears. Results: Improved contrast for cell nuclei was obtained and therefore the enhancement of chromatine structure visualisation is achieved. Conclusion: Adaptive method of contrast enhancement could be useful in cytological diagnosis, but requires verification with the use of large database of cytological images.

19

Histogram of Oriented Gradients with Cell Average Brightness for Human Detection

Wójcikowski M.

Metrology and Measurement Systems

|

2016

|

Vol. 23, nr 1

27--36

EN

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.

20

The use of web technologies on the example of the online store application supporting graphical selection of clothing for clients. Student project

Kielanowski P., Zabierowski W., Adamek Ł., Gęsiarz H.

International Journal of Microelectronics and Computer Science

|

2016

|

Vol. 7, nr 3

109--113

EN

Building online store with using current technologies should not be a challenge, although the promotion of this type of page without any additional functionalities can be difficult especially with huge competition. Graphical support for selection of clothing for clients would be distinguishing feature.