BazTech - Yadda

1

EDGE detection technique based on bilateral filtering and iterative threshold selection algorithm and transfer learning for traffic sign recognition

Parse Milind, Pramod Dhanya

Zeszyty Naukowe. Transport / Politechnika Śląska

|

2023

|

z. 119

199--222

EN

The traffic sign identification and recognition system (TSIRS) is an essential component for autonomous vehicles to succeed. The TSIRS helps to collect and provide helpful information for autonomous driving systems. The information may include limits on speed, directions for driving, signs to stop or lower the speed, and many more essential things for safe driving. Recently, incidents have been reported regarding autonomous vehicle crashes due to traffic sign identification and recognition system failures. The TSIRS fails to recognize the traffic signs in challenging conditions such as skewed signboards, scratches on traffic symbols, discontinuous or damaged traffic symbols, etc. These challenging conditions are presented for various reasons, such as accidents, storms, artificial damage, etc. Such traffic signs contain an ample amount of noise, because of which traffic sign identification and recognition become a challenging task for automated TSIRS systems. The proposed method in this paper addresses these challenges. The sign edge is a helpful feature for the recognition of traffic signs. A novel traffic sign edge detection algorithm is introduced based on bilateral filtering with adaptive thresholding and varying aperture size that effectively detects the edges from such noisy images. The proposed edge detection algorithm and transfer learning is used to train the Convolutional Neural Network (CNN) models and recognize the traffic signs. The performance of the proposed method is evaluated and compared with existing edge detection methods. The results show that the proposed algorithm achieves optimal Mean Square Error (MSE) and Root Mean Square Error (RMSE) error rates and has a better Signal to Noise Ratio (SNR) and Peak Signal to Noise Ratio (PSNR) ratio than the traditional edge detection algorithms. Furthermore, the precision rate, recall rate, and F1 scores are evaluated for the CNN models. With the German Traffic Sign Benchmark database (GTSRB), the proposed algorithm and Inception V3 CNN model gives promising results when it receives the edge-detected images for training and testing.

2

Zestawy aparaturowe firmy USTER TECHNOLOGIES A.G. służące do oceny jakości płaskich wyrobów włókienniczych. Część 1. Stan prac badawczych dotyczących wprowadzenia i wykorzysta cyfrowej analizy obrazu do oceny jakości płaskich wyrobów włókienniczych

Lewandowski Stanisław, Józkowicz Ignacy

Przegląd Włókienniczy - Włókno, Odzież, Skóra

|

2021

|

nr 2

20--29

PL

W pierwszej części artykułu przedstawiono stan rezultatów prac badawczych związanych z konstrukcją aparatów i urządzeń umożliwiających ocenę struktury, jakości i wyglądu płaskich wyrobów włókienniczych (tkanin, dzianin, itp.), a także automatyczne rozpoznawanie, zliczanie i klasyfikowanie błędów w tych wyrobach. Stan badań w tym zakresie poprzedzono informacjami dotyczącymi technice opartej na cyfrowej analizie obrazu, w połączeniu z elementami sztucznej inteligencji (sztucznymi sieciami neuronowymi) i jej potencjału rozpoznawczego. Przytoczone opracowania stanowią przyczynek do skonstruowania wymienionych urządzeń do przemysłu włókienniczego na skalę przemysłową.

EN

The first part of the article presents the state of research results related to the construction of apparatus and devices enabling assessment of the structure, quality and appearance of flat textile products (fabrics, knitwear, etc.), as well as automatic recognition, counting and classification of errors in these products. The state of research in this area was preceded by information on digital image analysis, combined with elements of artificial intelligence (artificial neural networks) and its recognition potential. The quoted studies contribute to the construction of the mentioned devices for the textile industry on an industrial scale.

3

Fusion of feature selection methods in gene recognition

Gil Fabian, Osowski Stanislaw

Bulletin of the Polish Academy of Sciences. Technical Sciences

|

2021

|

Vol. 69, nr 3

art. no. e136748

EN

The paper presents the fusion approach of different feature selection methods in pattern recognition problems. The following methods are examined: nearest component analysis, Fisher discriminant criterion, refiefF method, stepwise fit, Kolmogorov-Smirnov criteria, T2-test, Kruskall-Wallis test, feature correlation with class, and SVM recursive feature elimination. The sensitivity to the noisy data as well as the repeatability of the most important features are studied. Based on this study, the best selection methods are chosen and applied in the process of selection of the most important genes and gene sequences in a dataset of gene expression microarray in prostate and ovarian cancers. The results of their fusion are presented and discussed. The small selected set of such genes can be treated as biomarkers of cancer.

4

Urbanistyka zasobów lokalnych

Janik Marek

Builder

|

2021

|

R.25, nr 6

26--29

PL

Postulat sensownego wykorzystywania lokalnych zasobów w projektowaniu urbanistycznym wydaje się kwestią niebudzącą większych sporów. W praktyce jednak nader często spotykamy się z sytuacjami „straconych okazji”, czyli właśnie niewykorzystanych czy wręcz zaprzepaszczonych zasobów lokalnych albo konfliktów w sytuacji konieczności trudnego wyboru dotyczącego tego, który z identyfikowanych lokalnych zasobów warto wykorzystać. Przedsięwzięcia inwestycyjne, podejmowane zwykle przez samorząd, bywają wspierane opracowaniami studialnymi, na ogół jednak wykonywanymi już po podjęciu ogólnych kluczowych decyzji. W artykule rozważane są uwarunkowania i możliwości zmian w procesie przedprojektowym, które dałyby szansę na lepsze gospodarowanie zasobami lokalnymi.

EN

The postulate of reasonable use of local resources in urban design seems to be a matter of little dispute. In practice, however, we often encounter situations of "missed opportunities", i.e. unused or even wasted local resources, or conflicts when faced with a difficult choice as to which of the identified local resources should be used. Investments usually undertaken by the local government, are sometimes supported by studies, but usually carried out after the general key decisions have been made. The article considers the conditions and possibilities of changes in the pre-project process, which would give a chance for better management of local resources.

5

Leadership Styles and Talent Retention from Higher Education Institutions in Viet Nam. A Conceptual Framework

Truyen Bui Thi Hoang, Trang Nguyen Phu Phuong

Annals of Computer Science and Information Systems

|

2021

|

Vol. 28

315--319

EN

In recent years, several universities have implemented the accomplishments of the industrial revolution (4.0) in education. This demonstrates the importance of talent retention in the workplace, and brilliant individuals are seen as one of competitive advantage. Managers should have suitable talent management plans because talented individuals are scarce, valuable, and hard to substitute. Through the characteristics that leadership styles will affect, such as reward and recognition, learning orientation, and organizational justice, it will provide the organization with a perspective on the members' feelings about the factors affecting the intention to work long-term at higher education institutions. As a result, the authors propose exploring the talent retention model through leadership styles, which will impact the aspects that employees in an organization feel would be interesting and relevant to them. The authors to guide this study will conduct two phases: qualitative research and quantitative research. To investigate the fundamental factors of leadership style behavior, relating to the talent retention strategy of university leaders in Vietnam, qualitative research will be conducted on 8 universities in three regions. North, Central, and South of Vietnam by semi-structured interview method after interview questions with 8 leaders representing higher education institutions. Quantitative research will be conducted by gathering data from lecturers, researchers from organizations in order to test hypotheses based on the findings of qualitative research.

6

Wpływ czynnika ludzkiego na skuteczność bojową strzelania z broni strzeleckiej za pomocą celownika teleskopowego

Senatorov Volodymyr, Bilokur Mykola, Biloborodov Oleg, Melnyk Olexander

Problemy Techniki Uzbrojenia

|

2020

|

R. 49, z. 153

55--64

PL

Autorzy rozpatrują strukturę zadania bojowego jako logiczny łańcuch przedmiotowych modeli zaangażowanych w jego realizację: strzelec trzymający w rękach broń małokalibrową skierowaną na cel, z celownikiem oraz czynnikiem niszczącym (amunicją). W takim przypadku strzelec ma wizualny kontakt z celem przez celownik optyczny i przestrzeń powietrzną. Jak widać, kluczową rolę w tym łańcuchu odgrywa strzelec. Celem artykułu jest ocena wpływu czynnika ludzkiego na skuteczność bojową w łańcuchu misji bojowej z punktu widzenia podstawowej teorii. W artykule jest rozpatrzony pewien zamknięty cykl wykonania misji bojowej za pomocą broni strzeleckiej z celownikiem optycznym. Prawdopodobieństwo wykonania misji bojowej jest oceniane biorąc pod uwagę poprawność przygotowania danych strzelania, wykrywania, rozpoznawania i identyfikacji celu, poprawnego celowania i trafienia podczas strzelania.

EN

Authors are considering the combat task structureas a logical chain of the object models participating in its execution: shooter with small arms with optical sight in his hands, explosive items (ammunition) which are directed to target. Shooter through opticalsight and air environment is contacting visually with a target. As we can see, the key role in this chain belongs to the shooter. Paper purpose is to assess influence of human factor to combat effectiveness in the chain of combat task execution from a view point of fundamental theory. A closed cycle of combat task execution using small arms with optical sight is considered in the paper. Probability of combat task execution is assessed taking into consideration the reliability of shooting data preparation, target detection,recognition and identification, correct aiming and impact at shooting.

7

Motywowanie pracowników do doskonalenia jakości. Problemy realizacyjne

Bugdol Marek

Problemy Jakości

|

2020

|

R. 52, nr 11

2--6

PL

Artykuł omawia problemy związane z motywacją finansową (tutaj ograniczone do wynagradzania za jakość) i pozafinansową – głównie z systemem uznawania wysiłków na rzecz doskonalenia jakości. Celem artykułu jest próba usystematyzowania wiedzy dotyczącej szeroko rozumianej motywacji jakości. Autor próbuje odpowiedzieć na dwa podstawowe pytania: czy wyzwalane poczucie dumy pracowników może działać motywująco? Jakie środki motywacji wykorzystują organizacje projakościowe i jakie są ich ograniczenia? Główną metodą badawczą zastosowaną przez autora był przegląd literatury.

EN

The article discusses problems related to financial (here limited to rewarding for quality) and non-financial incentives – mainly the system of recognition of efforts to improve quality. The aim of the article is an attempt to systematize the knowledge concerning the broadly understood quality motivation. The author has tried to answer two basic questions: can the released sense of pride of employees have a motivating effect? What tools of motivation are used by pro-quality organizations and what are their limitations? The main research method used by the author was a literature review.

8

A universal architectural pattern and specification method for robot control system design

Kornuta T., Zieliński C., Winiarski T.

Bulletin of the Polish Academy of Sciences. Technical Sciences

|

2020

|

Vol. 68, nr 1

3--29

EN

The paper presents a universal architectural pattern and an associated specification method that can be applied in the design of robot control systems. The approach a describes the system in terms of embodied agents and proposes a multi-step decomposition enabling precise definition of their inner structure and operation. An embodied agent is decomposed into effectors, receptors, both real and virtual, and a control subsystem. Those entities communicate through communication buffers. The activities of those entities are governed by FSMs that invoke behaviours formulated in terms of transition functions taking as arguments the contents of input buffers and producing the values inserted into output buffers. The method is exemplified by applying it to the design of a control system of a robot executing one of the most important tasks for a service robot, i.e. picking up, by a position-force controlled robot, an object located using an RGB-D image acquired from a Kinect. Moreover in order to substantiate the universality of the presented approach we present how classical, known from the literature, robotic architectures can be expressed as systems composed of one or more embodied agents.

9

Porównanie skuteczności wybranych algorytmów rozpoznawania twarzy w przypadku zdjęć o niskiej jakości

Gozdur Jakub, Wiśniewski Bartosz, Kopniak Piotr

Journal of Computer Sciences Institute

|

2019

|

Vol. 10

67--70

PL

Celem artykułu jest określenie skuteczności popularnych algorytmów rozpoznawania twarzy w przypadku zdjęć o niskiej jakości. W trakcie pracy zostały opisane podstawowe algorytmy rozpoznawania twarzy takie jak LBPH, Eigenfaces i Fisherfaces. Do przeprowadzenia badań stworzono platformę badawczą wyposażona w oprogramowanie pozwalające testować dane i zbierać wyniki. Rezultaty badań pokazała, że jedynym algorytmem nadającym się do takich rozwiązań jest LBPH. Pozostałe natomiast nie uzyskały odpowiednio wysokiego współczynnika skuteczności.

EN

The goal of the article is to determine the effectiveness of popular face recognition algorithms for poor quality photos. Basic facial recognition algorithms such as LBPH, Eigenfaces and Fisherfaces were described during the work. A research platform equipped with software allowing to test data and collect results was created. The results of the research showed that the only algorithm suitable for such solutions is LBPH. The others, however, did not achieve a sufficiently high effectiveness factor.

10

Recognition of Sign Language from High Resolution Images Using Adaptive Feature Extraction and Classification

Csóka Filip, Polec Jaroslav, Csóka Tibor, Kačur Juraj

International Journal of Electronics and Telecommunications

|

2019

|

Vol. 65, No. 2

303--308

EN

A variety of algorithms allows gesture recognition in video sequences. Alleviating the need for interpreters is of interest to hearing impaired people, since it allows a great degree of self-sufficiency in communicating their intent to the non-sign language speakers without the need for interpreters. State-of-the-art in currently used algorithms in this domain is capable of either real-time recognition of sign language in low resolution videos or non-real-time recognition in high-resolution videos. This paper proposes a novel approach to real-time recognition of fingerspelling alphabet letters of American Sign Language (ASL) in ultra-high-resolution (UHD) video sequences. The proposed approach is based on adaptive Laplacian of Gaussian (LoG) filtering with local extrema detection using Features from Accelerated Segment Test (FAST) algorithm classified by a Convolutional Neural Network (CNN). The recognition rate of our algorithm was verified on real-life data.

11

A Review : Person Identification using Retinal Fundus Images

Elangovan Poonguzhali, Nath Malaya Kumar

International Journal of Electronics and Telecommunications

|

2019

|

Vol. 65, No. 4

585--596

EN

In this paper a review on biometric person identification has been discussed using features from retinal fundus image. Retina recognition is claimed to be the best person identification method among the biometric recognition systems as the retina is practically impossible to forge. It is found to be most stable, reliable and most secure among all other biometric systems. Retina inherits the property of uniqueness and stability. The features used in the recognition process are either blood vessel features or non-blood vessel features. But the vascular pattern is the most prominent feature utilized by most of the researchers for retina based person identification. Processes involved in this authentication system include pre-processing, feature extraction and feature matching. Bifurcation and crossover points are widely used features among the blood vessel features. Non-blood vessel features include luminance, contrast, and corner points etc. This paper summarizes and compares the different retina based authentication system. Researchers have used publicly available databases such as DRIVE, STARE, VARIA, RIDB, ARIA, AFIO, DRIDB, and SiMES for testing their methods. Various quantitative measures such as accuracy, recognition rate, false rejection rate, false acceptance rate, and equal error rate are used to evaluate the performance of different algorithms. DRIVE database provides 100 % recognition for most of the methods. Rest of the database the accuracy of recognition is more than 90 %.

12

Evaluating KGR10 Polish Word Embeddings in the recognition of temporal expressions using BiLSTM-CRF

Kocoń Jan, Gawor Michał

Schedae Informaticae

|

2018

|

Vol. 27

EN

The article introduces a new set of Polish word embeddings, built using KGR10 corpus, which contains more than 4 billion words. These embeddings are evaluated in the problem of recognition of temporal expressions (timexes) for the Polish language. We described the process of KGR10 corpus creation and a new approach to the recognition problem using Bidirectional Long-Short Term Memory (BiLSTM) network with additional CRF layer, where specific embeddings are essential. We presented experiments and conclusions drawn from them.

13

Rozpoznawanie obiektów w obrazie wideo z kamery do komputera

Cherednyk Oleksandr, Miłosz Elżbieta

Journal of Computer Sciences Institute

|

2018

|

Vol. 8

215--219

PL

Celem artykułu jest określenie skuteczności wykrywania obiektu w obrazie wideo za pomocą kamery internetowej. W trakcie pracy zostały zbadane i opisane podstawowe metody rozpoznawania obiektów na zdjęciu, a mianowicie wykorzystanie sztucznych sieci neuronowych i metod Viola-Jones. Do przeprowadzenia eksperymentów, na podstawie metody Viola-Jones, realizowano aplikację do rozpoznawania obiektów na wideo. Za pomocą tej aplikacji, przeprowadzono badanie w celu określenia skuteczności metody Viola-Jones do wykrywania obiektów na wideo.

EN

The goal is to determine the effectiveness of object detection in a video using the camera for the computer. In the course of work studied and described the main methods of recognition of objects in the image, namely the use of artificial neural networks and techniques of Viola-Jones. For the study, based on the method of Viola-Jones, implemented the application for object recognition in video, as this method is effective for solving this problem. With this application, a study was conducted to determine the effectiveness of the method of viola-Jones to detect objects in the video.

14

Definition of dynamic characteristics of pointer measuring devices on the basis of automatic indications determination

Kucheruk V., Kurytnik I., Kulakov P., Lishchuk R., Moskvichova Y., Kulakova A.

Archives of Control Sciences

|

2018

|

Vol. 28, No. 3

401--418

EN

The article presents the method and algorithm of automatic pointer measuring devices (voltmeter, manometer, metronomes etc.) indications determination in order to determine their dynamic characteristics with the help of web-camera and personal computer. The results of testing and experimental research of developed tool for determining the dynamic characteristics of pointer measuring devices are given. Using this method, the algorithm and the software developed, the process of determining the dynamic characteristics of the pointer measuring devices was automated. The time of recognition and calculation of one measured value for a dual-core processor and webcam with a resolution of 0.3 Mp averages 250–330 ms.

15

Minusy programu Rodzina 500 Plus

Dziwosz E.

Zeszyty Naukowe. Organizacja i Zarządzanie / Politechnika Śląska

|

2017

|

z. 104

209--216

PL

Przedmiotem artykułu jest krytyczna refleksja dotycząca programu polskiego rządu Rodzina 500 Plus, zakładającego wsparcie finansowe dla rodzin w celu zwiększenia dzietności w Polsce. Artykuł koncentruję się na relacji pomiędzy ekonomią a kulturą, szczególnie na wpływie założeń programu na wizerunek polskiej kobiety, który od momentu uzyskania przez nią praw wyborczych uległ zmianie: z kobiety zależnej finansowo do wykształconej i niezależnej. Realizacja programu rodzi wiele pytań dotyczących jego wpływu na aktywność zawodową polskich kobiet, ale też na poczucie ich uznania. Niemiecki socjolog Axel Honneth łączy uznanie z najważniejszą sferą życia człowieka – z pracą. Z pracą, z której na rzecz 500 Plus coraz częściej rezygnują kobiety. Autorka artykułu zadaje pytania o możliwy wpływ programu na poczucie uznania polskich kobiet.

EN

Subject of this article is a critical reflection on the program launched by the Polish Government, Family 500 Plus, which provides financial support for families with aim of increasing birthrate in Poland. The article focuses on a relationship between the economics and culture of this program. Specifically how this program will influence the image of Polish women, which have changed since women received their electoral rights – from a financially dependent woman, to an educated and independent woman. The implementation of the 500 Plus raises questions about the impact of the program on professional activity of Polish women, but also on the sense of their recognition. German sociologist Axel Honneth links a recognition with most important sphere of human life, work. Due to the impact of 500 Plus, women are increasingly giving up their jobs. The author of the article examines the possible impact of the program on the sense of recognition of Polish women.

16

Projekt architektury programowej autonomicznego biomimetycznego pojazdu podwodnego przeznaczonego do zadań rozpoznawania podwodnego

Praczyk Tomasz, Szymak Piotr

Modern Engineering

|

2017

|

1

1--11

PL

Artykuł przedstawia projekt architektury programowej autonomicznego biomimetycznego pojazdu podwodnego (ABPP) przeznaczonego do zadań rozpoznania podwodnego. Pojazd ten jest przedmiotem badań w ramach projektu finansowanego przez Narodowe Centrum Badań i Rozwoju. Dwie cechy czynią ten pojazd unikatowym w warunkach polskich, są nimi, po pierwsze –autonomiczność, a po drugie –biomimetyczność czyli podobieństwo do żywych przedstawicieli środowiska morskiego. Całkowita nowość technologii opracowywanej w ramach projektu czyni konstrukcję pojazdu w tym jego oprogramowania dużym wyzwaniem. Proponowana w artykule architektura oprogramowania zakłada jego elastyczność oraz skalowalność.

EN

The paper presents the project of software architecture for autonomous biomimetic underwater vehicle dedicated for underwater reconnaissance tasks. The vehicle is build within the framework of the national project funded by National Center for Research and Development. Two features make this vehicle unique in Poland, that is, autonomy, and resemblance to living organisms of sea environment. The project presented in the paper provides for easy expansion and modification of the vehicle control system with new sensors and autonomous behaviors.

17

Recognition of rotor damages in a DC motor using acoustic signals

Głowacz A., Głowacz Z.

Bulletin of the Polish Academy of Sciences. Technical Sciences

|

2017

|

Vol. 65, nr 2

187--194

EN

Diagnosis of electrical direct current motors is essential for industrial plants. The emphasis is put on the development of diagnostic methods of solutions for capturing, processing and recognition of diagnostic signals. This paper presents a technique of early fault diagnosis of a DC motor. The proposed approach is based on acoustic signals. A real-world data of the DC motor were used in the analysis. The work provides an original feature extraction method called the shortened method of frequencies selection (SMoFS-15). The obtained results of the presented analysis show that the early fault diagnostic method can be used for monitoring electrical DC motors. The proposed method can also support other fault diagnosis methods based on thermal, current, and vibration signals.

18

Verification of people based on palm vein with the ROI automatic appointment

Smorawa D.

Journal of Applied Mathematics and Computational Mechanics

|

2016

|

Vol. 15, nr 3

123--133

EN

In the paper, the new approach to identification and verification of people based on the palm vein pattern will be presented. To create the feature vector, palm vein shape geometric arrangement will be applied. For detailed features will be considered similarly to minutiae which was applied in finger lines analysis in vein endings and bifurcation. The methods of vein location on the inner hand, methods of minutiae location, and features coding will be discussed in detail. To extract specific features a two-dimension density function will be used. The method to determine minutiae-vein bifurcation and endings will be presented.

19

Mathematical problem of straightening text lines

Tymchenko O., Kulczycka I., Szturo K.

Technical Sciences / University of Warmia and Mazury in Olsztyn

|

2015

|

nr 18(4)

313--321

EN

The rapid distribution of digital cameras has caused several new problems related to text recognition. Based on experimental studies, was revealed that existing OCR systems cannot cope with complex perspective and geometric distortions that arise when photographing text document. Therefore it is necessary to apply text documents pre-processing so that the text lines were straight and horizontal. This article briefly consider existing methods pre-processing documents and found that it depend on the type of distortion and not universal. Proposed new method involving the mathematical raising of straightened text lines on the image and heterogeneous distortion correction based on a page surface transformation model. This method is better than others because it is universal and corrects any type of distortion, including a combination of several types of distortion.

20

Comparative Survey on Traffic Sign Detection and Recognition: a Review

Wali S. B., Hannan M. A., Hussain A., Samad S. A.

Przegląd Elektrotechniczny

|

2015

|

R. 91, nr 12

38-42

EN

Developing real-time Advanced Driver Assistance Systems (ADAS) based on video aiming to extract reliable vehicle state information has attracted a lot of attention during the past decades. This ADAS system includes inter-vehicle communication, driver behavioral monitoring, and human-machine interactions. In these systems, robust and reliable traffic sign detection and recognition (TSDR) technique is a critical step for ensuring vehicle safety. This paper provides a comprehensive survey on traffic sign detection and recognition system based on image and video data. Our main focus is to present the current trends and challenges in the field of developing an efficient TSDR system followed by a detail comparative study between different renowned methods used by various researchers. Finally, conclusion followed by some future suggestion is provided to develop an efficient TSDR system is provided. This survey will hopefully lead to develop an effective traffic sign detection and recognition system which will ensure driver safety in future.

PL

System ADAS (Advanced Driver Assistance System) obejmuje także metody rozpoznawania znaków drogowych. W artykule przedstawiono przegląd metod detekcji i rozpoznawania znaków drogowych bazujących na obrazie video. W artykule dokonano oceny istniejących metod oraz zaproponowano środki poprawy ich efektywności.