Rosa Maria Vasconcelos
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Rosa Maria Vasconcelos has a total of 71 co-authors. Here are the top co-authors by number of shared publications:
- Filomena Soares
University of Minho
34 shared publications - Vítor Carvalho
Ai-Applied Artificial Intelligence Laboratory, School of Technology, Polytechnic University of Cávado and Ave (UPCA), 4750-810 Barcelos, Portugal
33 shared publications - Luis Amaral
University of Minho, Portugal
19 shared publications - Michael Belsley
Centre of Physics of Minho and Porto Universities (CF-UM-UP), Laboratory for Physics of Materials and Emergent Technologies (LaPMET), University of Minho, Campus de Gualtar, 4710-057 Braga, Portugal
18 shared publications - Claudio da Rocha Brito
Science and Education Research Council
16 shared publications - Victor Freitas de Azeredo Barros
University of Minho
15 shared publications
Latest Publications
- Open Access
- 12 August 2025
- Published by European Alliance for Innovation n.o. in EAI Endorsed Transactions on Digital Transformation of Industrial Processes
- Vol. 1 (2)
A Low-Cost Framework for Textile Yarn Characterization Using Image Processing
The textile industry increasingly demands innovative and cost-effective solutions for yarn quality assessment, as conventional equipment is costly and occupies substantial space. This work presents a compact, low-cost image processing framework to characterize key yarn parameters, providing a foundation for future automated quality control systems. The framework employs classical image processing techniques—smoothing, thresholding, segmentation, and morphological operations—implemented with open-source tools such as Visual Studio and OpenCV. An experimental setup using low-cost hardware enabled the acquisition of high-quality images under controlled conditions. The system extracted parameters including linear mass, average diameter, specific volume, defect quantification, hairiness coefficient, and twist direction and pitch. Tests on three yarn types (cotton and polyester) produced results comparable to the industrial reference Uster Tester 3, with error rates below 7%. The proposed solution offers an affordable alternative for small industries and research laboratories, with potential for future integration of advanced computer vision and artificial intelligence to enhance defect detection and classification.
- 12 August 2025
- Published by European Alliance for Innovation n.o. in EAI Endorsed Transactions on Digital Transformation of Industrial Processes
- Vol. 1 (2)
Open AccessA Low-Cost Framework for Textile Yarn Characterization Using Image Processing
The textile industry increasingly demands innovative and cost-effective solutions for yarn quality assessment, as conventional equipment is costly and occupies substantial space. This work presents a compact, low-cost image processing framework to characterize key yarn parameters, providing a foundation for future automated quality control systems. The framework employs classical image processing techniques—smoothing, thresholding, segmentation, and morphological operations—implemented with open-source tools such as Visual Studio and OpenCV. An experimental setup using low-cost hardware enabled the acquisition of high-quality images under controlled conditions. The system extracted parameters including linear mass, average diameter, specific volume, defect quantification, hairiness coefficient, and twist direction and pitch. Tests on three yarn types (cotton and polyester) produced results comparable to the industrial reference Uster Tester 3, with error rates below 7%. The proposed solution offers an affordable alternative for small industries and research laboratories, with potential for future integration of advanced computer vision and artificial intelligence to enhance defect detection and classification.
- Open Access
- 27 December 2024
- Published by MDPI AG in Applied Sciences
- Vol. 15 (1) , 149
A Novel Deep Learning Approach for Yarn Hairiness Characterization Using an Improved YOLOv5 Algorithm
In textile manufacturing, ensuring high-quality yarn is crucial, as it directly influences the overall quality of the end product. However, imperfections like protruding and loop fibers, known as ‘hairiness’, can significantly impact yarn quality, leading to defects in the final fabrics. Controlling yarn quality in the spinning process is essential, but current commercial equipment is expensive and limited to analyzing only a few parameters. The advent of artificial intelligence (AI) offers a promising solution to this challenge. By utilizing deep learning algorithms, a model can detect various yarn irregularities, including thick places, thin places, and neps, while characterizing hairiness by distinguishing between loop and protruding fibers in digital yarn images. This paper proposes a novel approach using deep learning, specifically, an enhanced algorithm based on YOLOv5s6, to characterize different types of yarn hairiness. Key performance indicators include precision, recall, F1-score, mAP0.5:0.95, and mAP0.5. The experimental results show significant improvements, with the proposed algorithm increasing model mAP0.5 by 5% to 6% and mAP0.5:0.95 by 11% to 12% compared to the standard YOLOv5s6 model. A 10k-fold cross-validation method is applied, providing an accurate estimate of the performance on unseen data and facilitating unbiased comparisons with other approaches.
- 27 December 2024
- Published by MDPI AG in Applied Sciences
- Vol. 15 (1) , 149
Open AccessA Novel Deep Learning Approach for Yarn Hairiness Characterization Using an Improved YOLOv5 Algorithm
In textile manufacturing, ensuring high-quality yarn is crucial, as it directly influences the overall quality of the end product. However, imperfections like protruding and loop fibers, known as ‘hairiness’, can significantly impact yarn quality, leading to defects in the final fabrics. Controlling yarn quality in the spinning process is essential, but current commercial equipment is expensive and limited to analyzing only a few parameters. The advent of artificial intelligence (AI) offers a promising solution to this challenge. By utilizing deep learning algorithms, a model can detect various yarn irregularities, including thick places, thin places, and neps, while characterizing hairiness by distinguishing between loop and protruding fibers in digital yarn images. This paper proposes a novel approach using deep learning, specifically, an enhanced algorithm based on YOLOv5s6, to characterize different types of yarn hairiness. Key performance indicators include precision, recall, F1-score, mAP0.5:0.95, and mAP0.5. The experimental results show significant improvements, with the proposed algorithm increasing model mAP0.5 by 5% to 6% and mAP0.5:0.95 by 11% to 12% compared to the standard YOLOv5s6 model. A 10k-fold cross-validation method is applied, providing an accurate estimate of the performance on unseen data and facilitating unbiased comparisons with other approaches.
- Open Access
- 21 March 2024
- Published by Elsevier in Data in Brief
- Vol. 54, 110355
Online yarn hairiness– Loop & protruding fibers dataset
- 21 March 2024
- Published by Elsevier in Data in Brief
- Vol. 54, 110355
Open AccessOnline yarn hairiness– Loop & protruding fibers dataset
- 18 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Transnational Higher Education: Diversity as Challenge
Despite the opportunities for intercultural exchange and diversity in higher education, HEIs continue to grapple with implementing diversity policies and establishing a culture that fosters dialogue and acceptance of diverse perspectives and modes of life. This paper analyzes important trends in the country (Portugal), highlighting key incidents and identified problems, as well as showcasing main practices that have been implemented. Furthermore, it describes the primary policy instruments adopted by one specific university - University of Minho- and provides insights into students' perceptions of discrimination and hate practices within the same institution. By examining these aspects, this work aims to contribute to the understanding of the challenges and potential strategies for Higher Education Institutions (HEI) in fostering a culture of diversity, ultimately paving the way for more inclusive and equitable learning environments in engineering education.
- 18 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Transnational Higher Education: Diversity as Challenge
Despite the opportunities for intercultural exchange and diversity in higher education, HEIs continue to grapple with implementing diversity policies and establishing a culture that fosters dialogue and acceptance of diverse perspectives and modes of life. This paper analyzes important trends in the country (Portugal), highlighting key incidents and identified problems, as well as showcasing main practices that have been implemented. Furthermore, it describes the primary policy instruments adopted by one specific university - University of Minho- and provides insights into students' perceptions of discrimination and hate practices within the same institution. By examining these aspects, this work aims to contribute to the understanding of the challenges and potential strategies for Higher Education Institutions (HEI) in fostering a culture of diversity, ultimately paving the way for more inclusive and equitable learning environments in engineering education.
- Open Access
- 3 January 2023
- Published by MDPI AG in Electronics
- Vol. 12 (1) , 236
Intelligent Computer Vision System for Analysis and Characterization of Yarn Quality
The quality of yarn is essential in the control of the fabrics processes. There is some commercial equipment that measures the quality of yarn based on sensors, of different types, used for collecting data about some textile yarn characteristic parameters. The irregularity of the textile thread influences its physical properties/characteristics and there may be a possibility of a break in the textile thread during the fabric manufacturing process. This can contribute to the occurrence of unwanted patterns in fabrics that deteriorate their quality. The existing equipment, for the above-mentioned purpose, is characterized by its high size and cost, and for allowing the analysis of only few yarn quality parameters. The main findings/results of the study are the yarn analysis method as well as the developed algorithm, which allows the analysis of defects in a more precise way. Thus, this paper presents the development and results obtained with the design of a mechatronic prototype integrating a computer vision system that allows, among other parameters, the analysis and classification, in real time, of the hairs of the yarn using artificial intelligence techniques. The system also determines other characteristics inherent to the yarn quality analysis, such as: linear mass, diameter, volume, twist orientation, twist step, average mass deviation, coefficient of variation, hairiness coefficient, average hairiness deviation, and standard hairiness deviation, as well as performing spectral analysis. A comparison of the obtained results with the designed system and a commercial equipment was performed validating the undertaken methodology.
- 3 January 2023
- Published by MDPI AG in Electronics
- Vol. 12 (1) , 236
Open AccessIntelligent Computer Vision System for Analysis and Characterization of Yarn Quality
The quality of yarn is essential in the control of the fabrics processes. There is some commercial equipment that measures the quality of yarn based on sensors, of different types, used for collecting data about some textile yarn characteristic parameters. The irregularity of the textile thread influences its physical properties/characteristics and there may be a possibility of a break in the textile thread during the fabric manufacturing process. This can contribute to the occurrence of unwanted patterns in fabrics that deteriorate their quality. The existing equipment, for the above-mentioned purpose, is characterized by its high size and cost, and for allowing the analysis of only few yarn quality parameters. The main findings/results of the study are the yarn analysis method as well as the developed algorithm, which allows the analysis of defects in a more precise way. Thus, this paper presents the development and results obtained with the design of a mechatronic prototype integrating a computer vision system that allows, among other parameters, the analysis and classification, in real time, of the hairs of the yarn using artificial intelligence techniques. The system also determines other characteristics inherent to the yarn quality analysis, such as: linear mass, diameter, volume, twist orientation, twist step, average mass deviation, coefficient of variation, hairiness coefficient, average hairiness deviation, and standard hairiness deviation, as well as performing spectral analysis. A comparison of the obtained results with the designed system and a commercial equipment was performed validating the undertaken methodology.
- Open Access
- 30 November 2022
- Published by MDPI AG in Preprints.org
Intelligent Computer Vision System for Analysis and Characterization of Yarn Quality
The quality of yarn is essential in the control of the fabrics processes. There is some commercial equipment that measures the quality of yarn based on sensors, of different types, used for collecting data about some yarn characteristic parameters. The existing equipment, for the above-mentioned purpose, is characterized by its high size and cost, and for allowing the analysis of only few yarn quality parameters. Thus, this paper presents the development and results obtained with the design of a mechatronic prototype integrating a computer vision system that allows, among other parameters, the analysis and classification, in real time, of the hairs of the yarn using artificial intelligence techniques. The system also determines other characteristics inherent to the yarn quality analysis, such as: linear mass, diameter, volume, twist orientation, twist step, average mass deviation, coefficient of variation, hairiness coefficient, average hairiness deviation and standard hairiness deviation, as well as performs spectral analysis. A comparison of the obtained results with the designed system and a commercial equipment was performed validating the undertaken methodology.
- 30 November 2022
- Published by MDPI AG in Preprints.org
Open AccessIntelligent Computer Vision System for Analysis and Characterization of Yarn Quality
The quality of yarn is essential in the control of the fabrics processes. There is some commercial equipment that measures the quality of yarn based on sensors, of different types, used for collecting data about some yarn characteristic parameters. The existing equipment, for the above-mentioned purpose, is characterized by its high size and cost, and for allowing the analysis of only few yarn quality parameters. Thus, this paper presents the development and results obtained with the design of a mechatronic prototype integrating a computer vision system that allows, among other parameters, the analysis and classification, in real time, of the hairs of the yarn using artificial intelligence techniques. The system also determines other characteristics inherent to the yarn quality analysis, such as: linear mass, diameter, volume, twist orientation, twist step, average mass deviation, coefficient of variation, hairiness coefficient, average hairiness deviation and standard hairiness deviation, as well as performs spectral analysis. A comparison of the obtained results with the designed system and a commercial equipment was performed validating the undertaken methodology.
- 20 October 2022
- Published by Springer Nature
- p. 662-674
Analysis of Sustainable Marketing Practices of Fashion Brands: A Multiple Case Analysis in the Portuguese Market
- 20 October 2022
- Published by Springer Nature
- p. 662-674
Analysis of Sustainable Marketing Practices of Fashion Brands: A Multiple Case Analysis in the Portuguese Market
- 11 July 2022
- Published by Trans Tech Publications, Ltd. in Advances in Science and Technology
- Vol. 113, 169-174
Time as Challenge in Textile Industry: Issues of Education, Culture and Science
The textile industry has developed throughout the 21st century highly sustained by the accuracy of time control, reduction of waiting times and intensification of working time regimes. It is one of the industries where the times and methods were best tested and where mass production model was intensely developed. In parallel, the textile industry followed through a colossal transformation at the level of lifestyles, with the increase diversification of fashion consumption [1]. Currently, the textile industry is associated with various fashion consumer products, in addition to clothing. It is one of the most important in the world, with a relevant impact on the economy, at regional and national levels, such is the case of Portugal. In this context of high acceleration, the paper focus on two important ideas: i) companies are ever more facing the need to adapt to the ever-increasing time flexibility, mobility and fragmentation that characterize young graduates’ expectations and ways of live; ii) these cultural changes on values of time are demanding new modes of organizing and administering time and human resources in the organizations [2].
- 11 July 2022
- Published by Trans Tech Publications, Ltd. in Advances in Science and Technology
- Vol. 113, 169-174
Time as Challenge in Textile Industry: Issues of Education, Culture and Science
The textile industry has developed throughout the 21st century highly sustained by the accuracy of time control, reduction of waiting times and intensification of working time regimes. It is one of the industries where the times and methods were best tested and where mass production model was intensely developed. In parallel, the textile industry followed through a colossal transformation at the level of lifestyles, with the increase diversification of fashion consumption [1]. Currently, the textile industry is associated with various fashion consumer products, in addition to clothing. It is one of the most important in the world, with a relevant impact on the economy, at regional and national levels, such is the case of Portugal. In this context of high acceleration, the paper focus on two important ideas: i) companies are ever more facing the need to adapt to the ever-increasing time flexibility, mobility and fragmentation that characterize young graduates’ expectations and ways of live; ii) these cultural changes on values of time are demanding new modes of organizing and administering time and human resources in the organizations [2].
- Open Access
- 13 March 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Message from the Local Chair of Guimarães, Portugal
- 13 March 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Open AccessMessage from the Local Chair of Guimarães, Portugal
- 13 March 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 8, 1-4
COVID main challenges in a Portuguese HEI
The main challenges in the health crisis, as experienced in a Portuguese public university observed during this period, are presented in this paper. The pandemic forced the suspension of university calendars and work routines in higher education institutions, requiring several changes, both in the ways of interacting with students and professors, and in the structure of interaction with the surrounding community. Institutions of higher education are microcosms that reflect well the great trends of social change. The text is supported by the analysis of documents, as well as the content analysis of meetings and interviews conducted with students from a Portuguese university. The results show that, at the same time as the pandemic changes introduced that will be momentary and that require successive adjustments, they also led to changes that will be more definitive and that could represent, in fact, the transformation of the patterns of organization of academic work.
- 13 March 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 8, 1-4
COVID main challenges in a Portuguese HEI
The main challenges in the health crisis, as experienced in a Portuguese public university observed during this period, are presented in this paper. The pandemic forced the suspension of university calendars and work routines in higher education institutions, requiring several changes, both in the ways of interacting with students and professors, and in the structure of interaction with the surrounding community. Institutions of higher education are microcosms that reflect well the great trends of social change. The text is supported by the analysis of documents, as well as the content analysis of meetings and interviews conducted with students from a Portuguese university. The results show that, at the same time as the pandemic changes introduced that will be momentary and that require successive adjustments, they also led to changes that will be more definitive and that could represent, in fact, the transformation of the patterns of organization of academic work.