Gagiu Daniel-Gheorghe
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Gagiu Daniel-Gheorghe has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Dorin Șendrescu
Department of Automatic Control and Electronics, University of Craiova, 200585 Craiova, Romania
2 shared publications - Besnea Petcu Florina Luminita
Mechatronics and Robotics Department, University of Craiova, 200440 Craiova, Romania
1 shared publication - Dumitrascu Razvan-George1 shared publication
- Ștefan Irinel Cismaru
Department of Mechatronics and Robotics, University of Craiova, RO-200440 Craiova, Romania
1 shared publication
Latest Publications
- Open Access
- 20 May 2025
- Published by University of Craiova in Annals of the University of Craiova Mathematics and Computer Science Series
- Vol. 52 (1) , 272-287
TV production application based on Artificial Intelligence specific algorithms
The paper proposes an application that integrates an artificial intelligence model and is intended for the television production environment. This uses a pre-trained model, capable of quickly and accurately identifying relevant video files in a vast archive. This process involves the automatic analysis of metadata and audio-visual content to detect the information sought in each file, resulting in a list of files that match the selection criteria made with the help of implemented YOLO-type algorithms. The application is powered by an artificial intelligence model that can be customized and continuously created through additional training, using input data provided by users. Thus, an efficient and adaptable solution is created, which optimizes archive management and improves the production flow. The proposed application aims to eliminate the time spent identifying audio-video material necessary for editing.
- 20 May 2025
- Published by University of Craiova in Annals of the University of Craiova Mathematics and Computer Science Series
- Vol. 52 (1) , 272-287
Open AccessTV production application based on Artificial Intelligence specific algorithms
The paper proposes an application that integrates an artificial intelligence model and is intended for the television production environment. This uses a pre-trained model, capable of quickly and accurately identifying relevant video files in a vast archive. This process involves the automatic analysis of metadata and audio-visual content to detect the information sought in each file, resulting in a list of files that match the selection criteria made with the help of implemented YOLO-type algorithms. The application is powered by an artificial intelligence model that can be customized and continuously created through additional training, using input data provided by users. Thus, an efficient and adaptable solution is created, which optimizes archive management and improves the production flow. The proposed application aims to eliminate the time spent identifying audio-video material necessary for editing.
- Open Access
- 18 February 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (4) , 2154
Detection of Personality Traits Using Handwriting and Deep Learning
A series of studies and research have shown the existence of a link between handwriting and a person’s personality traits. There are numerous fields that require a psychological assessment of individuals, where there is a need to determine personality traits in a faster and more efficient manner than that based on classic questionnaires or graphological analysis. The development of image processing and recognition algorithms based on machine learning and deep neural networks has led to a series of applications in the field of graphology. In the present study, a system for automatically extracting handwriting characteristics from written documents and correlating them with Myers–Briggs type indicator is implemented. The system has an architecture composed of three levels, the main level being formed by four convolutional neural networks. To train the networks, a database with different types of handwriting was created. The experimental results show an accuracy ranging between 89% and 96% for handwritten features’ recognition and results ranging between 83% and 91% in determining Myers–Briggs indicators.
- 18 February 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (4) , 2154
Open AccessDetection of Personality Traits Using Handwriting and Deep Learning
A series of studies and research have shown the existence of a link between handwriting and a person’s personality traits. There are numerous fields that require a psychological assessment of individuals, where there is a need to determine personality traits in a faster and more efficient manner than that based on classic questionnaires or graphological analysis. The development of image processing and recognition algorithms based on machine learning and deep neural networks has led to a series of applications in the field of graphology. In the present study, a system for automatically extracting handwriting characteristics from written documents and correlating them with Myers–Briggs type indicator is implemented. The system has an architecture composed of three levels, the main level being formed by four convolutional neural networks. To train the networks, a database with different types of handwriting was created. The experimental results show an accuracy ranging between 89% and 96% for handwritten features’ recognition and results ranging between 83% and 91% in determining Myers–Briggs indicators.