TY - JOUR AU - Saleem, Mohammad AU - Szücs, Cintia Lia AU - Kővári, Bence András TI - Systematic Evaluation of Pre-Processing Approaches in Online Signature Verification JF - INTELLIGENT DECISION TECHNOLOGIES J2 - INTELL DECIS TECHNOL VL - 17 PY - 2023 IS - 3 SP - 655 EP - 672 PG - 18 SN - 1872-4981 DO - 10.3233/IDT-220247 UR - https://m2.mtmt.hu/api/publication/34034421 ID - 34034421 N1 - Export Date: 29 August 2023 Correspondence Address: Saleem, M.; Budapest University of Technology and EconomicsHungary; email: msaleem@aut.bme.hu LA - English DB - MTMT ER - TY - CONF AU - Szücs, Cintia Lia AU - Kővári, Bence András AU - Charaf, Hassan TI - Származtatott függvénytulajdonságok alkalmazásának szerepe az online aláírás-hitelesítésben T2 - Képfeldolgozók és Alakfelismerők társaságának 14. konferenciája PB - NJSZT Képfeldolgozók és Alakfelismerők Társasága PY - 2023 SP - Paper ID 45 UR - https://m2.mtmt.hu/api/publication/34025204 ID - 34025204 LA - Hungarian DB - MTMT ER - TY - CHAP AU - Szücs, Cintia Lia AU - Kővári, Bence András TI - The Usability of Derived Function Features in Online Signature Verification T2 - 2022 9TH INTERNATIONAL CONFERENCE ON SOFT COMPUTING & MACHINE INTELLIGENCE, ISCMI PB - IEEE CY - New York, New York SN - 9798350320886 T3 - International Conference on Soft Computing & Machine Intelligence ISCMI, ISSN 2640-0154 PY - 2022 SP - 192 EP - 197 PG - 6 DO - 10.1109/ISCMI56532.2022.10068475 UR - https://m2.mtmt.hu/api/publication/34021323 ID - 34021323 N1 - WoS:hiba:000985064000036 2023-12-31 19:44 befoglaló egyiknél nincsenek szerzők LA - English DB - MTMT ER - TY - CHAP AU - Szücs, Cintia Lia ED - Dunaev, Dmitriy ED - Vajk, István TI - The effectiveness of derived local features in online signature verification T2 - Proceedings of the Automation and Applied Computer Science Workshop 2022 (AACS'22) PB - Budapesti Műszaki Egyetem, Automatizálási és Alkalmazott Informatikai Tanszék CY - Budapest SN - 9789634218753 PY - 2022 SP - 44 EP - 55 PG - 12 UR - https://m2.mtmt.hu/api/publication/33606537 ID - 33606537 LA - English DB - MTMT ER - TY - JOUR AU - Heszler, András AU - Szücs, Cintia Lia AU - Kővári, Bence András TI - The Use of Confidence Indicating Prediction Score in Online Signature Verification JF - JOURNAL OF ADVANCES IN INFORMATION TECHNOLOGY J2 - J ADV INFORM TECH VL - 13 PY - 2022 IS - 3 SP - 290 EP - 294 PG - 5 SN - 1798-2340 DO - 10.12720/jait.13.3.290-294 UR - https://m2.mtmt.hu/api/publication/32842136 ID - 32842136 N1 - Export Date: 22 June 2022 AB - Signature verification is an actively researched area whose goal is to decide whether unknown signatures are genuine or forged. Online signature verification applies signatures captured with an electronic device (digital tablet or pen). Online signatures contain not only spatial information but dynamics as well. There are two types of possible errors, the false prediction as genuine and the false prediction as a forgery. This paper proposes a prediction score as the classification output, which indicates the confidence of the system decision. This approach allows a trade-off between the different error types to create specialized verifiers and construct combined classifiers. This paper presents two types of combined classifiers, pre-filtering classifiers and majority voting classifiers. The proposed approaches are evaluated using the MCYT-100 dataset. LA - English DB - MTMT ER - TY - JOUR AU - Ruben, Tolosana AU - Ruben, Vera-Rodriguez AU - Carlos, Gonzalez-Garcia AU - Julian, Fierrez AU - Aythami, Morales AU - Javier, Ortega-Garcia AU - Juan, Carlos Ruiz-Garcia AU - Sergio, Romero-Tapiador AU - Santiago, Rengifo AU - Miguel, Caruana AU - Jiajia, Jiang AU - Songxuan, Lai AU - Lianwen, Jin AU - Yecheng, Zhu AU - Javier, Galbally AU - Moises, Diaz AU - Miguel, Angel Ferrer AU - Marta, Gomez-Barrero AU - Ilya, Hodashinsky AU - Konstantin, Sarin AU - Artem, Slezkin AU - Marina, Bardamova AU - Mikhail, Svetlakov AU - Saleem, Mohammad AU - Szücs, Cintia Lia AU - Kővári, Bence András AU - Falk, Pulsmeyer AU - Mohamad, Wehbi AU - Dario, Zanca AU - Sumaiya, Ahmad AU - Sarthak, Mishra AU - Suraiya, Jabin TI - SVC-onGoing: Signature Verification Competition JF - PATTERN RECOGNITION J2 - PATTERN RECOGN VL - 127 PY - 2022 PG - 14 SN - 0031-3203 DO - 10.1016/j.patcog.2022.108609 UR - https://m2.mtmt.hu/api/publication/32526085 ID - 32526085 AB - This article presents SVC-onGoing1, an on-going competition for on-line signature verification where re-searchers can easily benchmark their systems against the state of the art in an open common platform using large-scale public databases, such as DeepSignDB(2) and SVC2021_EvalDB(3), and standard experimen-tal protocols. SVC-onGoing is based on the ICDAR 2021 Competition on On-Line Signature Verification (SVC 2021), which has been extended to allow participants anytime. The goal of SVC-onGoing is to eval-uate the limits of on-line signature verification systems on popular scenarios (office/mobile) and writing inputs (stylus/finger) through large-scale public databases. Three different tasks are considered in the competition, simulating realistic scenarios as both random and skilled forgeries are simultaneously con-sidered on each task. The results obtained in SVC-onGoing prove the high potential of deep learning methods in comparison with traditional methods. In particular, the best signature verification system has obtained Equal Error Rate (EER) values of 3.33% (Task 1), 7.41% (Task 2), and 6.04% (Task 3). Future stud-ies in the field should be oriented to improve the performance of signature verification systems on the challenging mobile scenarios of SVC-onGoing in which several mobile devices and the finger are used during the signature acquisition. (C) 2022 The Author(s). Published by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license ( http://creativecommons.org/licenses/by-nc-nd/4.0/ ) LA - English DB - MTMT ER - TY - CHAP AU - Ruben, Tolosana AU - Ruben, Vera-Rodriguez AU - Carlos, Gonzalez-Garcia AU - Julian, Fierrez AU - Santiago, Rengifo AU - Aythami, Morales AU - Javier, Ortega-Garcia AU - Juan, Carlos Ruiz-Garcia AU - Sergio, Romero-Tapiador AU - Jiajia, Jiang AU - Songxuan, Lai AU - Lianwen, Jin AU - Yecheng, Zhu AU - Javier, Galbally AU - Moises, Diaz AU - Miguel, Angel Ferrer AU - Marta, Gomez-Barrero AU - Ilya, Hodashinsky AU - Konstantin, Sarin AU - Artem, Slezkin AU - Marina, Bardamova AU - Mikhail, Svetlakov AU - Saleem, Mohammad AU - Szücs, Cintia Lia AU - Kővári, Bence András AU - Falk, Pulsmeyer AU - Mohamad, Wehbi AU - Dario, Zanca AU - Sumaiya, Ahmad AU - Sarthak, Mishra AU - Suraiya, Jabin ED - Lladós, Josep ED - Lopresti, Daniel ED - Uchida, Seiichi TI - ICDAR 2021 Competition on On-Line Signature Verification T2 - Document Analysis and Recognition – ICDAR 2021 PB - Springer Netherlands CY - Cham SN - 9783030863371 T3 - Lecture Notes in Computer Science, ISSN 0302-9743 ; 12824. PY - 2021 SP - 723 EP - 737 PG - 15 DO - 10.1007/978-3-030-86337-1_48 UR - https://m2.mtmt.hu/api/publication/32525104 ID - 32525104 AB - This paper describes the experimental framework and results of the ICDAR 2021 Competition on On-Line Signature Verification (SVC 2021). The goal of SVC 2021 is to evaluate the limits of on-line signature verification systems on popular scenarios (office/mobile) and writing inputs (stylus/finger) through large-scale public databases. Three different tasks are considered in the competition, simulating realistic scenarios as both random and skilled forgeries are simultaneously considered on each task. The results obtained in SVC 2021 prove the high potential of deep learning methods. In particular, the best on-line signature verification system of SVC 2021 obtained Equal Error Rate (EER) values of 3.33% (Task 1), 7.41% (Task 2), and 6.04% (Task 3). SVC 2021 will be established as an on-going competition (https://sites.google.com/view/SVC2021 ), where researchers can easily benchmark their systems against the state of the art in an open common platform using large-scale public databases such as DeepSignDB (https://github.com/BiDAlab/DeepSignDB ) and SVC2021_EvalDB (https://github.com/BiDAlab/SVC2021_EvalDB ), and standard experimental protocols. © 2021, Springer Nature Switzerland AG. LA - English DB - MTMT ER - TY - CHAP AU - Szücs, Cintia Lia AU - Saleem, Mohammad AU - Kővári, Bence András AU - Dócs, Zoltán TI - Előfeldolgozási algoritmusok szisztematikus vizsgálata az online aláírás-hitelesítésben T2 - Képfeldolgozók és Alakfelismerők társaságának 13. konferenciája PB - Képfeldolgozók és Alakfelismerők Társasága C1 - Budapest PY - 2021 SP - 1 UR - https://m2.mtmt.hu/api/publication/32165631 ID - 32165631 LA - Hungarian DB - MTMT ER - TY - CHAP AU - Heszler, András AU - Szücs, Cintia Lia ED - Dunaev, Dmitriy ED - Vajk, István TI - Online signature verification using non-binary classification T2 - Proceedings of the Automation and Applied Computer Science Workshop 2021 PB - Budapesti Műszaki és Gazdaságtudományi Egyetem CY - Budapest SN - 9789634218524 PY - 2021 SP - 204 EP - 212 PG - 9 UR - https://m2.mtmt.hu/api/publication/32118101 ID - 32118101 AB - Online signature verification is an actively researched area that uses signatures captured by a digitizing pen or tablet and stored as time series with various features, such as pressures. The goal of a signature verification system is to classify the signatures into forgeries and genuine signatures with low error rates for both cases. This paper proposes a confidence score as the classification output, which allows a trade-off between the different types of errors to optimize the classification, create specialized signature verifiers, and construct combined classifiers. Two types of combined classifiers will be presented, pre-filtering classifiers and majority voting classifiers. The proposed signature verification approaches are evaluated using the publicly available MCYT-100 dataset. LA - English DB - MTMT ER - TY - CHAP AU - Szücs, Cintia Lia ED - Dunaev, Dmitriy ED - Vajk, István TI - Combination of DTW and global features in on-line signature verification using writer-independent threshold T2 - Proceedings of the Automation and Applied Computer Science Workshop 2021 PB - Budapesti Műszaki és Gazdaságtudományi Egyetem CY - Budapest SN - 9789634218524 PY - 2021 SP - 262 EP - 271 PG - 10 UR - https://m2.mtmt.hu/api/publication/32118073 ID - 32118073 AB - Handwritten signatures are widely accepted and commonly used in everyday life. Therefore, it is important to be able to decide whether a signature is genuine or a forgery. Automated signature verification enables us to execute this decisionmaking process without human intervention. On-line signature verification uses not only the static image of the signature but also dynamic information about the signing process. This is possible because on-line signatures are captured with electronic devices such as pressure-sensitive pens or digital tablets, which can record additional features besides the coordinates. The dynamic time warping (DTW) algorithm is widely used in on-line signature verification. This work defines an on-line signature verification system that combines DTW and the use of global features. The presented approach deals with a signer-independent threshold. LA - English DB - MTMT ER -