RUS  ENG
Full version
JOURNALS // Doklady Rossijskoj Akademii Nauk. Mathematika, Informatika, Processy Upravlenia // Archive

Dokl. RAN. Math. Inf. Proc. Upr., 2023 Volume 514, Number 2, Pages 297–307 (Mi danma474)

SPECIAL ISSUE: ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING TECHNOLOGIES

Text reuse detection in handwritten documents

A. V. Grabovoyab, M. S. Kaprielovaabc, A. S. Kildyakova, I. O. Potyashina, T. B. Seyila, E. L. Finogeeva, Yu. V. Chekhovichac

a Antiplagiat Company, Moscow, Russian Federation
b Moscow Institute of Physics and Technology, Moscow, Russian Federation
c Federal Research Center "Computer Science and Control" of Russian Academy of Sciences, Moscow

Abstract: Plagiarism detection in scholar assignments becomes more and more relevant nowadays. Rapidly growing popularity of online education, active expansion of online educational platforms for secondary and high school education create demand for development of an automatic reuse detection system for handwritten assignments. The existing approaches to this problem are not usable for searching for potential sources of reuse on large collections, which significantly limits their applicability. Moreover, real-life data is likely to be low-quality photographs taken with mobile devices. We propose an approach that allows to detect text reuse in handwritten documents. Each document is a picture and the search is performed on a large collection of potential sources. The proposed method consists of three stages: handwritten text recognition, candidate search and precise source retrieval. We represent experimental results for the quality and latency estimation of our system. The recall reaches 83.3% in case of better quality pictures and 77.4% in case of pictures of lower quality. The average search time is 3.2 seconds per document on CPU. The results show, that the created system is scalable and can be used in production, where fast reuse detection for hundreds of thousands of scholar assignments on large collection of potential reuse sources is needed. All the experiments were held on HWR200 public dataset.

Keywords: optical character recognition, handwriting, text reuse detection, computer vision, handwritten text recognition, plagiarism detection.

UDC: 004.(89+93)

Presented: A. L. Semenov
Received: 02.09.2023
Revised: 15.09.2023
Accepted: 18.10.2023

DOI: 10.31857/S2686954323601720


 English version:
Doklady Mathematics, 2023, 108:suppl. 2, S424–S433

Bibliographic databases:


© Steklov Math. Inst. of RAS, 2024