Abstract:
The classical Otsu method is a common tool in document image binarization. Often, two classes, text and background, are imbalanced, which means that the assumption of the classical Otsu method is not met. In this work, we considered the imbalanced pixel classes of background and text: weights of two classes are different, but variances are the same. We experimentally demonstrated that the employment of a criterion that takes into account the imbalance of the classes' weights, allows attaining higher binarization accuracy. We described the generalization of the criteria for a two-parametric model, for which an algorithm for the optimal linear separation search via fast linear clustering was proposed. We also demonstrated that the two-parametric model with the proposed separation allows increasing the image binarization accuracy for the documents with a complex background or spots.
This publication is cited in the following 15 articles:
Darya Nikolaevna Shibaeva, Roman Pavlovich Voronin, Alena Arkadievna Kompanchenko, Denis Olegovich Volkov, Danil Alekseevich Asanovich, Victor Vladimirovich Bulatov, “Hardware and Software Solutions for the Generation of a Database of HSV-Color Characteristics for the Main Ores and Rocks of the Khibiny Massif”, Minerals, 14:2 (2024), 186
Alexander Egorov, Nataly Krupenina, Lyubov Tyndykar, PROCEEDINGS OF THE IV INTERNATIONAL CONFERENCE ON MODERNIZATION, INNOVATIONS, PROGRESS: Advanced Technologies in Material Science, Mechanical and Automation Engineering: MIP: Engineering-IV-2022, 3021, PROCEEDINGS OF THE IV INTERNATIONAL CONFERENCE ON MODERNIZATION, INNOVATIONS, PROGRESS: Advanced Technologies in Material Science, Mechanical and Automation Engineering: MIP: Engineering-IV-2022, 2024, 040020
jun yan, ji liang yi, Chun-Ping Liu, Liang Xiao, Fifteenth International Conference on Graphics and Image Processing (ICGIP 2023), 2024, 46
Marwah Al-Ogaidi, Ali A. Al-Temeemy, “Biospeckle techniques for evaluating the radial growth rate of a fungal colony”, Appl. Opt., 63:33 (2024), 8483
Artemii Mametev, Alexander Pavin, 2024 International Conference on Ocean Studies (ICOS), 2024, 053
Karol Struniawski, Ryszard Kozera, Paweł Trzciński, Agnieszka Marasek-Ciołakowska, Lidia Sas-Paszt, “Extreme learning machine for identifying soil-dwelling microorganisms cultivated on agar media”, Sci Rep, 14:1 (2024)
David Asatryan, Mariam Haroutunian, Grigor Sazhumyan, Alexander Kupriyanov, Rustam Paringer, Dmitriy Kirsh, 2023 IX International Conference on Information Technology and Nanotechnology (ITNT), 2023, 1
P. V. Bezmaternykh, D. P. Nikolaev, V. L. Arlazarov, “High-Performance Digital Image Processing”, Pattern Recognit. Image Anal., 33:4 (2023), 743
Aleksandr M. Sinitca, Airat R. Kayumov, Pavel V. Zelenikhin, Andrey G. Porfiriev, Dmitrii I. Kaplun, Mikhail I. Bogachev, “Segmentation of patchy areas in biomedical images based on local edge density estimation”, Biomedical Signal Processing and Control, 79 (2023), 104189
Yu Li, Tianlong Shao, Hao Wang, Xiaobo Xie, Di Fang, Dalin Zhang, Fifth International Conference on Mechatronics and Computer Technology Engineering (MCTE 2022), 2022, 236
Xiao Li, Sagheer Abbas, “Design and Realization of Computer Network Virtual Experiment Economic Teaching Platform Based on Mathematical Image and Signal Processing”, Mathematical Problems in Engineering, 2022 (2022), 1
Lukas Kopecky, Michal Dobrovolny, Antonin Fuchs, Ali Selamat, Ondrej Krejcar, Lecture Notes in Computer Science, 13501, Computational Collective Intelligence, 2022, 82
Yuchun He, Dezhi Liu, Yong Zeng, Qian Lu, Suheng Yao, Yuxin Yuan, “Research on the Recognition Method of the Axle End Mark of a Train Wheelset Based on Machine Vision”, Int J Comput Intell Syst, 15:1 (2022)
Citation in format AMSBIB
Contact us: