|
This article is cited in 3 scientific papers (total in 3 papers)
INTERNATIONAL CONFERENCE ON MACHINE VISION
Tiny CNN for feature point description for document analysis: approach and dataset
A. Sheshkusabc, A. Chirvonayacd, V. Arlazarovbc a Moscow Institute of Physics and Technology (State University), Dolgoprudny, Moscow region
b Institute for Systems Analysis of Russian Academy of Sciences
c Smart Engines Service LLC, Moscow
d National University of Science and Technology «MISIS», Moscow
Abstract:
In this paper, we study the problem of feature points description in the context of document analysis and template matching. Our study shows that specific training data is required for the task especially if we are to train a lightweight neural network that will be usable on devices with limited computational resources. In this paper, we construct and provide a dataset of photo and synthetically generated images and a method of training patches generation from it. We prove the effectiveness of this data by training a lightweight neural network and show how it performs in both general and documents patches matching. The training was done on the provided dataset in comparison with HPatches training dataset and for the testing, we solve HPatches testing framework tasks and template matching task on two publicly available datasets with various documents pictured on complex backgrounds: MIDV-500 and MIDV-2019.
Keywords:
feature points description, metrics learning, training dataset
Received: 23.07.2021 Accepted: 22.10.2021
Citation:
A. Sheshkus, A. Chirvonaya, V. Arlazarov, “Tiny CNN for feature point description for document analysis: approach and dataset”, Computer Optics, 46:3 (2022), 429–435
Linking options:
https://www.mathnet.ru/eng/co1032 https://www.mathnet.ru/eng/co/v46/i3/p429
|
Statistics & downloads: |
Abstract page: | 10 | Full-text PDF : | 2 |
|