Отрывок: Fig. 5. Neural network convergence plot and training statistics In fig. 6 we show some images from the used da- tasets. While HPatches is a dataset of the general image patches mostly containing outdoors images the MIDV- 500 and MIDV-2019 datasets contain document images. The second one introduces heavier projective distortions and is considered to be harder. Both datasets have various complex backgrounds and are challenging for the task. 3. Results In tab. 4, 5, and ...
Название : | Tiny CNN for feature point description for document analysis: approach and dataset |
Авторы/Редакторы : | Sheshkus, A. Chirvonaya, A. Arlazarov, V.L. |
Ключевые слова : | feature points description training dataset metrics learning |
Дата публикации : | Июн-2022 |
Издательство : | Самарский национальный исследовательский университет |
Библиографическое описание : | Sheshkus A, Chirvonaya A, Arlazarov VL. Tiny CNN for feature point description for document analysis: approach and dataset. Computer Optics 2022; 46(3): 429-435. DOI: 10.18287/2412-6179-CO-1016. |
Серия/номер : | 46;3 |
Аннотация : | 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. |
URI (Унифицированный идентификатор ресурса) : | https://dx.doi.org/10.18287/2412-6179-CO-1016 http://repo.ssau.ru/handle/Zhurnal-Komputernaya-optika/Tiny-CNN-for-feature-point-description-for-document-analysis-approach-and-dataset-103041 |
Другие идентификаторы : | Dspace\SGAU\20230413\103041 Dspace\SGAU\20230426\103041 Dspace\SGAU\20230503\103041 |
Располагается в коллекциях: | Журнал "Компьютерная оптика" |
Файлы этого ресурса:
Файл | Описание | Размер | Формат | |
---|---|---|---|---|
2412-6179_2022_46-3_429-435.pdf | Основная статья | 1.46 MB | Adobe PDF | Просмотреть/Открыть |
Показать полное описание ресурса
Просмотр статистики
Поделиться:
Все ресурсы в архиве электронных ресурсов защищены авторским правом, все права сохранены.