| Presentation | 2021-12-16 Neural Network-based Local Feature Descriptors for Matching Excavated Mokkan Fragments of Various Sizes Trung Tan Ngo, Hung Tuan Nguyen, Masaki Nakagawa, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | This paper presents a method to predict whether two excavated Mokkan fragments of various sizes are from the same tablet or not using an end-to-end attention-based neural network, namely A-VLAD. The method does not require any preprocessing stages such as binarization and segmentation. It has three main parts: a local feature extractor using Convolutional Neural Network from an input image, an attention filter for key-points selection, and a generalized deep neural network-based VLAD model to aggregate the extracted key-points and form a representative vector. The whole network is trained end-to-end using the stochastic gradient descent algorithm to optimize both cross-entropy and triplet losses. In the experiments, we evaluate the proposed model on 13,205 fragments broken from 556 complete wooden tablets excavated from the Heijo-Kyo Palace ruins in the Japanese Nara period. The proposed A-VLAD model achieved mean average precision of 75.5% and top-1 accuracy of 87.9% better than the state-of-the-art methods on this Mokkan dataset. Thus, it is expected to be used to support archaeologists to assemble Mokkan fragments to recover an original Mokkan tablet. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | MokkanHistorical documentsImage retrievalConvolution neural network |
| Paper # | PRMU2021-33 |
| Date of Issue | 2021-12-09 (PRMU) |
| Conference Information | |
| Committee | PRMU |
|---|---|
| Conference Date | 2021/12/16(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Online |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Seiichi Uchida(Kyushu Univ.) |
| Vice Chair | Masakazu Iwamura(Osaka Pref. Univ.) / Mitsuru Anpai(Denso IT Lab.) |
| Secretary | Masakazu Iwamura(NTT) / Mitsuru Anpai(Tottori Univ.) |
| Assistant | Kouta Yamaguchi(CyberAgent) / Yusuke Matsui(Univ. of Tokyo) |
| Paper Information | |
| Registration To | Technical Committee on Pattern Recognition and Media Understanding |
|---|---|
| Language | ENG |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Neural Network-based Local Feature Descriptors for Matching Excavated Mokkan Fragments of Various Sizes |
| Sub Title (in English) | |
| Keyword(1) | MokkanHistorical documentsImage retrievalConvolution neural network |
| 1st Author's Name | Trung Tan Ngo |
| 1st Author's Affiliation | Tokyo University of Agriculture and Technology(TUAT) |
| 2nd Author's Name | Hung Tuan Nguyen |
| 2nd Author's Affiliation | Tokyo University of Agriculture and Technology(TUAT) |
| 3rd Author's Name | Masaki Nakagawa |
| 3rd Author's Affiliation | Tokyo University of Agriculture and Technology(TUAT) |
| Date | 2021-12-16 |
| Paper # | PRMU2021-33 |
| Volume (vol) | vol.121 |
| Number (no) | PRMU-304 |
| Page | pp.pp.51-56(PRMU), |
| #Pages | 6 |
| Date of Issue | 2021-12-09 (PRMU) |