WEKO3
アイテム
Image Classification by Using Multi-Layer Neural Network
http://hdl.handle.net/10458/6437
http://hdl.handle.net/10458/6437e459ecfa-1d7e-4e71-8413-b3d708ce39fc
| 名前 / ファイル | ライセンス | アクション |
|---|---|---|
本文 (923.7 kB)
|
|
| アイテムタイプ | 紀要論文 / Departmental Bulletin Paper(1) | |||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 公開日 | 2020-06-21 | |||||||||||||||||
| タイトル | ||||||||||||||||||
| タイトル | Image Classification by Using Multi-Layer Neural Network | |||||||||||||||||
| 言語 | ja | |||||||||||||||||
| 言語 | ||||||||||||||||||
| 言語 | jpn | |||||||||||||||||
| キーワード | ||||||||||||||||||
| 言語 | en | |||||||||||||||||
| 主題Scheme | Other | |||||||||||||||||
| 主題 | Multi-Layer Neural Network, Deep Learning, Deep Convolutional Neural Network, Shape Image Classification, Color Image Classification, Size Image Classification | |||||||||||||||||
| 資源タイプ | ||||||||||||||||||
| 資源タイプ識別子 | http://purl.org/coar/resource_type/c_6501 | |||||||||||||||||
| 資源タイプ | departmental bulletin paper | |||||||||||||||||
| 著者 |
Swe, Zar Maw
× Swe, Zar Maw× Ei, Phyo Min× 横田, 光広
WEKO
7103
× ティ ティ ズイン
WEKO
31575
|
|||||||||||||||||
| 抄録 | ||||||||||||||||||
| 内容記述タイプ | Abstract | |||||||||||||||||
| 内容記述 | We perform a scalable approach for automatically classifying shape, color and size of the images using a multilayer neural network (deep learning) in order to demonstrate the interesting application that aims for kindergarten. Our process makes use of the state-of-the-art methodology of extracting deep features using convolutional neural network. The main idea of our system is a deep convolutional neural network that trained to classify different shapes and colors of the grayscale images. To implement our approach, we used BabyAIImageandQuestion Dataset which consists of different shape, color, size and location sub datasets. Among these sub datasets, we mainly applied shape, color and size datasets to present our proposed method. We have achieved a good performance accuracy (average 95%) in classification of shape color and size with fast processing time. The objective of our approach is to develop the visual ability of children which includes visual acuity, tracking, color perception, depth perception, and object recognition by effectively applying the deep learning algorithm. We also hope that our proposed method will be effectively useful for real world application. | |||||||||||||||||
| 言語 | en | |||||||||||||||||
| bibliographic_information |
ja : 宮崎大学工学部紀要 en : Memoirs of Faculty of Engineering, University of Miyazaki 巻 47, p. 193-199, 発行日 2018-07 |
|||||||||||||||||
| 出版者 | ||||||||||||||||||
| 出版者 | 宮崎大学工学部 | |||||||||||||||||
| 言語 | ja | |||||||||||||||||
| 出版者 | ||||||||||||||||||
| 出版者 | Faculty of Engineering, University of Miyazaki | |||||||||||||||||
| 言語 | en | |||||||||||||||||
| ISSN | ||||||||||||||||||
| 収録物識別子タイプ | ISSN | |||||||||||||||||
| 収録物識別子 | 05404924 | |||||||||||||||||
| item_10002_source_id_11 | ||||||||||||||||||
| 収録物識別子タイプ | NCID | |||||||||||||||||
| 収録物識別子 | AA00732558 | |||||||||||||||||
| 出版タイプ | ||||||||||||||||||
| 出版タイプ | VoR | |||||||||||||||||
| 出版タイプResource | http://purl.org/coar/version/c_970fb48d4fbd8a85 | |||||||||||||||||
