DC Field | Value | Language |
---|---|---|
dc.contributor.author | 이강산 | ko |
dc.contributor.author | 나주원 | ko |
dc.contributor.author | 손종덕 | ko |
dc.contributor.author | 손석만 | ko |
dc.contributor.author | 이승철 | ko |
dc.date.accessioned | 2023-09-13T08:00:20Z | - |
dc.date.available | 2023-09-13T08:00:20Z | - |
dc.date.created | 2023-09-13 | - |
dc.date.created | 2023-09-13 | - |
dc.date.issued | 2020-04 | - |
dc.identifier.citation | 한국소음진동공학회논문집, v.30, no.2, pp.136 - 142 | - |
dc.identifier.issn | 1598-2785 | - |
dc.identifier.uri | http://hdl.handle.net/10203/312590 | - |
dc.description.abstract | Tabulated data has been widely used to facilitate systematic and intuitive management. In particular, tabular images that contain a few simple symbols are useful for maintaining mechanical systems. Several companies have accumulated tabular images as their property. Although these images are valuable as they can be used to solve difficult problems using data-based methods, such as deep learning, they still remain unavailable because it is expensive to digitize them. For these reasons, we propose a model comprised of a convolutional neural network (CNN) and fully convolutional network (FCN) to digitize tabular images. We used some ResNet components as they are well-suited to the characteristics of tabular image data. A training set for each model was constructed by writing symbols in blank tables and then augmenting them. As a result, the trained CNN and FCN models exhibited 99.2% and 97.7% accuracy in 4.75s and 0.132s of inference time, respectively. | - |
dc.language | Korean | - |
dc.publisher | 한국소음진동공학회 | - |
dc.title | 정비 자료 디지털 변환을 위한 영상 인식 알고리듬: CNN and FCN | - |
dc.title.alternative | Image Recognition Algorithm for Maintenance Data Digitization: CNN and FCN | - |
dc.type | Article | - |
dc.type.rims | ART | - |
dc.citation.volume | 30 | - |
dc.citation.issue | 2 | - |
dc.citation.beginningpage | 136 | - |
dc.citation.endingpage | 142 | - |
dc.citation.publicationname | 한국소음진동공학회논문집 | - |
dc.identifier.kciid | ART002578483 | - |
dc.contributor.localauthor | 이승철 | - |
dc.contributor.nonIdAuthor | 이강산 | - |
dc.contributor.nonIdAuthor | 나주원 | - |
dc.contributor.nonIdAuthor | 손종덕 | - |
dc.contributor.nonIdAuthor | 손석만 | - |
dc.description.isOpenAccess | N | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.