부분적으로 가려진 물체 인식을 위한 어닐드 홉필드 네트워크Annealed Hopfield Neural Network for Recognizing Partially Occluded Objects
- Other Titles
- Annealed Hopfield Neural Network for Recognizing Partially Occluded Objects
- Authors
- 윤석훈
- Issue Date
- May-2021
- Publisher
- 한국전자거래학회
- Keywords
- Hopfield Network; Partially Occluded Objects; Annealing; Recognition; 홉필드 네트워크; 부분적으로 가려진 물체; 어닐링; 인식
- Citation
- 한국전자거래학회지, v.26, no.2, pp.83 - 94
- Journal Title
- 한국전자거래학회지
- Volume
- 26
- Number
- 2
- Start Page
- 83
- End Page
- 94
- URI
- http://scholarworks.bwise.kr/ssu/handle/2018.sw.ssu/41173
- DOI
- 10.7838/jsebs.2021.26.2.083
- ISSN
- 2288-3908
- Abstract
- The need for recognition of partially occluded objects is increasing in the area of computer vision applications. Occlusion causes significant problems in identifying and locating an object. In this paper, an annealed Hopfield network (AHN) is proposed for detecting threat objects in passengers’ check-in baggage. AHN is a deterministic approximation that is based on the hybrid Hopfield network (HHN) and annealing theory. AHN uses boundary features composed of boundary points and corner points which are extracted from input images of threat objects. The critical temperature also is examined to reduce the run time of AHN. Extensive computational experiments have been conducted to compare the performance of the AHNwith that of the HHN.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - College of Engineering > Department of Industrial & Information Systems Engineering > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/ssu/handle/2018.sw.ssu/41173)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.