Searching ROI for Object Detection based on CNN

Chia Lin Wu, Chih Yang Lin, Phanuvich Hirunsirisombut, Hui Fuang Ng, Timothy K. Shih

研究成果: 書貢獻/報告類型會議論文篇章同行評審

1 引文 斯高帕斯(Scopus)

摘要

Several studies have explored the structural design of CNN to improve the network's performance since a well-designed feature extractor can benefit convolution-based tasks. Although CNNs are able to learn important patterns on raw images, images may contain unpredictable noise that can negatively influence the convolutional stage. Feature extraction cannot always accurately capture the desired features based solely on the input image, but including extra information could improve the result. This paper proposes a fusion input design to generate an additional feature that a CNN can use to provide extra ROI information. Whether a model can utilize the additional information is a determining factor that affects the performance improvement. The proposed method is tested on two public datasets with different structural designs. Overall, the results indicate that additional ROI information can deliver benefits to specific tasks.

原文???core.languages.en_GB???
主出版物標題Proceedings - 2019 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2019
發行者Institute of Electrical and Electronics Engineers Inc.
ISBN(電子)9781728130385
DOIs
出版狀態已出版 - 12月 2019
事件2019 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2019 - Taipei, Taiwan
持續時間: 3 12月 20196 12月 2019

出版系列

名字Proceedings - 2019 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2019

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???2019 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2019
國家/地區Taiwan
城市Taipei
期間3/12/196/12/19

指紋

深入研究「Searching ROI for Object Detection based on CNN」主題。共同形成了獨特的指紋。

引用此