Analysis of Integrating Deep and Hand-Crafted Features for Thermal Obstacle Detection
碩士 === 國立高雄科技大學 === 電腦與通訊工程系 === 107 === Recently, the use of Convolutional Neural Network (CNN) automatically extracts effective features from raw data. CNN is different from the hand-crafted features which is designed by human being for solving the specific image processing problems. In order to i...
Main Authors: | CHI, TAI-TING, 紀岱廷 |
---|---|
Other Authors: | HUANG, SHIH-SHINH |
Format: | Others |
Language: | zh-TW |
Published: |
2019
|
Online Access: | http://ndltd.ncl.edu.tw/handle/74br35 |
Similar Items
-
Media Forensics Considerations on DeepFake Detection with Hand-Crafted Features
by: Dennis Siegel, et al.
Published: (2021-07-01) -
Feature detection and description for image matching: from hand-crafted design to deep learning
by: Lin Chen, et al.
Published: (2021-01-01) -
Detecting Pedestrian and Vehicle in 3D Point Cloud based on Hand-crafted and Deep-learned Features
by: Tzu-Chieh Lin, et al.
Published: (2018) -
Quality Assessment of Retargeted Images Using Hand-Crafted and Deep-Learned Features
by: Zhenqi Fu, et al.
Published: (2018-01-01) -
An Interpretable Hand-Crafted Feature-Based Model for Atrial Fibrillation Detection
by: Rahimeh Rouhi, et al.
Published: (2021-05-01)