- 期刊
Multi-pose Face Recognition Based on Convolutional Neural Network
摘要
The difficulty of multi-pose face recognition is the changes of posture. Compared with the traditional face recognition, multi-pose face recognition increases the difficulty of feature extraction due to the change of posture. The feature of face recognition requires distinguishing and recognizability. In this paper, the convolutional neural network is used to first train the face pose, and then perform a single pose face recognition on the classified image. Compared with the traditional face recognition method, it can be seen from the experimental results that the classification of face poses can increase the accuracy of multi-pose face recognition.
延伸閱讀
- 王緒傑（2022）。Masked face recognition based on two-stage convolutional neural network〔碩士論文，國立宜蘭大學〕。華藝線上圖書館。https://doi.org/10.6820/niu202200215
- 陳鵬安（2017）。Face Recognition based on Sharpening Convolutional NeuralNetwork〔碩士論文，國立暨南國際大學〕。華藝線上圖書館。https://www.airitilibrary.com/Article/Detail?DocID=U0020-2308201713015200
- 朱哲寬（2017）。Face Detection Based on Deep Convolutional Neural Network〔碩士論文，國立暨南國際大學〕。華藝線上圖書館。https://www.airitilibrary.com/Article/Detail?DocID=U0020-2308201706271600
- 陳郁萍（2022）。Research on Face Recognition Using Convolutional Neural Networks〔碩士論文，國立宜蘭大學〕。華藝線上圖書館。https://doi.org/10.6820/niu202200093
- Gong, T., Liu, X., & Yuan, H. (2022). Face Recognition Method based on Feature Fusion and Convolutional Neural Network. International Core Journal of Engineering, 8(5), 526-537. https://doi.org/10.6919/ICJE.202205_8(5).0068