Session Index

S4. Optical Information Processing and Holography

Optical Information Processing and Holography III
Saturday, Dec. 3, 2022  11:00-12:00
Presider: Hsi-Fu Shih、Ju-Yi Lee
Room: 1F 羅家倫
11:00 - 11:30
Manuscript ID.  0895
Paper No.  2022-SAT-S0403-I001
Invited Speaker:
Chung-Hao Tien
Deep Learning for Unconventional Optics: Reconstruction, Inference and More
Chung-Hao Tien, National Yang Ming Chiao Tung University (Taiwan)

Instead of traditional image models, which accompany various prior conditions and feature engineering, in recent years, data-driven deep learning network models have gradually become attractive. Based on a lensless configuration with ordinary white light (completely noncoherent), a coded mask (or diffuser) as an example to modulate the light field, the CMOS sensor measures the intermediate image, we employed the convolutional neural network (CNN) architecture to reconstruct the readily uninterpretable signal. In addition to the reconstruction, we also conducted the face recognition as the vision task. Practical implications through such unconventional optics will be expected if pattern recognition, rather than relying mostly on human recognizable fidelity as it does in conventional imaging system, become more directly linked to the hidden or incomplete optical fields. More possibilities will be addressed during the conference presentation

  Preview abstract
11:30 - 11:45
Manuscript ID.  0705
Paper No.  2022-SAT-S0403-O001
Tzu-Yuan Huang Real-Time Fall Detection via Deep Learning with Attention Transfer on Embedded System
Tzu-Yuan Huang, Chih-Chieh Yang, Chieh-En Lee, Chung-Hao Tien, National Yang Ming Chiao Tung University (Taiwan)

Real-time fall detection via deep learning is usually a challenge on embedded system due to limited computing power. In this work, we apply attention transfer to reduce the computational complexity and optimize memory usage. The proposed method achieved 98.06% testing accuracy on a real-time multi-view fall detection system.

  Preview abstract
11:45 - 12:00
Manuscript ID.  0527
Paper No.  2022-SAT-S0403-O002
Tzu-Kai Wang Depth image completion using an iterative low-pass filter
Tzu-Kai Wang, National Central University (Taiwan), General Interface Solution (Taiwan); Yeh-Wei Yu, Tsung-Hsun Yang, Pin-Duan Huang, Guan-Yu Zhu, National Central University (Taiwan); Chi-Chung Lau, Industrial Technology Research Institute (Taiwan); Ching-Cherng Sun, National Central University (Taiwan)

We proposed a spatial-modulate method to recover missing data in depth images. Depth cameras often fail to get depth data due to shinny and absorbing surfaces. Additionally, depth image inpainting using deep learning methods have compromised abilities to noise. These advance techniques often fail to provide correct depth data due to the influence of noise. To address both issues, we iteratively applied several low-pass filters to recover the missing data. We evaluated our method using depth images which were manually added large noise and defected area. The results indicate the high accuracy, precision, and anti-noise ability of our approach.

  Preview abstract