Wei-Yao Chiu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Wei-Yao Chiu has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Chia-Hung Wu
Industrial Technology Research Institute
1 shared publication - Du-Ming Tsai
Department of Industrial Engineering and Management, Yuan Ze University, Taoyuan, Taiwan
1 shared publication Saul A. Reynoso Farnes
1 shared publication- Wen-Chung Chang
Department of Electrical Engineering, National Taipei University of Technology, Taipei, Taiwan, R.O.C.
1 shared publication - Ya-Hui Tsai
School of Nursing, Yuan Ze University, Chung-Li, Taoyuan, Taiwan
1 shared publication
Latest Publications
- 22 February 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Components, Packaging and Manufacturing Technology
- Vol. 11 (4) , 697-707
Autofocus Measurement for Electronic Components Using Deep Regression
Image-based focus measurement in manufacturing process is important for tasks such as automated inspection, automated assembly and auto-soldering. To inspect or manipulate an object, the visual system must sense the best image position to ensure all the details of the product can be viewed. For this reason, an auto-focus system is required. Traditional auto-focus systems based on Depth-from-Focus (DFF) or Depth-from-Defocus (DFD) rely on a series of images by moving the lens with a control motor to find the sharpest location. The process time defers it for in-line, real-time industrial applications. In this paper, we propose a deep neural network regressor for fast and accurate auto-focus. The Convolutional Neural Network (CNN) model is proposed and evaluated for the auto-focus task on a variety of electronic surfaces, including Wafers, LCD (Liquid Crystal Display) and ball grid array (BGA). The proposed deep regression model requires only one single sensed image of the object to estimate the depth. The effect of environmental variations in the illumination is evaluated for the robustness of the proposed method. Experimental results indicate the proposed CNN Regressor can achieve fast and accurate results for the tested objects with repetitive and arbitrary patterns.
- 22 February 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Components, Packaging and Manufacturing Technology
- Vol. 11 (4) , 697-707
Autofocus Measurement for Electronic Components Using Deep Regression
Image-based focus measurement in manufacturing process is important for tasks such as automated inspection, automated assembly and auto-soldering. To inspect or manipulate an object, the visual system must sense the best image position to ensure all the details of the product can be viewed. For this reason, an auto-focus system is required. Traditional auto-focus systems based on Depth-from-Focus (DFF) or Depth-from-Defocus (DFD) rely on a series of images by moving the lens with a control motor to find the sharpest location. The process time defers it for in-line, real-time industrial applications. In this paper, we propose a deep neural network regressor for fast and accurate auto-focus. The Convolutional Neural Network (CNN) model is proposed and evaluated for the auto-focus task on a variety of electronic surfaces, including Wafers, LCD (Liquid Crystal Display) and ball grid array (BGA). The proposed deep regression model requires only one single sensed image of the object to estimate the depth. The effect of environmental variations in the illumination is evaluated for the robustness of the proposed method. Experimental results indicate the proposed CNN Regressor can achieve fast and accurate results for the tested objects with repetitive and arbitrary patterns.
- 1 November 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Object volume estimation based on 3D point cloud
An approach to estimating the volume of an object based on 3D point cloud is proposed in this paper. Firstly, 3D point cloud is cut into slices of equal thickness along the z-axis. Bisect each slice along the y-axis and cut each slice into sub-intervals along the x-axis. Using the minimum and maximum coordinates in each sub-interval, two surface curve functions can be fitted accordingly for the bisected slices. Then, the curves are integrated to estimate the area of each slice and further integrated along the z-axis for an estimated volume of the object.
- 1 November 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Object volume estimation based on 3D point cloud
An approach to estimating the volume of an object based on 3D point cloud is proposed in this paper. Firstly, 3D point cloud is cut into slices of equal thickness along the z-axis. Bisect each slice along the y-axis and cut each slice into sub-intervals along the x-axis. Using the minimum and maximum coordinates in each sub-interval, two surface curve functions can be fitted accordingly for the bisected slices. Then, the curves are integrated to estimate the area of each slice and further integrated along the z-axis for an estimated volume of the object.