| Proj No. | A2240-251 |
| Title | Deep Learning Assisted Machine Vision for Fiber Photonic Sensors |
| Summary | Current state-of-art CCD imaging is formed by RGB 3 colors to identify all the colors in imaging. However, in many highly sensitive sensors today, the changes of spectrum is just few nanometres. The challenge is that common CCD cannot identify or distinguish among such tiny spectral signals. Therefore the goal of this project is to use build a model to characterize different spectral emission wavelength on CCD. Eventually the software is able to precisely distinguish the wavelength from each pixels on CCD. This will be applied to micro-array sensors which can be targeted for medical diagnostics. Hence, we are inviting students to work with us in developing deep learning algorithms to automate the analysis and encoding of spectral images. The goal is to develop a deep learning model that can help classify or predict the responses from a developed photonic fiber sensor. The responses of fiber will change its color and thus need a system to faciliate the readout. *The major function required is machine learning and likely image analysis. The student would work in a multi-disciplinary team on the following tasks: - Develop and apply feature extraction algorithms on spectral data - Develop algorithms to apply machine learning methods on data - Apply the final software to laser imaging for testing At the end of the FYP, the student would deliver a functional software capable of performing classification of newly acquire images OR spectral data. |
| Supervisor | A/P Yu-Cheng, Chen (Loc:S1 > S1 B1A > S1 B1A 26, Ext: +65 8228 7812) |
| Co-Supervisor | - |
| RI Co-Supervisor | - |
| Lab | CBB2 (formerly Machine Learning Lab) (Loc: S1-B4c-10, ext: 4882) |
| Single/Group: | Single |
| Area: | Intelligent Systems and Control Engineering |
| ISP/RI/SMP/SCP?: |