-
Course Date:
08 Mar 2023 to 09 Mar 2023
-
Registration Period:
01 Dec 2022 to 15 Feb 2023
-
Time:
09:00 AM to 06:00 PM,
16 hours / 2 days
-
Mode of Training:
Facilitated Learning (F2F) & Practical Training
-
Venue:
Singapore Polytechnic
-
Funding:
Eligible for SkillsFuture Credit
*Please note that once the maximum class size is reached, the online registration will be closed. You may register your interest, and would be notified if there is a new run.
This course introduces image processing techniques in computer vision, application of machine learning in computer vision and advanced pre-trained neural network models for computer vision solution.
Participants will be equipped with necessary image processing techniques to pre-process data for building and deploying high accurate computer vision pipeline. They will also be equipped with machine-learning and deep learning skills to develop and train the models for complex and critical tasks such as healthcare image anomaly detection and wall crack detection.
Participants will also gain performance metrics knowledge to evaluate computer vision models’ accuracy, precision, recall, etc., fine-tune parameters and improve the system.
By the end of the course, participants will be able to:
1. Apply computer vision techniques for feature extraction, image processing, anomaly image detection and classification applications.
2. Deploy AI project cycle to solve real-world problems such as access card detection, wall crack detection and pneumonia x-ray image classification.
3. Elaborate AI powered computer vision applications, future trend and challenges in the industry and society.
Topics to be covered
1. Basic Image Processing Techniques
2. Machine Learning for Computer Vision
3. Deep Learning for Computer Vision
4. Project and Test
With support from Intel, selected content from Intel® Digital Readiness Program material is included in this short course as supplementary content to enhance the relevance of this course to the Industry and to better support learners in appreciation of the applicability of the concepts covered.