In the manufacturing process for the automotive sector, quality matters. Traditional ways of defect detection processes are dominated by manual inspection, which can be time-consuming and may have human-induced errors. This is why this project proposes a system of automated defect detection to enhance quality control processes at an organization through image processing and machine learning.
This system will be based on advanced algorithms that analyze images of vehicle parts and detect defects with a high degree of accuracy, thereby improving production efficiency and product quality.
Week 1-2: Initial Planning and Requirement Analysis
Define the objectives of the project, scope, and high-level requirements
Gather necessary data and resources.
Week 3-4: Data Collection and Preprocessing Phase
A collection of image data regarding vehicle parts, its preprocessing, feature extraction, and data augmentation.
Week 5-6: Model Development Phase
Development of machine learning models related to defect detection and their training process. Model accuracy and performance validation with test data.
Week 7-8: System Implementation Phase
Implementation of the defect detection system.
Integrate the model into the user-friendly interface
Test and develop the system based on performance metrics and user feedback.
Week 9-10: System Integration and Testing Phase
Conduct rigorous testing to ensure appropriate defect detection.
Measure the system's performance and user’s interactions with the same.
Develop improvement continuously through analytics and user feedback.
Week 11-12: Final Evaluation and Reporting Phase
The final evaluations are done, followed by the validation of the defect detection system.
Compilation of the final project report with documentation.
Individual report presentations by students.
