Computer Vision for Quality Control in Manufacturing Training Course

Module 1: Industrial Optics and Image Acquisition

• Selecting industrial cameras: CMOS vs. CCD sensors, resolution, and frame rates
• Lens physics: Calculating focal length, depth of field, and field of view for the shop floor
• Industrial lighting techniques: Backlighting, darkfield, and coaxial illumination strategies
• Triggering and synchronization: Interfacing cameras with sensors and PLCs
• Digital image formats and bit depth for high-precision metrology
• Practical session: Configuring a high-speed industrial camera and optimizing lighting for reflective metallic parts

Module 2: Image Pre-processing and Feature Enhancement

• Noise reduction filters: Gaussian, Median, and Bilateral filtering for industrial environments
• Contrast enhancement: Histogram equalization and CLAHE for unevenly lit production lines
• Geometric transformations: Correcting lens distortion and perspective warping
• Image binarization: Adaptive thresholding techniques for separating parts from backgrounds
• Morphology operations: Dilation and erosion for cleaning up binary masks of defects
• Practical session: Building a Python-based pre-processing pipeline to enhance the visibility of micro-cracks

Module 3: Classical Vision Algorithms for Quality Control

• Edge detection: Sobel, Canny, and Laplacian operators for boundary identification
• Template matching: Locating parts and components within a complex assembly
• Blob analysis: Calculating area, circularity, and centroid for part counting
• Hough Transforms: Detecting lines and circles for structural integrity checks
• Sub-pixel metrology: Accurate measurement of dimensions and tolerances
• Practical session: Developing an automated system to measure the diameter and spacing of drilled holes

Module 4: Machine Learning for Pattern Recognition

• Feature extraction: Using HOG (Histogram of Oriented Gradients) and SIFT for part description
• Dimensionality reduction: Applying PCA to handle high-resolution image data
• Supervised learning: Support Vector Machines (SVM) for part classification
• Random Forests for identifying material types and surface textures
• Model evaluation: Accuracy, Precision, Recall, and F1-score in a manufacturing context
• Practical session: Training a classifier to distinguish between different mechanical components on a conveyor

Module 5: Deep Learning and CNNs for Defect Detection

• Fundamentals of Convolutional Neural Networks (CNNs) for industrial vision
• Transfer Learning: Adapting ResNet and VGG models for small industrial datasets
• Loss functions and optimizers specifically for identifying rare manufacturing defects
• Overcoming data scarcity: Data augmentation and synthetic data generation
• Visualizing model decisions: Using Heatmaps to see where the AI detects a flaw
• Practical session: Fine-tuning a pre-trained CNN to identify "Pass" or "Fail" states in electronic assemblies

Module 6: Real-time Object Detection and Localization

• Modern detection architectures: Overview of YOLO (You Only Look Once) and SSD
• Bounding box regression and Anchor boxes for locating multiple parts
• Performance metrics: Intersection over Union (IoU) and mean Average Precision (mAP)
• Real-time constraints: Balancing detection speed with model accuracy
• Multi-object tracking: Monitoring parts as they move through the production line
• Practical session: Deploying a YOLO model to detect and count moving items on a high-speed belt

Module 7: Semantic Segmentation for Surface Inspection

• Introduction to pixel-level classification for detailed flaw mapping
• Architecture of U-Net for medical and industrial segmentation tasks
• Identifying irregular shapes: Scratches, spills, and corrosion patches
• Creating custom masks for training segmentation models on specialized materials
• Evaluating segmentation: Dice Coefficient and Jaccard Index metrics
• Practical session: Building a segmentation model to outline and measure the area of paint defects on automotive panels

Module 8: Anomaly Detection and One-Class Learning

• Challenges of missing data: When you have many "Good" parts but few "Bad" ones
• Unsupervised learning: Using Autoencoders to learn the "Normal" state of a product
• Variational Autoencoders (VAEs) for generating anomaly scores
• Isolation Forests for detecting outliers in sensor and vision fusion data
• Thresholding for real-time alerts: Reducing false positives in autonomous systems
• Practical session: Implementing an anomaly detection pipeline that flags "Unknown" defects not seen during training

Module 9: Industrial Edge Deployment and Optimization

• Constraints of the factory floor: Latency, connectivity, and power consumption
• Hardware accelerators: Deploying on NVIDIA Jetson, Intel OpenVINO, and TPUs
• Model compression: Pruning and Quantization to speed up inference on the edge
• Containerization: Using Docker to deploy vision apps across multiple production lines
• Cloud-Edge orchestration: When to process locally and when to use the cloud

Practical session: Optimizing a defect detection model for sub-10ms inference on a low-power edge device

Module 10: System Integration and Regulatory Compliance

• Interfacing vision systems with PLCs using Modbus, OPC-UA, and EtherNet/IP
• Designing the Operator Interface: Effective HMI design for quality inspectors
• Data logging and traceability: Meeting ISO and industry-specific documentation standards
• Ethical AI and Bias: Ensuring consistent inspection across different product variations
• Strategies for scaling from a single pilot line to a global manufacturing network
• Practical session: Designing a complete system architecture that triggers a pneumatic reject arm based on AI detection

Requirements:

• Participants should be reasonably proficient in English.
• Applicants must live up to Armstrong Global Institute admission criteria.

Terms and Conditions

1. Discounts: Organizations sponsoring Four Participants will have the 5th attend Free

2. What is catered for by the Course Fees: Fees cater for all requirements for the training – Learning materials, Lunches, Teas, Snacks and Certification. All participants will additionally cater for their travel and accommodation expenses, visa application, insurance, and other personal expenses.

3. Certificate Awarded: Participants are awarded Certificates of Participation at the end of the training.

4. The program content shown here is for guidance purposes only. Our continuous course improvement process may lead to changes in topics and course structure.

5. Approval of Course: Our Programs are NITA Approved. Participating organizations can therefore claim reimbursement on fees paid in accordance with NITA Rules.

Booking for Training

Simply send an email to the Training Officer on training@armstrongglobalinstitute.com and we will send you a registration form. We advise you to book early to avoid missing a seat to this training.

Or call us on +254720272325 / +254725012095 / +254724452588

Payment Options

We provide 3 payment options, choose one for your convenience, and kindly make payments at least 5 days before the Training start date to reserve your seat:

1. Groups of 5 People and Above – Cheque Payments to: Armstrong Global Training & Development Center Limited should be paid in advance, 5 days to the training.

2. Invoice: We can send a bill directly to you or your company.

3. Deposit directly into Bank Account (Account details provided upon request)

Cancellation Policy

1. Payment for all courses includes a registration fee, which is non-refundable, and equals 15% of the total sum of the course fee.

2. Participants may cancel attendance 14 days or more prior to the training commencement date.

3. No refunds will be made 14 days or less before the training commencement date. However, participants who are unable to attend may opt to attend a similar training course at a later date or send a substitute participant provided the participation criteria have been met.

Tailor Made Courses

This training course can also be customized for your institution upon request for a minimum of 5 participants. You can have it conducted at our Training Centre or at a convenient location. For further inquiries, please contact us on Tel: +254720272325 / +254725012095 / +254724452588 or Email training@armstrongglobalinstitute.com

Accommodation and Airport Transfer

Accommodation and Airport Transfer is arranged upon request and at extra cost. For reservations contact the Training Officer on Email: training@armstrongglobalinstitute.com or on Tel: +254720272325 / +254725012095 / +254724452588