Key Takeaways
Deep learning inspection tools streamline complex tasks like defect detection, assembly verification, and text reading by learning from images and improving over time. They bring adaptability to production lines; handling challenges that traditional systems or human inspectors can't easily manage.
Maintaining consistent quality in automotive manufacturing can be challenging – especially due to the unpredictable defects that can crop up. Deep learning inspection systems use digital cameras and image recognition algorithms to learn to spot a broad spectrum of problems like rust, discoloration, and damage. When developed properly, deep learning applications help reduce errors and improve product quality.
In an inspection application, machine vision and deep learning work together like this:
- Developers build a training set of images of good products to establish the “correct” product appearance.
- Developers add images of defects to find the most common anomalies and flaws.
- Machine vision cameras take pictures of items on production lines. The machine learning application compares these new images against the training images to flag defects.
- Because the application is optimized to seek success and avoid failure, it teaches itself to become more accurate over time.
The software to build deep learning applications must have four core capabilities:
1. Feature location and assembly verification
Finding defects isn’t the only role for machine vision and deep learning software. It can also use training images and learning algorithms to locate components, which can help with tasks like instructing a robotic arm to align components. This is important for high-precision products like semiconductors, smartphones, and pharmaceuticals.
These applications can also scan the number of products in a location. Then, it can tell a robot to keep adding more of the same products until a shelf or carton is full. They can also count all the components in a package to make sure nothing was left out.
The best location and verification tools work in a wide variety of lighting and surfaces that confound rules-based vision systems and quality-control personnel.
Read more: Identify various components or part configurations with deep learning assembly verification tools
2. Defect detection and segmentation
Identifying defects is the most sought-after capability for deep learning software in production. While machine vision systems can be programmed to flag one kind of defect, identifying multiple ones is far too time-consuming.
Defect detection tools start with a set of “good” images and pictures of common defects like rust, dents, scratches, and misalignments. Top-quality detection tools also have an option for identifying any defects that differ from the “good” image. These images of rare production outcomes can help the tool teach itself to improve its accuracy.
Segmentation identifies one section within an image, telling the software to scan that area for defects. This helps simplify deep learning applications by filtering out areas that aren’t relevant to the segment scan.
Learn more: How deep learning defect detection automates inspections for the automotive and other industries
3. Object and scene classification
Classifying objects and scenes helps deep learning applications divide defects into classes, which helps the application’s ability to self-improve without human intervention. In general, images are labeled according to certain characteristics and then classified according to parameters. That way, for example, scratched products could be automatically rerouted to the paint line while dented products could be sent to the metalworking shop.
Classification also sorts products and components based on common characteristics like color, texture, materials, packaging, and defect type. The best classification tools establish tolerances for natural deviations in shades, shapes, or dimensions, and vary these tolerances according to the needs of each class.
Read more: How deep learning classification tool works
4. Text and character reading
Reading words, numbers, or text on a surface – like an engine block or copper tube – can be almost impossible for people and standard machine vision algorithms. Lighting can vary on a production line, creating shadows in some places and glare in others – and shifting throughout the day depending on changes in ambient light on the factory floor.
Deep learning applications connect fonts and typefaces with the lettering on parts in production. This makes it much easier to read text through plastic covers and on uneven surfaces like clothing or gardening tools. Advanced character reading tools go beyond the factory floor, finding a role in distribution, logistics, and commerce systems.
Check it out: Read complex and challenging codes under any condition with deep learning-based OCR
Other features to look for in deep learning software
In addition to the four capabilities outlined above, a robust deep learning software package should be:
- Easy to learn, with an intuitive GUI that does not require advanced technical knowledge.
- Optimized for visual-inspection production environments, with smaller image sets that require less training.
- Designed for Windows PCs with GPUs (graphics processing units).
Cognex deep learning has these, and many more powerful features designed for factory and production environments, unlike other open-source deep learning frameworks. It combines a machine vision tool library with advanced deep learning tools inside a common development and deployment framework.