Deep learning is a subset of machine learning, which is essentially a neural network with three or more layers. These neural networks attempt to simulate the behavior of the human brain—albeit far from matching its ability—allowing it to “learn” from large amounts of data. While a neural network with a single layer can still make approximate predictions, additional hidden layers can help to optimize and refine for accuracy.

Deep learning drives many artificial intelligence (AI) applications and services that improve automation, performing analytical and physical tasks without human intervention. Deep learning technology lies behind everyday products and services (such as digital assistants, voice-enabled TV remotes, and credit card fraud detection) as well as emerging technologies (such as self-driving cars).

Machine Vision software applications which stands as one of the important aspects of factory automation, has now gained momentum by the introduction of Deep Learning Machine Vision tools that allows Training of models of defects, good, bad etc., with large data to overcome limitations of conventional vision algorithms.

Why AI?

Traditional Machine Vision Tools                               AI Classification Algorithm

✗ Confuse water droplets and surface damage      ✓ Ignores water droplets

✗ Can’t handle shade and perspective changes     ✓ Is robust to variations in surface finish and perspective

✗ Miss subtle surface damage                                   ✓ Can detect a full range of defects

Application Examples

1. Significantly improves quality, productivity, and efficiency in X-ray medical imaging

The tiny and random nature of fibers on X-ray detectors make them challenging and time consuming for traditional methods or humans.

2. Surface inspection on metal plates

Classification of good and bad metal sheets. Tiny scratches on metal are detected and classified as bad samples. AI – Deep Learning detects small defects on high resolution images of rough texture. Just a few tens of samples are required to train a good accuracy model. Classification is used when good and bad samples are available, while Anomaly Detection is used when only good samples are available.

3. Location/identification of wood knots

Localization and classification of various types of knots in wood planks. Software can robustly locate and classify small knots 10-pixels wide in high-resolution images of 2800 x 1024 using the tiling mechanism which preserves native resolution.

4. Detection/segmentation of vehicles

Detection and segmentation of various types of vehicles in outdoor scenes. Software provides output shapes where each pixel is assigned a class. Usage of blob tool on the segmentation output allows performing shape analysis on the vehicles.

TELEDYNE DALSA has released ASTROCYTE – a No-Code AI training tool to quickly deploy AI models for machine vision solutions. Tackle tough inspection cases traditional methods can’t handle.

TELEDYNE DALSA ASTROCYTE software empowers users to harness their own images of products, samples, and defects to train neural networks to perform a variety of tasks such as anomaly detection, classification, object detection, and segmentation. With its highly flexible graphical user interface, ASTROCYTE allows visualizing and interpreting models for performance/accuracy as well as exporting these models to files that are ready for runtime in TELEDYNE DALSA Sapera and Sherlock vision software platforms.

NOTE: Online Solutions (Imaging) Pvt. Ltd., Chennai, India. are the authorized distributors of TELEDYNE DALSA in India. (www.onlsol.com)

Please contact us at [email protected]

Blog created with contents from different web sites and also from the contents of TELEDYNE DALSA. Any objectionable usage of images or contents can be informed to us at [email protected] and we can remove or correct it as required. Purpose of this Blog to give technical info and promote TELEDYNE DALSA products also.