Deep Learning

List of Operators ↓

Introduction

The term deep learning (DL) refers to a family of machine learning methods. In HALCON, the following methods are implemented:

3D Gripping Point Detection:

Detect gripping points on objects in a 3D scene. For further information please see the chapter 3D Matching / 3D Gripping Point Detection.

A possible example for a 3D Gripping Point Detection application: A 3D scene (e.g., an RGB image and XYZ-images) is analyzed and possible gripping points are suggested.

Anomaly Detection and Global Context Anomaly Detection

Assign to each pixel the likelihood that it shows an unknown feature. For further information please see the chapter Deep Learning / Anomaly Detection and Global Context Anomaly Detection.

Top: A possible example for anomaly detection: A score is assigned to every pixel of the input image, indicating how likely it shows an unknown feature, i.e., an anomaly. Bottom: A possible example for Global Context Anomaly Detection: A score is assigned to every pixel of the input image, indicating how likely it shows a structural or logical anomaly.

Classification:

Classify an image into one class out of a given set of classes. For further information please see the chapter Deep Learning / Classification.

A possible example for classification: The image gets assigned to a class.

Deep Counting:

Detect and count objects in images. For further information please see the chapter Matching / Deep Counting.

A possible example for a Deep Counting application: Objects in an image are counted and the object quantity is returned.

Deep OCR:

Detect and recognize words (not just characters) in an image. For further information please see the chapter OCR / Deep OCR.

A possible example for deep-learning-based optical character recognition: Words in an image are detected and recognized.

Multi-label Classification:

An image is assigned all contained classes from a given set of classes. For further information please see the chapter Deep Learning / Multi-Label Classification.

A possible example for multi-label classification: All contained classes are assigned to the image.

Object Detection and Instance Segmentation:

Detect objects of the given classes and localize them within the image. Instance segmentation is a special case of object detection, where the model also predicts distinguished object instances and additionally assigns for the found instances their region within the image. For further information please see the chapter Deep Learning / Object Detection and Instance Segmentation.

Top: A possible example for object detection: Within the input image three instances are found and assigned to a class. Bottom: A possible example for instance segmentation: Every instance gets its individual region marked.

Semantic Segmentation and Edge Extraction:

Assign a class to each pixel of an image, but different instances of a class are not distinguished. A special case of semantic segmentation, where every pixel of the input image is assigned to one of the two classes 'edge' and 'background'. For further information please see the chapter Deep Learning / Semantic Segmentation and Edge Extraction.