CVB Polimago is a pattern matching tool, combining the individual advantages of different proven approaches for the first time in a single tool. With the help of simulated training images different poses of an object are taught. After a predefined pattern has been trained in all variable positions, the algorithm extracts specific features out of this dataset.
Thus the process learns which detail of the image needs to be detected in the subsequent search process as relevant for further processing. During the teach process CVB Polimago automatically creates thousands of training images; randomly generated views of the model. The algorithm learns the versatility of the given pattern and gains the ability to detect the training image reliably from a number of different angles, thus considerably reducing the effort for the user.
Pattern recognition is one of the major tasks in machine vision and is used in a variety of applications. The proper and robust functioning of pattern recognition largely depends on the variability of the teaching model. If geometrical transformations such as rotation, size changes and tilting as well as changes in illumination have not been taught during the teaching phase the recognition rate decreases in a later stage of the process. So far, the effort for the user has been significantly high in teaching variable training images as all kinds of geometrical transformations are supposed to be integrated in order to obtain a complete training set.
The tool delivers robust detection rates of polymorphic objects in different positions and is especially suited for tasks such as pose evaluation and object tracking. The extremely high recognition rates are an important base for pick and place applications such as robot gripping and the robust tracking and tracing of objects.
CVB Polimago is delivered with a variety of application and programming examples and thus provides the user a fast introduction to the tool.
Position, rotation, scaling and tipping invariant pattern recognition
Fast execution speed for use in real time applications
Fully automatic generation of additional training images
With the introduction of CVB Polimago an teach application has been launched which provides a common teaching environment for not only CVB Polimago but also CVB Minos.
Have a look at our demo systems from Automatica 2016 including explanations of hyperspectral imaging and our new software tool for pose estimation called CVB Polimago.
The main focus of CVB Polimago ist the tracking of pre-trained objects in images. With its sophisticated algorithms the tool is not only capable of finding the position of a trained object but also of retrieving the orientation and the scale which is commonly denoted as the pose of the object.
CVB Polimago is the tool for fast and robust recognition of polymorphic objects: In this example every pre-learned salami slices are recognized proper - even the partly hidden ones.