Interviews
ViDi Systems to show ViDi Suite 2.0 at German Vision expo
24 Oct '16
2 min read
ViDi Systems, a leading Swiss software firm, is set to launch its ViDi Suite 2.0 with its new capabilities and features at VISION 2016 expo, where OEMs, mechanical engineering companies, and system houses learn about the latest innovations in machine vision components, to be held from November 8 to 10, 2016, at booth #1B33, in Messe Stuttgart, Germany.
Typical defects like hits, scratches, or stains are often hardly discernable at the early production stages because of the parts' rough and strongly textured surfaces. With the ViDi red tool in its supervised mode and the ViDi green, the automated detection and classification of defects is now extremely simple.
The software algorithm trains itself on a representative set of annotated images as well as known good samples. The learning system automatically incorporates contextual information in order to form a reliable model of the part's shape and texture. As a consequence, difficult to discern defects can be detected as in the sample to the right: the hits and scratches are considered as anomalies because they have a textured area that deviates from the expected average local surface aspects and tolerable deviations.
One of the key challenges when inspecting surface defects is that they are dynamic, process-related, and caused by the forming process. They become visible and disturbing only after the later production steps, in which the parts get painted and varnished such that the resulting polished surface becomes a specular reflector of light. With ViDi red, typical defects can be detected and classified on coarse material in any orientation with standard illumination and on images acquired with standard matrix cameras.
After the training phase is completed, the inspection process reliably identifies defects in a couple of milliseconds when computing on a standard GPU.
ViDi 2.0 can reliably detect and classify the defects on the complex textured surface on images with specular reflections and tolerable anomalies during early stages of the production process. The inspection is performed without the need for a multitude of carefully tuned and optimised detection algorithms, but instead relies on a human-like approach with an improved testing consistency and repeatability. Learning from the representative set of samples can be achieved in less than 30 minutes. (GK)
Typical defects like hits, scratches, or stains are often hardly discernable at the early production stages because of the parts' rough and strongly textured surfaces. With the ViDi red tool in its supervised mode and the ViDi green, the automated detection and classification of defects is now extremely simple.
The software algorithm trains itself on a representative set of annotated images as well as known good samples. The learning system automatically incorporates contextual information in order to form a reliable model of the part's shape and texture. As a consequence, difficult to discern defects can be detected as in the sample to the right: the hits and scratches are considered as anomalies because they have a textured area that deviates from the expected average local surface aspects and tolerable deviations.
One of the key challenges when inspecting surface defects is that they are dynamic, process-related, and caused by the forming process. They become visible and disturbing only after the later production steps, in which the parts get painted and varnished such that the resulting polished surface becomes a specular reflector of light. With ViDi red, typical defects can be detected and classified on coarse material in any orientation with standard illumination and on images acquired with standard matrix cameras.
After the training phase is completed, the inspection process reliably identifies defects in a couple of milliseconds when computing on a standard GPU.
ViDi 2.0 can reliably detect and classify the defects on the complex textured surface on images with specular reflections and tolerable anomalies during early stages of the production process. The inspection is performed without the need for a multitude of carefully tuned and optimised detection algorithms, but instead relies on a human-like approach with an improved testing consistency and repeatability. Learning from the representative set of samples can be achieved in less than 30 minutes. (GK)
Fibre2Fashion News Desk – India
Popular News
Leave your Comments
Jason Kent
British Textile Machinery Association (BTMA)
Esteemed Clients
-Ltd..jpg?tr=w-120,h-60,c-at_max,cm-pad_resize,bg-ffffff "Thermore (Far East) Ltd.")
.jpg?tr=w-120,h-60,c-at_max,cm-pad_resize,bg-ffffff "Telangana State Industrial Infrastructure Corporation Limited (TSllC Ltd)")
.jpg?tr=w-120,h-60,c-at_max,cm-pad_resize,bg-ffffff "Taiwan Textile Federation (TTF)")
