[Page 2] Video interview: System integrator discusses OCR/OCV imaging challenges and how to overcome them
Following his description of theline scan vision system, Goc touched on the webcast topic and the webcast itself, and what people who tune in can expect to hear about.
"OCR and OCV systems are one of the hardest tasks for machine vision systems. [For these systems], I would start where the characters are created. Talk to whoever is creating these characters and make sure the font is OCR-friendly, has enough space between characters, has simple texts, and have good contrast."
When it comes to the components Goc suggested using in a system, he noted thatlighting is extremely important, and that the goal is to get as much contrast between characters and background as possible, while keeping the background uniform. Concerning the selection of cameras, these should be selected based on the resolution, he suggested.
"I would try to get at least 20 pixels per character height even though somesoftware manufacturers will suggest that 7 pixels is enough. My experience is that this can lead to mismatches, so I would go by this resolution and then choose software you are comfortable with," he said.
Goc also said that those who view the webcast can expect to learn about products traceability, what characters should look like, lighting and filtering options for various surfaces and marking types, preprocessing and transforming images, and different software tools. He will also present case studies with challenging OCR requirements, and how these were overcome. In addition Goc commented on the future of themachine vision industry, citing such applications as the automotive industry, inline gauging, and vision sensor systems as potential growth areas.
Also check out:
2014 poised for significant machine vision industry growth
Video interview: Industry expert discusses 360° vision for intelligent transportation systems
VDMA: European machine vision industry to grow 12% in 2014
Share your vision-related news by contactingJames Carroll, Senior Web Editor, Vision Systems Design
To receive news like this in your inbox,click here.
Join ourLinkedIn group | Like us on Facebook | Follow us on Twitter| Check us out on Google +
Page 1 | Page 2
James Carroll
Former VSD Editor James Carroll joined the team 2013. Carroll covered machine vision and imaging from numerous angles, including application stories, industry news, market updates, and new products. In addition to writing and editing articles, Carroll managed the Innovators Awards program and webcasts.