Just a reminder, in my experience, auto focus and exposure can be a problem. Vision software often works by comparing changes in pixels between one frame and the next, or differences in pixels within the same frame. One should look for a camera that doesn't have auto focus or has a manual setting for zoom, focus, exposure, color balance or anything else that might be done automatically. That way the vision software can better distinguish what has changed and what has not. Don't forget to provide consistent lighting too.
Also, most webcams use a wide angle lens with lots of distortion. It's better to have a camera with a C or S mount, so one can mount a lens that is appropriate for the application (maybe a telecentric lens). So a camera made for machine vision would be best, or one made for astro-photography or microscopy. Adding or removing filters may be appropriate. It depends on what kind of light is useful for the application (monochrome, narrow wavelength, polarized). Astro-photography cameras often have the normal IR filter removed, so is another reason to look at this class of camera for machine vision. Basically speaking, common consumer cameras are generally not very good for machine vision. -- Kirk Wallace http://www.wallacecompany.com/machine_shop/ http://www.wallacecompany.com/E45/ ------------------------------------------------------------------------------ Download BIRT iHub F-Type - The Free Enterprise-Grade BIRT Server from Actuate! Instantly Supercharge Your Business Reports and Dashboards with Interactivity, Sharing, Native Excel Exports, App Integration & more Get technology previously reserved for billion-dollar corporations, FREE http://pubads.g.doubleclick.net/gampad/clk?id=164703151&iu=/4140/ostg.clktrk _______________________________________________ Emc-users mailing list Emc-users@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/emc-users
