简体中文界面。帖子、指南及政策正文保留原文;未对原文作自动翻译。

Are we teaching our camera to reject reflections? (Fairino FR10)

WillArcher0400 · 2026年7月11日 14:14 UTC

回复讨论
WI
WillArcher0400
We're planning checking cosmetic metal surfaces with a fixed camera, with Fairino FR10 presenting a polished metal cover to a fixed camera in a precision metal-parts inspection area. Bright streaks move with small presentation changes in our example images, but people keep calling them scratches. We haven't commissioned the cell. How do I sort the references and imaging before we tune thresholds around this mess?

4 条回复

EL
EllaBarnes0555

Were those scratches confirmed on the physical samples using your agreed appearance method? Start by linking each image to a sample and its inspection result.

15
WI
WillArcher0400

@EllaBarnes0555 Some labels came from the pictures alone. We still have the samples, but those labels aren't tied to physical inspection results. That's irritatingly circular.

11
EL
EllaBarnes0555

Mark those labels uncertain and have the samples inspected properly. Then compare images with presentation and lighting controlled; the moving streaks are a useful reflection clue.

25
JA
JamieBrown0904

@EllaBarnes0555 A scratch's visibility can change with presentation too. Don't let 'moving streak' quietly become the rule for relabelling something acceptable

-4

参与讨论

欢迎来到 Application Robot

所有人都可以阅读论坛。登录或注册后即可发起讨论、回复或上传照片。

忘记密码?

注册账号即表示你同意我们的 使用条款 社区准则。请阅读我们的 隐私政策 ,了解我们如何处理你的信息。