Deep-Learning-Approach-for-Surface-Defect-Detection How to prepare data

How to prepare data

Open PowerDi opened this issue 5 years ago • 10 comments

Your work is outstanding. But could u tell me how should I prepare the image? Does it need label the defects firstly with bounding box or pixel segmentation?

May 27 '19 03:05 PowerDi

You should label the defects with pixel segmentation.

May 29 '19 08:05 ShuaiLYU

@Wslsdx What tool did you use for pixel segmentation or what tool is good to use here?

Jun 19 '19 13:06 Shahdoust

@Shahdoust what dose "pixel segmentation" mean?

Jun 19 '19 14:06 ShuaiLYU

@Wslsdx thank you for your reply. Sorry I am a little confused and new here. I meant the exact tool like LabelMe or PixelAnnotationTool that provides to segment your images manually. I really appreciate if you help me to prepare my data.

Jun 19 '19 14:06 Shahdoust

@Shahdoust LabelMe or PixelAnnotationTool is oK. I prepare my data with Halcon .

Jun 20 '19 01:06 ShuaiLYU

@Wslsdx Does Halcon have pixel-level labeling capabilities? If not, what is the best way to label images at pixel level?

Oct 11 '19 06:10 nys09

@Shahdoust So what tools did you end up using for data tagging?Which tool is effective?Can you tell me?Thank you very much

Apr 12 '20 03:04 li675599061

@li675599061 I think the PixelAnnotation tool is good and easy to use.

Apr 13 '20 16:04 Shahdoust

@Shahdoust ,windows10安装和使用 PixelAnnotation tool的方法教程有嘛

May 13 '21 03:05 qwfeng

windows使用Halcon制作数据集的教程有嘛

May 13 '21 03:05 qwfeng

Deep-Learning-Approach-for-Surface-Defect-Detection Deep-Learning-Approach-for-Surface-Defect-Detection copied to clipboard

How to prepare data

Deep-Learning-Approach-for-Surface-Defect-Detection
Deep-Learning-Approach-for-Surface-Defect-Detection copied to clipboard