Semantic segmentation for grayscale image
6 次查看(过去 30 天)
显示 更早的评论
How can implement semantic segmentation for gray scale image? How to train that network?
2 个评论
Walter Roberson
2022-6-27
Yes. At worst case, repmat() the grayscale along the third dimension to make it an RGB image.
回答(2 个)
Image Analyst
2022-6-27
Start here:
I'm working on a simplified version where you simply just locate your input images, and labeled images folder but it's not ready to share yet.
2 个评论
Image Analyst
2022-6-28
If the Mathworks demo isn't working then make sure your input is correct (whether color image or gray scale, and size of image, if that matters). If it is correct then call tech support and tell them the demo doesn't work.
Zara Khan
2022-6-28
12 个评论
Walter Roberson
2022-6-30
Perhaps you should be training your own network; see https://www.mathworks.com/help/deeplearning/ug/create-simple-semantic-segmentation-network-in-deep-network-designer.html
The pre-trained Triangle Semantic Segmentation Network might simply be too weak for your purposes, especially since your sample sign images are not very triangular.
另请参阅
类别
在 Help Center 和 File Exchange 中查找有关 Image Data Workflows 的更多信息
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!