Semantic Segmentation for objects with random shape

Question

Roohollah Milimonfared 2018-7-2

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/408474-semantic-segmentation-for-objects-with-random-shape

编辑： jim peyton 2019-3-8

Hi All the examples and tutorial about Semantic Segmentation are about shape specific objects (e.g. cars, animals, scenes, plants, etc.). I am working on a problem in which the classes do not have a specific shape. They are visually distinguishable based on their textures. Now, my questions is whether semantic segmentation concept and methods (like CNN) can be used in such a context. Thanks, Roohollah

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Image Analyst 2018-7-2

1
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/408474-semantic-segmentation-for-objects-with-random-shape#answer_327215

I don't believe so. If there is no shape that your object takes on, and can be any random shape, then you'll have to use other methods to segment it, like texture segmentation. Then just don't worry at all about assigning a name to the shape.

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

Answer 2

jim peyton 2019-3-8

1
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/408474-semantic-segmentation-for-objects-with-random-shape#answer_364462

编辑：jim peyton 2019-3-8

The problem you're describing is texture segmentation. Here's a good tutorial on using Gabor filters to extract texture features (spatial frequency and orientation).

MathWorks: Texture segmentation with gabor filters

There are other types of texture filters you could use to extract features: Energy/Entropy, gradient magnitudes and directions, even creating your own shape-specific filters.