Which one is a better method for contour detection? image processing or deep learning?
1 visualización (últimos 30 días)
Mostrar comentarios más antiguos
Mustafa Uysal
el 13 de Dic. de 2019
Respondida: Image Analyst
el 13 de Dic. de 2019
I'm studying on a project using MATLAB. i don't know which method should i choose, image processing or deep learning?
1- Detect the sample when sample is put on the frame
2- Remove the background
3- Detect contours of each 3 parts of sample.
0 comentarios
Respuesta aceptada
Image Analyst
el 13 de Dic. de 2019
Do you have hundreds of images with ground truth to train a deep learning network with? You'll need them. Often the ground truth is gotten from traditional image analysis or by manually tracing/painting over each training image. I don't know what your samples look like, but a simple traditional method might work as well or better than a deep learning method, and without hundreds of labeled, ground truth samples being needed for training.
0 comentarios
Más respuestas (0)
Ver también
Categorías
Más información sobre Recognition, Object Detection, and Semantic Segmentation en Help Center y File Exchange.
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!