How to manually change the ObjectTrainingSize in trainCascadeDetector for training larger patches?

3 visualizaciones (últimos 30 días)
Avijit Ashe
Avijit Ashe el 9 de Oct. de 2016
Respondida: Anand el 10 de Oct. de 2016
I'm testing the classifier design functions. When I run the detector it automatically sets the ObjectTrainingSize to [ 32, 44 ] irrespective of the no positive/negative samples. Hw do I manually change it to train on larger patches like [hei,wid]=[50,150]?

Iniciar sesión para responder a esta pregunta.

Respuestas (1)

Anand
Anand el 10 de Oct. de 2016
If you are training using the trainCascadeObjectDetector function, you can set the 'ObjectTrainingSize' parameter during training to change this.

Categorías

Más información sobre Recognition, Object Detection, and Semantic Segmentation en Help Center y File Exchange.

Etiquetas

Productos

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by