How to create the groundTruth and evaluate the classical computer vision model for crack detection and does training models only restricted for machine and deep

If I have a model to detect cracks which can be consider as classical computer vision model, it works based on thresholding and morphological operation to detect the cracks on the surface, the model is based on Matlab, My questions are : 1- How to create the ground Truth and it necessary for this type of model for performance evaluation? 2- How to evaluate this model based on precision and recall if I have 100 images or more? 3- Do I need to train this model or training restricted to machine learning and deep learning models only? I attached the original image (The model input) and the model output

Answer 1

[Aneela]

Hi @yasmin ismail

1. The Image Labeller in MATLAB app allows you to label ground truth data in a collection of images. Refer to the following MathWorks documentation link for more information on image labeller app: https://www.mathworks.com/help/vision/ref/imagelabeler-app.html
2. Precision measures the accuracy of positive predictions, while recall measures the ability of the model to find all relevant instances. The "precisionRecall" function in MATLAB gets precision and recall metrics of object detection results. https://www.mathworks.com/help/vision/ref/objectdetectionmetrics.precisionrecall.html
3. Computer vision models based on thresholding and morphological operations typically do not require training in the same way that machine learning or deep learning models do. They rely on manually set parameters such as threshold values, structuring element shapes, and sizes. Experiment with different parameters to optimize the model's performance.

Hope that helps!