I am completely new to image processing and python. I hope I can find some help here. I am trying out a project on detecting fouling% on a ship hull using raspberry pi. I am trying to learn how this going to be done and how can i pre-process these images. Images will be captured underwater using Picam module and purpose of stitching is to generate an overview of overall fouling and to calculate the percentage of fouling. Below are ways I will approach this problem, but am I right to say haarcascade will not be able to use in this project because it is not possible to use it to calculate percentage of fouling?
To classify type of fouling and percentage of fouling
Macro fouling and microfouling pictures added and trained using Haarcascade or PCA algorithm to identify them OR Colour Segmentation/blob detection. The final result can be then obtain accurately in comparison to manual image segmentation like Grabcut algorithm.