0

I am working on an image classification problem and the dataset comes in the following format :

  • class_1_folder : consists of images_folder and mask_folder
  • class_2_folder : consists of images_folder and mask_folder

I am quite new to the field and would like your advice on the use of the mask folders in general in classification tasks.

I did some research but I cannot find an understandable answer.

My thought is that I could use them to improve my classifier's metric results by helping to focus on specific parts of the image. Is this valid ? If yes, should I consider the convolution of the image with its mask before feeding the image to a classifier ?

Any help is much appreciated. Thank you.

john_ny
  • 173
  • 8
  • Are you sure the problem is classification? and not segmentation? – Jeru Luke May 22 '22 at 20:14
  • I am looking at the problem as a classification one.. I just wanted to see if I can use the masks information as well.. – john_ny May 23 '22 at 07:56
  • 1
    As you stated, you can use the mask on the image and feed the result to the CNN. After training the CNN, analyze the feature space in each layer. You should find something interesting – Jeru Luke May 23 '22 at 08:00

0 Answers0