CODEWITHSUNDEEP
neural-networkdeep-learningcaffeconv-neural-network
Z.Kal
Z.Kal

Reputation: 426

Training image orientation classifier - Neural Network

I would like to train a conv neural network to detect the correct orientation of images. only 4 degrees (0,90,180 and 270).

The difficulty is that: the images will contain different objects - single person, group of person, mountain view, buildings, etc...

I was thinking of training the convNet on a big set of images. each image will be rotated 4 times (0,90,180 and 270). and each image will have a label (0 -> 0, 90 -> 1, 180 -> 2, 270 -> 3).

Are there other examples of orientation convNets / complex 4-class convNets / RNNs I could use for inspiration? (I'm using Caffe framework)

Upvotes: 2

Views: 806

Answers (1)

Shai
Shai

Reputation: 114866

I agree with your observation, that looking at specific objects in the photos and use their orientation to decide on the image orientation can be misleading. Check this image for example:
enter image description here

It is perfectly oriented, yet the face is not upright.

Therefore, I suppose your approach to treat this problem as an image labeling problem (i.e., single orientation label per input image) is a good way to proceed.
I would take any not-too-fancy off-the-shelf net and fine tune it based on the labeling you suggested.

Upvotes: 0

Related Questions