Deep Learning Model for Complicated Pattern REcognition

Question

I am using transfer learning using ResNet50 for snack packets recognition.

They are one and another similar in dominant color and shape. Those like in images below.

I have about 33 items to recognize.

I used FasterRCNN and SSD for ResNet50.

Not doing well and a lot of items are confused each other.

Which Deep Learning Architecture is suitable to recognize such objects?

Or are there any special tricks to have better recognition for such objects?

I think we need to have architecture to recognize detail pattern.

Answer 1

Make sure you are linking the original pre-trained network in caffe, or you're starting from the beginning with network training!

If you're looking to increase your dataset size, ill frequently take the same image set and rotate each image a few times.

Definitely decrease your image size, and consider giving your images less background noise to work with (people, variable backgrounds etc.)

In the past I have used Alexnet for similar issues with small feature differences.

best of luck!