Tagged in

Keras

3D body recognition using VGG16 like network

3D body recognition is actual for CADs. Here you can find relatively simple approach for solving that problem. In two words this approach is calculating cylinder projection of the body and then feeding it to the NN.

More information

Followers

Elsewhere

More, on Medium

Keras

Vladimir Tsyshnatiy in 3D body recognition using VGG16 like network

Apr 4, 2018

3D body recognition — Lets recognize!

Episode 3: Data preprocessing

We have done a very important thing in the last episode. Namely, found a suitable way to convert 3D bodies into images which we will be able to feed to the Neural Network (NN).

Preparing the data

Image datasets contain giant number of samples nowadays. Similar is wrong for 3d model datasets. They do not contain hundreds of thousands images. They are not well studied and balanced. Also most datasets contain not orientation-aligned bodies.

Intro to 3D body recognition

Problem description

The story starts at March 2017 when my boss told that it is almost impossible to recognize 3d bodies automatically. What the one considers impossible challenges the other.