We will see in this article, how with the YOLO neural network we can very simply detect several objects in a photo. The objective is not to go into the details of the implementation of this neural network (much more complex than a simple sequential CNN) but rather to show how to use the implementation which was carried out in C ++ and which is called Darknet.
In this article we will discuss the concept of Transfer Learning … or how to avoid redoing long and consuming learning by partially reusing a pre-trained neural network. To do this we will use a network which is the reference in the matter: VGG-Net (vgg16).
We will discuss in this post a kind of filters widely used by all images software (such as Photoshop or Gimp). In fact and to go further (without “sploiling” the following posts either) this convolution principle will also be widely used by neural networks (Deep Learning) … but we will see that later. First of all, let’s focus on the principle of these convolution filters.
In the previous article we saw how our digital images were built and stored. This naturally brings us to the image histograms. Of course we don’t manage an image like we do for a text . Images are in fact just matrix (like a pixel map ), so first of all we need to analyse the image, and to do that we’ll take a look on the pixel histograms.
In this article we will see and especially understand how images are stored in a computer just to make it usable by other softwares. In fact, this post is the first within a series that will allow us to approach image processing in general but also subsequently the place of Artificial Intelligence and especially Deep Learning in this discipline which is part of a set known as computer vision.