In this course, we have been only doing classification of cats vs dogs, hourses vs humans, etc, using conv net.
But these are not useful in real world. Why do we spend so muc time learning image classification ?
What are the real applications of conv nets ?
Hi @mc04xkf mc04xkf,
There are plenty of applications nowadays: facial recognition, object detection, image captioning, semantic segmentation, and many others.
The same idea of convolution, as feature extraction, is a crucial concept in deep learning, with images in particular, but not only. If we should flatten an image and process it as it is, without convolutional steps, we would probably miss important content (a pedestrian for a self-driving car?).
The skeleton of these applications is the same of the ones you see here.
Allow me to tell it my opinion.
Considering the growing potential of computer vision, many organizations are investing in image recognition to interpret and analyze data coming primarily from visual sources for a number of uses such as medical image analysis, identifying objects in autonomous cars, face detection for security purpose.
If you doesn’t have any basic skill and experience on it, i think you would very confuse in doing more advance thing.