Chapter 12

Performing Image Classification


Bullet Recognizing the key contributions of image recognition challenges

Bullet Discovering the importance of image augmentation

Bullet Using the German Traffic Sign Benchmark dataset

Bullet Creating your own CNN capable of classifying traffic signs

Understanding how convolutional layers work, as shown in Chapter 10, is just a starting point. Theory can only explain how things work, but it can’t adequately describe the success of deep neural network solutions in the image-recognition field. The great part of this technology’s success, especially in AI applications, comes from the availability of suitable data to train and test image networks, their application to different problems thanks to transfer learning, and further sophistication of the technology that allows it to answer complex questions about image content.

In this chapter, you delve into the topic of object classification and detection challenges to discover their contribution in the foundation of the present deep learning renaissance. Competitions, such as those based on the ImageNet dataset, ...

Get Deep Learning For Dummies now with O’Reilly online learning.

O’Reilly members experience live online training, plus books, videos, and digital content from 200+ publishers.