8 Telling Things Apart: Image Segmentation
This chapter covers,
- Recognizing the differences between segmentation images and standard images and load segmentation images successfully into Python
- Implementing a fully-fledged data pipeline for the segmentation data and investigate techniques to reduce IO overhead while loading data through the pipeline
- Implementing advance segmentation model (Deeplab v3) that require complex model manipulations via the Keras Functional API
- Implementing custom functions of loss functions/metrics used in Image segmentation and using them to compile models
- Training the image segmentation model on the clean and processed image data
- Evaluating the trained model with a suitable performance metric (e.g. mean intersection over union)
In the last chapter, we learned about various advance computer vision models and techniques to push the performance of an image classifier. Here we will learn about image segmentation. Image segmentation relates to identifying different objects present in an image. It is a very important topic of computer vision and applications like self-driving cars live and breathe image segmentation models. Self-driving cars need to precisely identify objects in their surrounding which is where image segmentation come to play. As you might have guessed already, they also have their roots in many other ample applications such as,