Summary

In this chapter, we began by learning about creating a training dataset for the process of object localization and detection. Then, we learned about SelectiveSearch, a region proposal technique that recommends regions based on the similarity of pixels in proximity. We also learned about calculating the IoU metric to understand the goodness of the predicted bounding box around the objects present in the image.

In addition, we looked at performing non-max suppression to fetch one bounding box per object within an image, before learning about building R-CNN and Fast R-CNN models from scratch. We also explored why R-CNN is slow and how Fast R-CNN leverages RoI pooling and fetches region proposals from feature maps to make inference faster. Finally, we understood that having region proposals coming from a separate model results in more time taken to predict on new images.

In the next chapter, we will learn about some of the modern object detection techniques that are used...