Summary

In this chapter, we learned how to build an object recognition system. The differences between object detection and object recognition were discussed in detail. We learned about the dense feature detector, visual dictionary, vector quantization, and how to use these concepts to build a feature vector. The concepts of supervised and unsupervised learning were discussed. We talked about Support Vector Machines and how we can use them to build a classifier. We learned how to recognize an object in an unknown image, and how we can extend that concept to build a visual search engine.

In the next chapter, we are going to discuss stereo imaging and 3D reconstruction. We will talk about how we can build a depth map and extract the 3D information from a given scene.