As part of the Computer Vision nanodegree from UDacity I learned cutting-edge computer vision and deep learning techniques—from basic image processing, to building and customizing convolutional neural networks. Applying these concepts to vision tasks such as automatic image captioning and object tracking, and build a robust portfolio of computer vision projects.
1. Facial Keypoint Detection (Code)
Used image processing techniques and deep learning to recognize faces and facial keypoints, such as the location of the eyes and mouth on a face.
Combine CNN and RNN knowledge to build a network that automatically produces captions, given an input image.
Use sensor data to localize a robot and build a map of the environment with SLAM.