Repository containing all the code for my 2018 Udacity CV nanodegree course
This Nanodegree program is broken into three main sections:
Use image processing techniques and deep learning techniques to detect faces in an image and find facial keypoints, such as the position of the eyes, nose, and mouth on a face.
The system consists of a face detector that uses Haar Cascades and a Convolutional Neural Network (CNN) that predict the facial keypoints in the detected faces. The facial keypoint detection system takes in any image with faces and predicts the location of 68 distinguishing keypoints on each face.
Some results from part 1:
Train a CNN-RNN model to predict captions for a given image. The network is trained on the Microsoft Common Objects in Context (MS COCO) dataset. The image captioning model is displayed below.
Landmark Detection & Tracking (SLAM): Implementing SLAM, a robust method for tracking an object over time and mapping out its surrounding environment, using elements of probability, motion models, and linear algebra. Sensor and motion data gathered by a simulated robot is used to create a map of an environment. SLAM gives us a way to track the location of a robot in the world in real-time and identify the locations of landmarks such as buildings, trees, rocks, etc.
Nanodegree Link:
https://www.udacity.com/course/computer-vision-nanodegree--nd891