Face-Recognition

About

Built a model for predicting facial expressions under different lighting conditions

Objective:

Create a model for predicting facial expressions under different lighting conditions

Steps and Tasks:

1. Exploratory Data Analysis
2. Find a good predicting model for facial expressions under different lighting conditions

Contents

The data set contains ten images each of fourty people.The image were created under diffrent lighting conditions, and the subjects varied their facial expressions.

The images are grey scale and 92×11 pixels in dimension. While these images are small, a feature vector that encodes the intensity of every pixel will have 10304 dimensions. Training from such high dimensional data could require many samples to avoid over-fitting. Instead, i use PCA to compactly represent the images in terms of a small number of principal components.

Result

Logistic Regression model gives a good accuracy (0.97)

Tools Used

1. Python
2. Scikit- learn
3. Pandas
4. Numpy
5. Mahotas
6. Jupyter Notebook

Technologies Used

If you liked what you saw, want to have a chat with me about the portfolio, work opportunities or collabration, shoot an email at [email protected]