An introduction to image processing and deep learning in MATLAB
This project explores a few examples of image processing:
- Spatial domain filtering with kernels.
- Image enlargement followed by interpolation and filtering.
- Distinguishing the outline of a piece of paper in an image by means of spatial filtering.
- Introduction to two dimentional fourier transform and frequency domain filtering of images.
- Face recognition by means of a one-layer neural network. The data used in this section is acquired from the AT&T Database of Faces.
5-1. Compressing inputs with an autoencoder.
5-2. Training a one-layer neural network with one-hot targets.
5-3. Stacking the neural network on top of the autoencoder to create the final system.
5-4. Test the accuracy of the system (It yields a 93.75% accuracy rate).
- This project is a computer assignment for the Digital Signal Processing course by Professor M. Akhaee in the spring of 2020 at the University of Tehran.
- I did not design the project; however, the solution which is provided in this page is written by me.
NOTE: First, extract 'data.rar' and then run the code.