Semester project for Digital Image Processing course

The CNN model mentioned in this project uses UFPR04 parking lot images. The model is trained and tested on these images.

The python code to store the image pixels and their labels(in CSV and NPY files) is in file - xml_to_csv.ipynb, and the main code written to read, pre-process, visualize, train and test the CNN model, to evaluate the model's performance and to save the model can be found in file - CNN_parking.ipynb

The complete work done is explained in the project report - DK_DIP_proj.pdf file, along with the results and the references.

1. PKLot dataset - Almeida, P., Oliveira, L. S., Silva Jr, E., Britto Jr, A., Koerich, A., PKLot – A robust dataset for parking lot classification, Expert Systems with Applications, 42(11):4937-4949, 2015.
2. Previous work using CNN : http://cs231n.stanford.edu/reports/2016/pdfs/280_Report.pdf