As a part of the Image Signal processing course project I reproduced the paper “Normalized Cuts and Image Segmentation” by Jianbo Shi and Jitendra Malik. The normalized cut algorithm employs optimization via Rayleigh’s inequality, and was found to be effective on images with distinct partitions. The algorithm’s dependency on the hyperparameters has been explained in the report. The sparsity in the graph has been exploited and the code was implemented without any explicit loops; thus decreasing the run time significantly.