Symptotic Analysis of Autoencoder Architectures for Image Colorization and Noise Reduction
Click for more details about project
In this study, the project embarked on leveraging deep learning to address image colorization and noise reduction challenges. The centerpiece of this project was the deployment of a Convolutional Neural Network (CNN)-based autoencoder, meticulously trained on grayscale CIFAR-10 images, achieving a Root Mean Square Error (RMSE) score of 0.052 for generating colorized versions. Further investigations encompassed a comparative analysis of the performance between autoencoders and Principal Component Analysis (PCA) in the context of gaussian and salt pepper noise reduction, employing training data from MNIST images. This analytical approach provided valuable insights into the strengths and limitations of these methodologies, shedding light on suitability of various noise reduction scenarios. Additionally, the project ventured into exploring the data specificity of autoencoders by executing the same model on different image classes, effectively illustrating how autoencoders adapt to diverse data sets.