On the performance of convolutional neural networks initialized with Gabor filters.

Over the years, image recognition has been gaining popularity due to its various possible usages. Convolutional Neural Networks (CNNs) have been the classic approach taken on by many researchers because of their capability to learn through the parameter space given a sufficient amount of representative data. When observing a fully trained CNN, researchers have found that the pattern on the kernel filters (convolution window) of the receptive convolutional layer closely resembles the Gabor filters. Gabor filters have existed for a long time, and researchers have been using them for texture analysis. Given the nature and purpose of the receptive layer of CNN, Gabor filters could act as a suitable replacement strategy for the randomly initialized kernels of the receptive layer in CNN, which could potentially boost the performance without any regard to the nature of the dataset. The findings in this thesis show that when low-level kernel filters are initialized with Gabor filters, there is a boost in accuracy, Area Under ROC (Receiver Operating Characteristic) Curve (AUC), minimum loss, and speed in some cases based on the complexity of the dataset.