Recognition-and-Classification-of-Facial-Attributes

Created a classifier that can identify and classify 41 types of facial attributes, using an ImageNet pre-trained ResNext50 model provided by PyTorch and CelebA dataset. Multiple data augmentation techniques were used along with the MSE loss function. Obtained a training accuracy of 95.7% and test accuracy of 91.8%.

Disparity-Computing-from-Stereo-Vision

Disparity Computing of rectified images of the same scene captured from two different viewpoints.

Histogram-Equalization

Histogram equalization based image processing to improve the contrast of the image