I started off today working through a few computer vision homework problems involving training classifiers on different datasets, discussing the limitations and potential solutions associated with the various classifiers, implementing histogram equalization for image enhancement (altering the contrast as well as gamma value), and experimenting with linear filtering to apply different convolutions to images.
This is the original image.
________________________________________________
These two images are with diagonal convolutions applied. The filters highlight the diagonal lines in the image in different directions.
_________________________________________________
This is the original image manipulated by changing the contrast and gamma values.
__________________________________________________
The graph on the right displays the histogram of pixel values separated by RGB values.
The graph on the left shows the normalized and cumulative histogram of the pixel values for the flower image.
__________________________________________________
After working through a number of those problems, I was introduced to the current projects being researched in the lab which I could become a part of. One idea is to research the potential effects of implementing openset recognition (a model is able to identify database objects and reject unseen novel objects) along with incremental learning (input data is continuously used to further a model's knowledge) and fixed classifiers (exploring the marginal value of training the last weight layer).
All of these aspects of computer vision and deep learning seem very compelling to me, and I hope to conduct interesting experiments exploring their connections in the future.
Comments
Post a Comment