Python code for merging two separate photos to create a single, multi-person photo

Description

This project is a python code that merges two portraits of different people to create a single, multi-person photo. To do this, Person A takes a photo of Person B, and Person B takes a photo of Person A with the same background.
Given these two input images, our goal is to create a third image with both Person A and Person B in the photo together. We first color correct the photos and then register the images by performing keypoint matching to estimate the homography. We then blend the images either by alpha blending or by GrabCut segmentation, depending upon the relative locations of the human subjects in the two images.

Result

Python code for Frequency-tuned Salient Region

Python code for Classification of photographic images based on perceived aesthetic quality

http://www.maths.lth.se/matematiklth/personal/petter/rapporter/grabcut.pdf