Using machine learning methods to improve image suggestion and image retrieval results

Vidigami, the sponsor company, is developing tools to create digital yearbooks for schools – organizing personal photo collections of students, parents, and staff. Current technologies have made it easy for everybody to have a digital camera or simply digitalize their hardcopy versions of their photos. However, this huge amount of data makes it hard to sort photos and extract an album based on specific criteria. The problem of managing photos becomes more complicated by the growth of social networks where people can share and see each other’s photos of an event. To address this problem it seems reasonable to have a system which tries to capture similarities in the photos and also tag photos with as much labels as we can and then select the photos based on these labels to make an album with user specific description. The main goal of this internship is to implement a system which can be used to help generate school year albums.

Amirhossein Bakhtiari
Faculty Supervisor: 
Dr. Greg Mori
British Columbia