“Manufacturing branded handbags is a big business in the fashion world. Shoppers’ feedback showing photos of their purchased handbags in social networks or blogs is important for branding purposes. In this paper, we deal with handbag recognition.”
So explain researchers Yan Wang, Sheng Li and Alex C. Kot of the Rapid-Rich Object Search (ROSE) Laboratory, at the School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore. The team used Convolutional Neural Networks (and other algorithms) on (what is believed to be) the first handbag datasets constructed for branded handbag recognition.
“The experimental results show that our method performs very well on recognizing handbags. In our future work, more elaborate patch partition methods are needed to deal with the nonrigid deformation of handbags.”
See: On Branded Handbag Recognition in IEEE Transactions on Multimedia (Volume: 18, Issue: 9, Sept. 2016)