Deep Learning Applications for Shopping Industry

Deep Learning Applications for Shopping Industry

For CMPE492 Senior Project, we focused on the modern applications of Deep Learning and came up with two ideas for shopping industry. First project is related to fruit and vegetable shopping in stores with cashier-free systems. We observed that fruit and vegetables that are sold in the stores with cashier-free systems are specified manually by the customers. Which can cause frauds and great losses to the markets because, a customer is able to type a different product’s name(intentionally or not) and buy the item cheaper. We offered an image recognition solution which recognizes and classifies the bagged grocery item pictures and proccesses according to the class using CNNs(VGGNet). The second project is a shirt swapping project for e-shopping platforms. Due to the epidemic, people are willing do clothing shopping online rather than using unhygienic fitting rooms. The problem is that a customer would like to try the product s/he is buying in order to see if it looks good on top or not. Our solution is to make customer able to try the shirt virtually. Given two male models with shirts as input, our model is able to transfer shirts from to another using dress extraction and GAN(Generative Adversarial Networks) approach.




Project Poster: 

Project Members: 

Ali Meriç Deşer
Mete Han Kurt

Project Advisor: 

Fikret Gürgen

Project Status: 

Project Year: 

  • Spring

Contact us

Department of Computer Engineering, Boğaziçi University,
34342 Bebek, Istanbul, Turkey

  • Phone: +90 212 359 45 23/24
  • Fax: +90 212 2872461

Connect with us

We're on Social Networks. Follow us & get in touch.