Deep learning based image similarity search for product recommendations
This project demonstrates, how we can make use of deep learning to do state-of-the-art image similarity search. I have used tensorflow and some publicly available datasets.
root folder
│
└───lib
│
└───server
| │───rest-server.py
| │───imagenet
| │───static
| │───templates
| │───uploads
| │────dogs_and_cats
| │────shoes
| │────sandals
| │────slippers
| │────boots
| │────apparels
python server/image_vectorizer.py
This will generate two files namely, image_list.pickle and saved_features.txt. Keep them inside lib folder where search.py script is available.
python server/rest-server.py
One interesting application of this project is a recommendation engine based on image features.Here is an example of similar project of mine. Here instead of a web UI i have used an android UI. Once the user clicks a product image, the image will go to the server and k-number of similar product images can be displayed on UI as product recommendations. Theses rescommendations are purely based on image similarity. This kind of recommendations have high potentials in fashion-based ecommerce industry.