Introduction for the complete detection and recommendation system. In this post, I will talk about the dataset used to train the object detection model.
A majority of the available datasets distinguished clothing items on the basis of their category such as T-Shirt, Jeans, Dress etc., and not on the basis of occasion wear. Also, they mostly contained Western clothing items. Since we were unable to find a dataset containing Indian clothing items, we decided to construct a custom dataset which categorized clothes according to Occasion Wear.
The dataset contained 6864 clothing instances and was approximately equally distributed over the following five clothing styles:
- Comfort Wear
- Street Wear
- Office Wear
- Party Wear
- Ethnic Wear
For the Ethnic Wear subset, we collected images of Indian clothes such as Sari, Kurta, Pyjama etc., from the Internet and manually labelled them using labelImg software. For the remaining categories, we modified subsets of DeepFashion dataset and labelled them according to the above clothing styles using labelImg.
labelImg is a graphical annotation tool and can be found here: https://github.com/tzutalin/labelImg
Further information on DeepFashion dataset available here: https://liuziwei7.github.io/projects/DeepFashion.html