Event Details
Identifying Vehicle Exterior Color by Image Processing and Deep Learning
Presenter: Somayeh Abniki
Supervisor:
Date: Fri, March 11, 2022
Time: 11:00:00 - 12:00:00
Place: via Zoom - please see link below
ABSTRACT
Join Zoom Meeting
https://uvic.zoom.us/j/81436149220?pwd=UU9KRE9wTkdsRGUyNisyWXJVZFJpQT09
Meeting ID: 814 3614 9220
Password: 714756
Please log in to Zoom via SSO and your UVic Netlink ID.
ABSTRACT
Colour is one of the primary criteria in a car buyer’s decision process. Hence, vehicle colour extraction and identification from vehicle images play an important role in the success of online automobile purchasing operators. In this study, we present a vehicle colour recognition method using image processing techniques to construct different feature vectors, and then use these feature vectors as input to deep neural networks to classify the vehicle colours into 14 classes. Local relative entropy is utilized as a measure of image segmentation to select the region of interest. Experiments are performed on the image dataset supplied by an e-commerce operator. Our implementation result shows a 72% average precision rate of all 14 colour categories.