I am doing a vehicle color detection. i have implemented a simple method. Steps are below.
- Getting the ROI ( above the license plate on the vehicle bonnet area) (Extracted Image Window)
- Getting the HS histogram of ROI
- Histogram Back-projection ( BackProj Window)
- From the Back-projection area extracting the vehicle image (devide Window)
- Calculating distance of HS values from predefined HS values for colors. (Doing this for each and every pixcel on the vehicle area shown in devide Window)
- Voting the color and getting the color which has the maximum number of votes.
From thees steps i have only achieved an accuracy of 75%. How can i increase the accuracy? Is there any other method to do this?
I am very new to opencv :) :)