search

nisargptl / vehicle-recognition

This enables users to gather information about any vehicle and they can see the details in a matter of seconds. Snap a quick photo in the app and it will provide the details about the vehicle make, model, year, user ratings and starting retail price. In addition, it will provide this same information for the 2 closest competitors so a user can do some quick comparison shopping.
https://viris.herokuapp.com/
0 stars 1 forks source link

201801416_Challenges_Solutions #72

Closed khyatibhuva closed 3 years ago

khyatibhuva commented 3 years ago

Write your challenges you faced in this entire project and how to solved them.

Mohil027 commented 3 years ago

Challenges : 1) For our project we found a dataset prepared by the Stanford University AI Lab consisting of the images for the cars, but the other important details of the cars except it’s names were not available anywhere. The cars in this database were all manufactured during 2012 or before that period, thus, it became very difficult to find the details of the cars. Solution 1 : The best possible option to make an accurate database was none other than doing the manual search. So we manually collected the data from official websites for all the features of the cars. Also, there were many issues while running queries which required frequent changes in the database in order to solve those issues in a pragmatic approach.

2) For the image dataset, all the car images were required in a specific pixel dimensions format i.e. (800 x 305). But while searching images, none of the images were specifically found in that dimensions. Solution : All the images had to be resized and formatted according to the required dimensions format.

khyatibhuva commented 3 years ago

Great Job!