You are on page 1of 2

The assignment entails you to develop a simple Web Application, which when given an image,

is able to detect a face (show with a boundary box) and give a result saying whether ​Narendra
Modi​ and/or ​Arvind Kejriwal​ are present in the image or not.

You are not allowed to use any online services and/or APIs for facial recognition but are
supposed to build your own model(s) from scratch. Feel free to use any image processing and
learning techniques/libraries. You have the full liberty to decide on the architecture of the
system.

You are required to curate a data set for your model(s) by using any image search APIs and
would be required to store them in a MongoDB collection. We expect you to split your collected
data set into training and testing sets. Use the training set only, to train your model(s) and then
test the trained model on the testing data set. Make sure, there is no overlap of samples
between the training and the testing data sets.

You would be required to upload your codebase as well as MongoDB collection into a GitHub
repository.

Sample Input and Output have been explained as follows:

Sample Input Sample Output

{
“Face Present”: “No”,
“Narendra Modi”: “No”,
“Arvind Kejriwal”: “No”
}

{
“Face Present”: “Yes”,
“Narendra Modi”: “No”,
“Arvind Kejriwal”: “No”
}
{
“Face Present”: “Yes”,
“Narendra Modi”: “No”,
“Arvind Kejriwal”: “Yes”
}

{
“Face Present”: “Yes”,
“Narendra Modi”: “Yes”,
“Arvind Kejriwal”: “No”
}

{
“Face Present”: “Yes”,
“Narendra Modi”: “Yes”,
“Arvind Kejriwal”: “Yes”
}

You might also like