Download as pdf or txt
Download as pdf or txt
You are on page 1of 2

Capstone Title - Face detection and recognition

Domain - Data Science

Problem statement: Interviewer.AI thoroughly analyzes your candidates’ résumés,


putting their skills into assessment tests and pre-screening video interviews. As an
outcome, you get bias-free insights and highlights of the best talent suited for your
company. It allows you to reduce the time spent on pre-interviews and increase your
hiring efficiency and productivity. They want a system where the system detects the
face ID based on the database.

Learning Objectives:
● Demonstrate the ability to make use of openCV library and Haar cascade module
● Demonstrate the ability to implement Image processing techniques techniques

Business Objective:
Integrating a facial recognition attendance system together with a payroll system is a
relatively simple exercise. These systems are modular and highly customisable, which
means that the time-in, time-out, and date formats can be customized to work with
many different systems used in your business, and this allows you to organize data
much easier.

Company Introduction:

Interviewer.ai is an AI-powered video recruitment platform that helps companies


pre-screen candidates at the top of the funnel by grading uploaded resumes, small skill
assessment tests, and recording short video interview responses before scheduling
them for face-to-face interviews. It helps companies to reimagine every stage of the
talent acquisition process - from Screening, to Interviewing and Shortlisting candidates -
digitally and at scale.
Interviewer.ai creates a boundless bridge between employees and employers to match
the best quality professionals with relevant opportunities worldwide.

Project Task 2: Face Alignment

Background Description
In an image, most of the image is non-face region. So it is a better idea to have a simple
method to check if a window is not a face region. If it is not, discard it in a single shot,
and don't process it again. Instead, focus on regions where there can be a face. This
way, we spend more time checking possible face regions.

Task Instructions
Once the coordinates of the faces are obtained, crop the face and make them
translational invariant i.e.scale and rotate the image to ensure similar nature of all facial
images.

Submission Format - Share the .ipynb file with all the details and insights.

Resources - OpenCV: Cascade Classifier

You might also like