Exploring the Frontiers of Facial Recognition : Applications and Challenges
Within the field of computer vision, facial recognition is an area of research and development which deals with giving machines the ability to recognize and verify human faces in photos, video, or in real-time. Today it's considered to be the most natural of all biometric measurements. And for a good reason – we recognize ourselves not by looking at our fingerprints or irises, for example, but by looking at our faces. Face recognition systems use computer algorithms to pick out specific, distinctive details about a person’s face. These details, such as distance between the eyes or shape of the chin, are then converted into a mathematical representation and compared to data on other faces collected in a face recognition database. These templates are then used to distinguish one person from the other. It is being used today for :
- Surveillance Purposes
- Automated Tracking
- Shopping Stores
- Law Enforcement
- Augmented Reality
And the uses cases are infinite. However, as it is being ubiquitous in the world around us, there are potential challenges that surround us too.
Face recognition systems vary in their ability to identify people under challenging conditions such as poor lighting, low quality image resolution, and suboptimal angle of view (such as in a photograph taken from above looking down on an unknown person).
- Face Recognition data can be prone to error, which can implicate people for crimes they haven’t committed. Hence, there is a major risk of Privacy.
- Facial recognition software is particularly bad at recognizing African Americans and other ethnic minorities, women, and young people, often misidentifying or failing to identify them, disparately impacting certain groups
- Additionally, face recognition has been used to target people engaging in protected speech
- Low Reliability
Outline of the Session
The session will be a mix of theory followed by a couple of demonstrations and interesting activities and questions for the audience which will be presented to them from time to time to encourage brainstorming and idea building This is how the session will be arranged :
- Understanding the Fundamentals of Facial Recognition - How this amazing technology works and the algorithms used here.
- Project Showcase ( A simple Facial Recognition Project using OpenCV and KNN so that the audience is able to visualize the process.)
- Interesting Applications where this technology is being used today and which Companies are the leaders in this field.
- Project Demonstration that anyone can do without writing their own Code.
- Discussing the Pros and the Cons of this Technology
- The Big Picture : Challenges
- Current Scenario : Contributing our bit during the Challenging times of the Pandemic
- Future Aspects and Conclusion
- Inspiration for the Audience to make their own projects + Brainstorming ( Idea Boards)
- Getting the best Resources and Material to get started
- Engaging with the Audience ( Q/A )
Target Audience and Takeaways from the Session
This tutorial is aimed at Beginners to Intermediate learners in the field of Machine Learning and Artificial Intelligence who want to dive deep into this Technology and build sustainable and scalable Facial Recognition Systems. Basic Understanding of Python would be highly appreciated. By the end of this session, the audience will not only be able to visualize how the Facial Recognition Systems work but also will be ignited to create some amazing projects and have a chance to collaborate and interact with the help of activities in the session which will serve as a key takeaway.
Prerequisites for the Session :
- Basic Coding and Understanding of Python Works
- Key Concepts of Machine Learning and Image Processing
Know more about the proposal here
About the Speaker
Muskan Kumar is a goal oriented individual who always strives to work on end to end products to inculcate sustainable and scalable social & technical systems that produce an impact. She is a Computer Science Engineer, ML Enthusiast and a Community Influencer. Currently, she is an incoming Master's Student at Thapar Institute of Engineering and Technology.
She is involved in Research and has interned at the Center for Artificial Intelligence and Robotics, DRDO, Bangalore. Muskan loves teaching as well as learning ML. She is a very active member of the community. So far, I have helped over a 10,000 students to get started with their ML Journey. She is also an avid speaker and have spoken at various colleges as well as virtual meetups. She gets intrigued about technology because of its impact and its power to touch millions live. So far she has worked on end to end projects like Drowsiness Detection for Drivers, Twitter Sentimental Analysis, Facial Recognition Systems powered by Raspberry Pi and various other projects belonging to different domains. Currently, she is pursuing research on TOR Website Fingerprinting. Furthermore, she is an ardent reader and a fervent volunteer at the Samkalp Foundation at Chandigarh which aims to educate the lower sections of the society. Muskan is a strong believer of the saying “We rise by lifting others”.
- Google Explore ML Facilitator.
- Invited to Google Bangalore as a part of Google Explore ML Event.
- Microsoft Student Partner.
- Represented Punjabi University at SAE Supra 2018, which is a national formula one championship for students. Ranked 20 among 200 teams from all across India.
- Invited as a Speaker at GDG Vizag and Tensorflow User Group, Chennai.