I am a Lead AI Scientist working at TECH5 USA. I was previously a graduate student at the Pattern Recognition and Information Processing Lab (PRIP) at Michigan State University, working under the supervision of Prof. Anil K. Jain.

My current research interests include the application of Machine Learning to Computer Vision and Biometrics.

Skills

Machine Learning
Python
Tensorflow
PyTorch
C++

Vishesh Mistry


vsm2209@gmail.com

Michigan State University, United States


MS in Computer Science

Session: 2019-2021

Guide: Prof. Anil K. Jain

CGPA: 3.90 / 4.00

IIT Jodhpur, India


Bachelor of Technology in Computer Science and Engineering

Session: 2015-2019

CGPA: 8.99 / 10.00 (Gold Medalist)

Atmiya Vidya Mandir, India


AISSCE (CBSE)

Session: 2014-2015

Percentage: 95.6%

Atmiya Vidya Mandir, India


AISSE (CBSE)

Session: 2012-2013

CGPA: 10.00 (On the Scale of 10.00)

T5 BTP - Privacy Preserving Biometric Template Protection

TECH5, USA

  • Designing and developing an AI-powered privacy-preserving biometric template protection scheme in compliance with ISO 30136
  • Implementing a novel multi-layer solution that projects biometric templates to a protected space while practically reducing false accepts to zero

T5 AirSnap Face - Contactless Capture for Face

TECH5, USA

  • Extended T5 AirSnapFace, contactless face capture technology using smartphones and browsers, by developing and implementing algorithms for ICAO and ISO 39794-5 compliance
  • Improved the then implementation by making capture faster, fluid, and robust across multiple devices and operating systems
  • Played an integral role in deploying the technology in the national digital ID of Kenya (>30M identities), Digital Passenger Declaration (DPD) platform of Australia, and MTN (Africa’s largest mobile network operator)

T5 AirSnap Finger - Contactless Capture for Finger

TECH5, USA

  • Led the research behind contactless finger capture technology using smartphones for capturing accurate ridge lines and finger resolution
  • Developed and deployed a proprietary contactless finger presentation attack detection solution conforming to ISO 30107-3; won the 2023 LivDet Noncontact Fingerprint competition
  • The solutions were successfully deployed in the national digital ID of Kenya (>30M identities) and MTN (Africa’s largest mobile network operator)

Towards 100 Million Synthetic Fingerprints

PRIP Lab, Michigan State University, USA

  • Implemented an identity loss while training the I-WGAN which guides the generator to synthesize a diverse set of rolled and plain synthetic fingerprints corresponding to distinct identities
  • Synthesized fingerprints are closer to real fingerprints in terms of (i) fingerprint quality and (ii) fingerprint uniqueness

T5 Digital ID - Decentralized Verifiable Credential

TECH5, USA

  • Leading and managing the design and research behind the T5 Digital ID, a secure decentralized offline verifiable credential in the form of a proprietary two-dimensional high-density cryptograph
  • Optimized the T5 Face SDK to facilitate the use of 136 bytes lightweight face templates for real-time verification on smartphones
  • The solution is deployed in Columbia’s military to facilitate biometrics-powered gun ownership, and in DRC for their student and foreigner ID cards

Remote Medical Blood Collector and Injector - PreciHealth

TECH5, USA

  • Developed a robust set of AI tools to facilitate users for using a remote medical blood collector and injector through any device with an integrated camera system
  • Led research activities involving data collection, architecture analysis, model training/testing, and deployment for different modules in the pipeline
  • The end-to-end solution provides real-time detection and tracking of the custom devices along with live feedback

Adversarial Fingerprints Synthesis

PRIP Lab, Michigan State University, USA

  • Developed a black-box adversarial fingerprints synthesis method that automatically generates adversarial fingerprints capable of evading model-based and learning-based fingerprint matchers while preserving fingerprint attributes
  • The proposed method dropped the TAR of three fingerprint matchers on three datasets from 94.15% to as low as 5.52% (using Innovatrics SDK on FVC 2004 DB1-A at 0.01% FAR), outperforming other white-box state-of-the-art adversarial attack methods
  • The proposed method outperforms other white-box state-of-the-art adversarial attack methods while preserving fingerprint attributes

Contact Lens Detection and Classification

IIT Mandi, India

  • Used Keras to develop a hierarchically tuned two-model deep convolutional neural network for detection and classification of contact lens from iris images, outperforming the then existing state-of-the-art techniques
  • The novel implementation performed better or at par with existing state-of-the-art techniques on intra-sensor, inter-sensor, and multi-sensor iris datasets

AdvBiom: Adversarial Attacks on Biometric Matchers

Debayan Deb, Vishesh Mistry, Rahul Parthe

Springer Face Recognition Across the Imaging Spectrum (FRAIS) 2024, May 2024

Springer DOI: 10.1007/978-981-97-2059-0_6

System and Method for Decentralized Digital Identity Verification

US Patent No. 18/658,621 (Pending), May 2024

System and Method for AI-based Digital Identity Verification Field of Disclosure

US Patent No. 18/595,756 (Pending), May 2024

Contactless Fingerprint Capture using Artificial Intelligence and Image Processing on Integrated Camera Systems

Rahul Parthe, Vishesh Mistry, Debayan Deb

US Patent No. 17/967563, Oct 2022

Fingerprint Synthesis: Search with 100 Million Prints

Vishesh Mistry, Joshua J Engelsma, Anil K Jain

IEEE International Joint Conference on Biometrics (IJCB), 2020

IEEE Xplore DOI: 10.1109/IJCB48548.2020.9304885

BRIDGE: Building Plan Repository for Image Description Generation, and Evaluation

Shreya Goyal, Vishesh Mistry, Chiranjoy Chattopadhyay, Gaurav Bhatnagar

IEEE International Conference on Document Analysis and Recognition (ICDAR), 2019

IEEE Xplore DOI: 10.1109/ICDAR.2019.00174

GHCLNet: A Generalized Hierarchically tuned Contact Lens detection Network

Avantika Singh, Vishesh Mistry, Dhananjay Yadav, Aditya Nigam

IEEE Conference on Identity, Security and Behavior Analysis (ISBA), 2018

IEEE Xplore DOI: 10.1109/ISBA.2018.8311471

Table-Tennis

I am an avid table-tennis player and have represented my college and school at various national-level tournaments

Secured 3rd position at the Inter-IIT Sports Meet 2016

iOS App Development

I have tried my hands at developing a few apps on the iOS platform using Swift

The most recent one was developed during Microsoft Code.Fun.Do Hackathon (2018), which checked if a contact in any user’s contact list had updated any of his/her data and automatically merged the update in the user's device