AI-powered Facial recognitation tool.
FacEAI-PRO
COMPANY
CairoVision
ROLE
UX Designer
EXPERTISE
Figma || Miro
YEAR
2018
ContentIn 2018, the need for advanced investigative tools in law enforcement had grown significantly. Traditional methods of identifying suspects were time-consuming and inefficient, creating an urgent demand for technological solutions that could enhance the speed and accuracy of criminal investigations.
I was part of a groundbreaking project to design FacEAI-PRO, a high-performance, scalable facial recognition and analytics tool. This project aimed to transform the way law enforcement agencies analyze and act on data, enabling them to address critical challenges with greater efficiency.
To comply with confidentiality agreements, I have omitted and obfuscated any sensitive or proprietary information in this case study. All information presented here is based on my personal contributions and does not necessarily reflect the views of the organizations involved.
Introduction
In 2018, the demand for advanced investigative tools in law enforcement surged, driven by the inefficiencies of traditional suspect identification methods. This case study explores the development of FacEAI-PRO, a cutting-edge facial recognition and analytics tool designed to enhance the speed and accuracy of criminal investigations.
Project overview
Outcome
My role
As a UX Designer on the Entomo project, I played a pivotal role in enhancing user experiences and ensuring seamless interaction with the platform. I conducted in-depth user research and heuristic evaluations to uncover key pain points and usability issues. Using insights from user journey mapping, I designed intuitive wireframes and prototypes that addressed specific challenges, focusing on simplicity and efficiency. Collaborating closely with stakeholders and development teams, I ensured the alignment of business goals with user needs. Additionally, I facilitated usability testing sessions and iterated designs based on user feedback to drive continuous improvement.
User Research
Prototyping & Testing
Collaboration
Testing & Iteration:
Research
To enhance Entomo's performance management platform, I conducted comprehensive user research focusing on understanding user behaviors, needs, and pain points. The research methodology included:
User Surveys:
Stakeholder Interviews:
Contextual Inquiries:
Persona Development:
Task Analysis:
Usability Testing:
How we got there
Adaptation: A Flexible Architecture
One of the core principles I focused on during the FacEAI-PRO design process was creating a flexible and adaptable architecture that could be scaled and customized for a variety of law enforcement environments. Recognizing that each department might have different technological infrastructures, I designed a flow that prioritized adaptability and scalability to ensure that the tool could be deployed seamlessly across diverse environments.
Location Confidence Score:
A central concept in the design was the location confidence score, which would help determine the accuracy of the facial recognition system in various conditions. This score would adapt to different environmental factors, such as the quality of the camera, lighting conditions, and the distance between the suspect and the camera. Here's how the flow was structured:
Data Collection:
The system collected facial data from multiple sources, including surveillance cameras, public databases, and even live feeds from officers in the field.
Each image or video input was evaluated based on several variables, such as resolution, angle, and environmental lighting.
Confidence Scoring:
The location confidence score was calculated by the system to assess the reliability of each face match based on the environmental conditions and the quality of the input data.
Dynamic Adjustments:
The architecture was built to be flexible, allowing the system to adjust its processing based on the score. For example, if the confidence score was low due to poor lighting or a low-resolution image, the system would prioritize more intensive algorithms or suggest manual verification by officers.
Real-Time Decision Making:
The flow was designed to ensure real-time processing. Officers could receive immediate feedback on the accuracy of a match, along with suggestions for further action, such as requesting additional footage or verifying the result through secondary sources.
This ensured that the system was always operating at maximum efficiency, providing real-time support without slowing down investigations.
Adaptability:
The flexible architecture of the system meant that as new data sources or surveillance technologies were adopted by law enforcement agencies, the system could easily integrate with these new inputs, adapting to different levels of data quality and infrastructure.
Design System
