With countless individuals, especially children, going missing every day in India, innovative solutions are vital. In this post, we’ll explore a groundbreaking AI project designed to assist authorities in locating missing persons swiftly. This guide will help you set it up, troubleshoot any issues, and understand the project’s working.

News Articles

• Article 1
• Article 2

Objective

The objective of this project is to empower the police and related authorities to track down missing persons more efficiently. Traditional investigative methods can be slow and sometimes ineffective, especially if the missing individual has moved elsewhere. Instead of just relying on conventional methods, this project leverages AI to analyze CCTV footage and other evidence to enhance the chances of finding them.

Solution (Project Implementation)

1. Registering New Cases

The first step involves registering a new case. The GUI application utilizes PyQT5, allowing you to gather and store vital information in a Postgres database.

![New Case Window](resources/new_case.PNG)

2. User Image Submissions

Next, the project relies on common citizens, who can anonymously submit pictures of individuals they suspect are lost. This anonymity helps protect users from backlash or trouble.

![Mobile Application](resources/mobile_application.PNG)

3. Matching Cases

The final step in the process involves matching submitted images using a KNN Algorithm, comparing user-submitted images with registered cases to find potential matches.

![Main Application](resources/app_window.PNG)

How to Run This Project

1. With Docker (Easy)

• Ensure you have Docker and Docker Compose installed.
• Clone the repository:

$ git clone https://github.com/gaganmanku96/Finding-missing-person-using-AI

• Navigate and build:

$ cd Finding-missing-person-using-AI
$ docker-compose up --build
$ cd app
$ pip install -r requirements.txt --no-cache-dir
$ python login_window.py

• Log in with admin/admin credentials.

2. Without Docker (Intermediate)

• Set up and configure the Postgres Database as outlined.
• Install dependencies to run each service similarly as with Docker.
• Log in using the credentials mentioned above and proceed with image submission.

Troubleshooting

If you encounter issues during installation or running the program, consider the following:

• Check if all dependencies are properly installed and compatible versions are used.
• Ensure the database service is running and correctly configured in config.env.
• If using a non-conda environment, you might face issues with the dlib library; verify your installations.

For more insights, updates, or to collaborate on AI development projects, stay connected with fxis.ai.

What is Left?

• [x] Implement Login (Authentication)
• [x] Submit new cases
• [x] Develop Mobile Application for user photos submission
• [ ] View submitted cases
• [ ] View confirmed cases
• [ ] Add unit tests

Developer

Reach out to Gagandeep Singh for any queries regarding this project.

Vote of Thanks

Special thanks to Davis King for creating dlib and providing the trained facial detection and encoding models that are crucial for this project’s success.

At fxis.ai, we believe that such advancements are crucial for the future of AI, as they enable more comprehensive and effective solutions. Our team is continually exploring new methodologies to push the envelope in artificial intelligence, ensuring that our clients benefit from the latest technological innovations.