identimood / littleantispoof

A multimodal face liveness detection module that can be used in the context of face anti-spoofing

IdentiMood

IdentiMood is an authentication system based on face verification and mood recognition, which has been developed as final project for the Biometric Systems course at Sapienza University of Rome, held by Prof. Maria De Marsico (2021-22).

• Project report
• Project presentation

How it works

Enrollment

Verification

Use case example

Running example

System design

Evaluation

The evaluation can be reproduced by executing the scripts in the benchmarks directory.

See the report/presentation for further information and detailed results.

How to run

1. Install the requirements from requirements.txt.
2. Tweak src/config.json as desired.
3. Execute src/enroll.py to perform enrollment.
4. Execute src/main.py to authenticate.

Authors

• Daniele Solombrino
• Davide Quaranta
• Emanuele Volanti

littleantispoof's Issues

Add words distance threshold to tolerate speech recognition errors

Eg. "house" may be recognized as "how's"; "car" as "carl", etc.

Implement some edit distance measure to allow such errors.

Add eye blinking detection

While a video operation is running (gaze, emotion), there should be a background blinking check.

In other words, there should be a certain ratio of blinks while the video window is open (configurable).

Improve prompt texts

Instead of just the plain task name, write something more.

Examples:

• "left" ==> "Look left"
• "happy" ==> "Do an happy face"

Add more sounds

• Startup
• After speech recognition

Make the video windows timed

Instead of having the "Shoot" button, the windows must have a visible timer (e.g. 3 seconds), after which:

• the frame is captured
• a sound is played (to help the user understand that the task is over)

Improve gaze detection

The gaze/blink detection doesn't work so well (e.g. if your eye is still for some time, it "forgets" the gaze and becomes None). Find if it can be tuned, or find another library.

Playsound says that is is relying on another subprocess

Playsound says a thing that is unexpected:

playsound is relying on another python subprocess. Please use `pip install pygobject` if you want playsound to run more **efficiently.**

(also, the installation of pygobject failed on my system, so I cannot see the difference)

Find:

• why it happens
• if it is a problem
• how to solve it

Add support for speech recognition

The system should ask the user to say a certain short phrase, randomly generated from a dictionary.

For this we need:

• Another Tkinter window to guide the task.
• A (short, for now) dictionary of phrases.
• Logic to handle the whole operation.

The window should also be timed, as described in #2

Convert eye blinking ratio check to consider seconds

The following config must be converted to seconds instead of frame ratios.

"blinking": {
        "min_threshold": 0.2,
        "max_threshold": 0.5
    },

Possible strategy:

• the callback function to Window must count the total number of analyzed frames
• you already know the window expiration time
• you calculate how many frame you have in 1 second
• you check whether the number of blinks is in the configured seconds range

Configuration refactoring

• Add Azure region as environment variable
• Flatten the configuration structure