All classes Deepfake Detection Vision Transformer Syllabus · Episode 2 of 6

Class Deepfake Detection Vision Transformer #2: Face Extraction & Alignment with YuNet Detector (OpenCV)

0 views

Face detection and alignment tutorial with OpenCV YuNet: face boxes, eye-nose-mouth landmarks, affine rotation, and testing on photos with multiple faces. Episode 2 of the Deepfake Vision Transformer Detection series.

Software: Deep Learning (PyTorch Vision Transformer)
Level: Intermediate
Duration: ± 10 min
Series total: 1 h 11 min · 6 videos
Published: October 24, 2026

Episode 2 of 6 · view syllabus

Subscribe ▶ Watch the video lesson0 plays

Checking access...

Want to go deeper?

Join one of our courses or ask us directly on WhatsApp.

View the full 6-episode syllabus View Deepfake Detection Courses Ask on WhatsApp

Recommended classes for you

Picked from the software, topic, and level of “Class Deepfake Detection Vision Transformer #2: Face Extraction & Alignment with YuNet Detector (OpenCV)”.

6 episodesFree preview

Python · Intermediate–Advanced

Occlusion Robust Face Recognition

6 video lessons with PDF guides, 1 h 26 min in total. Starts with: LFW Face Dataset & Creating Synthetic Occlusion (Mask, Sunglasses, Hand).

1 h 26 min 0 0

View class

Deep Learning CNN-LSTM Pneumonia Detection

6 episodesFree preview

Python · Intermediate–Advanced

Deep Learning CNN-LSTM Pneumonia Detection

6 video lessons with PDF guides, 57 min in total. Starts with: Chest X-ray Dataset: Loading, Exploration & Data Splitting.

57 min 22 0

View class

6 episodesFree preview

Python · Intermediate–Advanced

Transfer Learning for Leaf Disease

6 video lessons with PDF guides, 1 h 5 min in total. Starts with: PlantVillage Dataset: Folder Structure, Class Distribution & Data Split.

1 h 5 min 9 0

View class

50 episodesFree preview

Agentic AI · Beginner–Intermediate

Agentic AI Without Coding

50 video lessons with PDF guides, 14 h 29 min in total. Starts with: Chatbots, Automation, and AI Agents: What's the Difference?.

14 h 29 min 66 0

View class

100 episodesFree preview

Claude · Beginner–Advanced

Claude from Zero to Expert

100 video lessons with PDF guides, 15 h 1 min in total. Starts with: What Claude Is and How It Differs from ChatGPT and Gemini.

15 h 1 min 62 0

View class

6 episodesFree preview

Python · Intermediate–Advanced

Brain Tumor Segmentation with U-Net

6 video lessons with PDF guides, 1 h 10 min in total. Starts with: Brain MRI Dataset & Tumor Mask: Loading, Visualization & Patient-wise Splitting.

1 h 10 min 28 0

View class

ANFIS Metaheuristics Time Series Forecasting

6 episodesFree preview

Python · Intermediate–Advanced

ANFIS Metaheuristics Time Series Forecasting

6 video lessons with PDF guides, 59 min in total. Starts with: Non-Linear Time Series: Dataset, Stationarity, and Patterns.

59 min 13 0

View class

NSGA-II MOPSO Hybrid Multi-Objective Optimization

6 episodesFree preview

Python · Intermediate–Advanced

NSGA-II MOPSO Hybrid Multi-Objective Optimization

6 video lessons with PDF guides, 59 min in total. Starts with: Multi-Objective Optimization: Pareto Front, Dominance, and Test Functions ZDT/DTLZ.

59 min 9 0

View class

Need more than a video?

Other ways we can help with Python.

Learn with a mentor

Scheduled AI & Machine Learning courses with live guidance and a certificate.

Course

Multi-Objective Optimization Course: NSGA-II, MOPSO & Hybrid Algorithms (Python)

Course

ECG Arrhythmia Classification Course with Wavelet & Deep Learning (PyTorch)

Course

ANFIS + PSO/GA Course for Non-Linear Time Series Forecasting (Python)

See all in AI & Machine Learning →

Have it built for you

No time to learn Python? Our team can do the project for you.

Service

Python Machine Learning — Prediction Models, Customer Segmentation, Fraud Detection & AI Apps

Service

AI Image Creation with Stable Diffusion — Unlimited Custom Visual Production

★ 4.9

Service

AI Image & Video Creation with Leonardo AI — All-in-One Visuals for Business

★ 4.9

See all in AI & Machine Learning →

Get notified about new Python classes

At most one email a week. Unfollow anytime with one click.

Transcript

The full narration of this video. The current sentence is highlighted while the video plays; click any sentence to jump there.

Show transcript

Introduction

Here is the final result, a photo containing four tilted faces in different directions. The detector unit finds everything, complete with eye, nose, and mouth points. Then each face is rotated and cropped to be upright and neat. This is the first stage of every deepfake detection system. Let's get started. Hello, welcome to episode two of the deepfake detection series based on Vision Transformer. In real cases, photos or videos contain people, backgrounds, and other objects. Deepfake detectors work on faces, so the first step is to find faces. Then align them so that the position of the eyes and mouth is consistent. In videos, this step is performed for each frame. We use UNED, a lightweight built-in face detector from OpenCV. The UNED model is already in the model folder, its size is only 230 kilobytes.

Step 1: YuNet Face Detector

Create a file named face_detection.py The detection function creates a face detector with the appropriate size and confidence threshold of 0.6. Each detected face is returned as 15 numbers. 4 numbers for the face box, 10 numbers for 5 landmark points, which are 2 eyes, nose, and 2 corners of the mouth, along with the confidence score. Next, the alignment function.

Step 2: Alignment based on eyes

From the 2 eye points, we calculate the angle of tilt using the arctangent N, and the inter-eye distance to determine the scale. The affine rotation matrix rotates the face so that both eyes are horizontally aligned, enlarges or reduces it so that the eye distance is always the same, and then places the center of the eye at a fixed position. The result is that each face has a uniform position.

Step 3: Creating a test group image

Now create a file named face_detection_test.py. To test it, we create a group photo, 4 faces from the dataset are randomly rotated up to 25 degrees, and placed in different positions on the gray canvas. Then we detect, green bounding boxes and red landmark points, and display the aligned face results for each face.

Step 4: Detection & Alignment Results

Run. The four faces are detected with scores around 0.93 to 0.94. In the top image, you can see the boxes and five landmark points on each face, and the bottom row shows the four faces that are upright and uniform after alignment. At the end, we test on 240 dataset samples, all of them are detected.

Step 5: Alignment and Deepfake Trace

One important note for deepfake detection. Alignment rotates and resizes the image, and this process smooths out the high-frequency traces we saw in the previous episode. Our dataset is already aligned faces with original resolution, so for training we use it directly, while our detector unit is used to find faces in free photos, including in the web application at the end of the series.

Done!

Done. We have already used the detector unit to find faces and five landmarks, aligning faces based on eye position, and tested on photos containing several tilted faces. In the next episode, we enter the core of the series, understanding Vision Transformer, Starting from pack embedding, position tokens, up to self-attention. Currently working on a thesis, dissertation, or AI research in the field of deepfake detection and image forensics? Cerdas Inovasi Digital helps with deep learning implementation, from face detection, Vision Transformer, comparison with CNN, compression resilience testing, up to attention maps and web application, as well as opening deep learning courses with Pythor. Want to master the entire series? From face datasets up to deepfake checker applications? All 6 episodes, complete with step-by-step PDF guides and source code, are available for premium tutorial subscribers. Subscribe starting at Rp69.000 per month, save 28% with the 12-month package, or one-time payment of Rp999.000 for lifetime access. Want just one class? Buy single classes with lifetime access. Subscribe now on the premium page cerdasinovasidigital.com Contact our WhatsApp, or visit cerdasinovasidigital.com Thank you for watching, see you in the next episode. Thank you for watching,

Ask the class material

Type a question or keyword; we find the part of this episode that explains it and jump the video there.

My notes

Notes are saved with the current video time and are only visible to you.

Questions & answers

Stuck on a step? Ask here; the instructor and other learners can answer.

No questions yet.

Your instructor

Cerdas Inovasi Digital Team

Software developers, BIM & 3D engineers, and AI practitioners

53 video classes1,296 episodes

We build software, BIM models, games and AI automations for clients every day, and turn that hands-on work into step-by-step classes: every step is shown on screen and comes with a PDF guide you can keep.

See our clients →

Memuat

Recommended classes for you

Need more than a video?

Transcript

0:03Introduction

1:02Step 1: YuNet Face Detector

2:11Step 2: Alignment based on eyes

3:30Step 3: Creating a test group image

6:11Step 4: Detection & Alignment Results

8:04Step 5: Alignment and Deepfake Trace

8:29Done!

Ask the class material

My notes

Questions & answers

Your instructor

Recommended classes for you

Need more than a video?

Transcript

0:03Introduction

1:02Step 1: YuNet Face Detector

2:11Step 2: Alignment based on eyes

3:30Step 3: Creating a test group image

6:11Step 4: Detection & Alignment Results

8:04Step 5: Alignment and Deepfake Trace

8:29Done!

Ask the class material

My notes

Questions & answers

Your instructor

Introduction

Step 1: YuNet Face Detector

Step 2: Alignment based on eyes

Step 3: Creating a test group image

Step 4: Detection & Alignment Results

Step 5: Alignment and Deepfake Trace

Done!

Introduction

Step 1: YuNet Face Detector

Step 2: Alignment based on eyes

Step 3: Creating a test group image

Step 4: Detection & Alignment Results

Step 5: Alignment and Deepfake Trace

Done!