All Projects
Computer VisionYOLOv8OCRSocial Media

Popup Detector

AI Social Media Popup Classification System

Computer vision pipeline that detects login/signup popup modals in Facebook and Instagram screenshots. Combines YOLOv8 for spatial detection (finding blocking modal dialogs, dark overlays) with EasyOCR for text verification — correctly ignoring persistent nav-bar login buttons that would fool OCR-only approaches. Achieves 90–95% accuracy.

Type
AI / ML Platform
Category
AI & Machine Learning
Year
2025
Stack
Python · YOLOv8
Popup Detector
At a Glance
90-95%
Accuracy
YOLOv8
Object detection
EasyOCR
Text verification
YES/NO
Per-screenshot output
What's Built

Key features & capabilities.

01

YOLOv8 spatial detection — understands where on screen elements appear, not just what text says

02

Dual-verification: YOLO detects modal region + EasyOCR confirms popup keywords

03

Correctly ignores persistent Facebook/Instagram nav-bar login buttons (false positive prevention)

04

4-notebook training pipeline: augmentation → dataset split → YOLO training → evaluation

05

Streamlit UI: upload Excel with screenshot URLs → download annotated results

06

CLI alternative: python run_detection.py --input file.xlsx --output results.xlsx

Want something like this?

We build full products — from idea to deployment. Let's talk.

Ready to build?

Ready to build what's next?

Tell us about your product. We'll come back with a plan, a team and a timeline.