VisionLab
- 3 Devlogs
- 14 Total hours
VisionLab is a computer -vision experimental project designed to explore how images is processed in real time.
VisionLab is a computer -vision experimental project designed to explore how images is processed in real time.
VisionLab v1.2.2 — Shipped!
Today I completed the VisionLab GUI and made several improvements to prepare the project for public use.
🎨 Completed the GUI design
🖼️ Added a custom VisionLab favicon
📦 Created a standalone executable build
💾 Added the executable ZIP to the GitHub Releases section
🖥️ Anyone can now download and try VisionLab without installing Python or a compiler
📖 Completed the project README
🚀 VisionLab v1.2.2 is now shipped!
Next up: Hand Detection & Gesture Recognition 🖐️
VisionLab - GUI Progress & Video Frame Styling
Today I made further progress on VisionLab. The Normal, Grayscale, and Edge Detection modes are now working, and the GUI is approximately halfway completed.
One of the main things I worked on today was adding a border around the video frame. This took around 2 hours because I initially didn’t know about QFrame, so I tried several more complicated approaches before finding a simpler solution.
I also added the bottom bar and created the System Info box, which currently displays information about the system and camera status.
Tomorrow, I plan to continue improving the bottom bar and work further on the GUI.
Current progress:
🟢 Normal mode
🟢 Grayscale mode
🟢 Edge Detection mode
🟢 Video frame border
🟢 System Info panel
🟡 GUI approximately 50% complete
🟡 Bottom bar — ongoing
🔴 Gesture detection
VisionLab: Working on the GUI
I’m currently working on the GUI for VisionLab. I’ve already implemented grayscale and edge-detection filters. After finishing the GUI, I’ll add hand-gesture recognition to control the filters.