VisionLab
- 7 Devlogs
- 22 Total hours
VisionLab is a computer -vision experimental project designed to explore how images is processed in real time.
Ship #2
💀 Cursed
.png)
.png)
VisionLab
Hey Guyssss!!! New update is here!!
I have changed its theme and fonts. Currently it is not pushed to github but soon I will push after polishing .
Then I will work on object detection. I have dropped gesture detection for now and working on object detection after that I will work on gesture detection.
.png)
Clearing Up What VisionLab Is
A few reviews made me realize I didn’t explain VisionLab’s purpose clearly enough.
Some people saw VisionLab as a PC version of Snapchat because it currently has camera filters. That’s not what I’m building.
VisionLab is the starting point of a larger computer-vision project. The current version is intentionally simple: real time camera input, image processing, and a GUI. The goal is to build foundation before moving towards things like hand detection, gesture recognition.
Some people also pointed out areas I can improve, including performance, code structure, and executable size. Those are valid areas I need to improve as the project grows.
So no, VisionLab isn’t meant to be a “fancy camera app.” v1.2.2 is just the beginning.
I’m really happy to announce that VisionLab finally has its own logo!
Next → Hand Detection & Gesture Recognition 🖐️
This project was vetted by Shipwrights and is now up for voting. You can ship again after making more updates.
Feedback
Hey aarav_shrivastava,
Awesome project! I'd love to see what you make in the future!
For any other questions, DM @sl4shed or create a ticket in Slack—#ask-the-shipwrights.
Shipwright walkthrough
.png)
This needs changes before we can consider it shipped. Review the Shipwright feedback, make updates, then ship again.
Feedback
Hello,
Your README appears to be AI-generated, please rewrite it by hand,
If you have any questions, DM @kaboom or create a ticket in #ask-the-shipwrights.
Shipwright walkthrough
Ship #1
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 🖐️
.png)
.png)
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.
.png)
.png)