I created a PoC for live descriptions of the surroundings for the blind
Live image description solution using ESP32-CAM + Phone + Server. The difference in cost between products that are developed as accessibility tools compared to consumer products is huge.
Open source
Reactions (1)
Similar products
by description similarity
I taught GPT-OSS-120B to see using Google Lens and OpenCV
news.ycombinator.comI built an MCP server that gives any local LLM real Google search and now vision capabilities - no API keys needed.
Plug and play computer vision tool
demo.lionsight.aiBenchmarking VLMs vs. Traditional OCR
getomni.aiVision models have been gaining popularity as a replacement for traditional OCR.
Eyesite
blog.andykhau.comExperimental website combining computer vision and web design
Labelformat
github.comPython package for converting computer vision labels