VisionCreditScan
Scan Credit Cards using Vision's Rectangle Detection and OCR on the selected region.
Install / Use
/learn @anupamchugh/VisionCreditScanREADME
VisionCreditScan
Scan credit and other buisness cards using rectangle detection, followed by a perspective correction to handle distortion.
Finally, I've allowed the user to select the region of interest through gestures and extract the relevant information using Vision's Text Recognizer.
Doing so, not only makes it a secure way of extracting digits, but also allows us to step away from regular expressions for parsing texts. Regular Expressions are inefficient in scenarios, since there's not gurantee of the number of digits that'll be there on the card. For example AMEX cards don't have 16 digits.
Demo

Article
Related Skills
node-connect
354.3kDiagnose OpenClaw node connection and pairing failures for Android, iOS, and macOS companion apps
frontend-design
112.3kCreate distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
openai-whisper-api
354.3kTranscribe audio via OpenAI Audio Transcriptions API (Whisper).
qqbot-media
354.3kQQBot 富媒体收发能力。使用 <qqmedia> 标签,系统根据文件扩展名自动识别类型(图片/语音/视频/文件)。
