skills.rest
tuliopc23
tuliopc23COMMUNITY
Explore all skills by this author →
Website𝕏@tuliopinheiro_GitHub

axiom-vision

Implement computer vision tasks with Apple's Vision framework and VisionKit.

Updated Dec 3, 2025
Search Tags:#ocr#computer vision#object detection#segmentation#image analysis#pose estimation
One-click install
npx skills add https://github.com/tuliopc23/flying-dutchman-app --skill axiom-vision
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: axiom-vision
Source: https://github.com/tuliopc23/flying-dutchman-app/tree/main/.claude/skills/axiom-vision
Command: npx skills add https://github.com/tuliopc23/flying-dutchman-app --skill axiom-vision

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill empowers developers to integrate advanced computer vision capabilities directly into their applications, simplifying complex tasks like object recognition, segmentation, and text extraction.

Core Features & Use Cases

  • Subject Segmentation: Isolate subjects from backgrounds for effects like background replacement or virtual try-on.
  • Object & Text Recognition: Detect and recognize text, barcodes, and QR codes within images and video streams.
  • Pose Estimation: Track human body and hand poses for gesture recognition and motion analysis.
  • Document Scanning: Automatically detect, scan, and extract data from documents.
  • Use Case: Integrate real-time barcode scanning into an inventory management app or use subject lifting to create dynamic photo filters.

Quick Start

Use the axiom-vision skill to isolate a subject from the background in the provided image.

Frequently Asked Questions about axiom-vision

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I implement subject segmentation to isolate an image background using the Apple Vision framework?▼

Subject segmentation isolates subjects from backgrounds using Apple's Vision framework, enabling effects like background replacement. This Skill provides implementation patterns for extracting subjects and integrating results with CoreImage for compositing.

Can I perform real-time barcode and text recognition in a camera stream with VisionKit?▼

Real-time barcode and text recognition is supported through VisionKit camera analysis. This Skill offers solutions for detecting and extracting text, barcodes, and QR codes within live video streams for immediate processing.

What's the best way to track hand and body poses for gesture recognition in iOS?▼

Tracking hand and body poses for gesture recognition is achieved using Apple's Vision framework pose estimation. This Skill provides comprehensive guidance for detecting human body and hand movements to analyze motion.

Does the Vision framework support automatic document scanning and data extraction?▼

Automatic document scanning and data extraction are supported by VisionKit. This Skill covers how to detect, scan, and extract data from documents programmatically, streamlining the intake of physical records.

How do I composite isolated subjects with CoreImage after performing segmentation?▼

Compositing isolated subjects with CoreImage involves passing Vision framework segmentation results to CoreImage filters. This Skill details how to programmatically access vision results and integrate them for background replacement and dynamic filters.

Related Skills

Explore More Software Engineering Skills→
tondevreltondevrel
19

opencv

Process images and video with feature detection and object recognition.

Community
Intermediate
adiytharpansaadiytharpansa

barcode-scanner

Scan barcode images to retrieve product details and pricing information.

Community
Intermediate
onymchatonymchat

vision-framework

Build iOS apps with Vision, VisionKit, and Core ML for OCR, face detection, barcode scanning, segmentation, and tracking.

Official
Advanced
tuliopc23tuliopc23

axiom-vision-ref

Reference Apple's Vision framework APIs for subject segmentation, pose detection, face analysis, text recognition, and barcode detection.

Community
Intermediate