skills.rest
86maid
86maidCOMMUNITY
Explore all skills by this author →
GitHub

ddddocr

Run OCR, object detection, and slide matching via MCP and REST endpoints.

342|55|Updated May 23, 2023
Search Tags:#ocr#mcp#image-processing#captcha#object-detection#slide-matching
One-click install
npx skills add https://github.com/86maid/ddddocr --skill ddddocr
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ddddocr
Source: https://github.com/86maid/ddddocr/tree/main/.agent/skills/ddddocr
Command: npx skills add https://github.com/86maid/ddddocr --skill ddddocr

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Provides an integrated OCR and image-analysis service capable of reading text from images, locating text regions, and verifying slide positions, enabling automated CAPTCHA solving, document processing, and image verification workflows.

Core Features & Use Cases

  • OCR Recognition: Extracts text from images with optional color filtering and character ranges.
  • Object Detection: Locates text regions and other elements within images.
  • Slide Matching: Determines slide positions within a background image using template matching or difference-based methods.
  • MCP Protocol & REST API: Exposes endpoints for OCR, detection, slide operations, and programmatic control.

Quick Start

Start the service using the provided start script to enable ocr, det, slide, and mcp features.

Frequently Asked Questions about ddddocr

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

FAQPage Schema
How do I extract text from captcha images using an automated service?▼

Automated OCR recognition extracts text from captcha images by sending image data to the /ocr REST endpoint, which supports optional color filtering and character range configurations for accurate text extraction.

Can I locate text regions within an image for document processing?▼

Object detection locates text regions within images by sending image data to the /det REST endpoint, enabling automated document processing and text-region localization workflows.

Does this OCR service support slide matching for captcha verification?▼

Slide matching is supported via /slide-match and /slide-comparison REST endpoints, which determine slide positions within background images using template matching or difference-based methods for automated captcha verification.

Do I need an MCP client to use the OCR and image recognition features?▼

An MCP client is not required; OCR, detection, and slide features are accessible via standard REST endpoints. However, MCP protocol support is available at the /mcp endpoint for programmatic control within MCP-enabled environments.

How to start an OCR server with object detection and slide matching enabled?▼

Start the OCR server with object detection and slide matching enabled by running the provided start script, which activates the ocr, det, slide, and mcp features. Companion scripts in the scripts/ directory enable local testing of these REST endpoints.

What are the limitations of using template matching for slide position verification?▼

Template matching limitations for slide position verification relate to background image complexity; the service offers both template matching and difference-based methods at /slide-match and /slide-comparison endpoints to accommodate different captcha verification scenarios.

Related Skills

Explore More Software Engineering Skills→
Pikapika260214Pikapika260214
349

ppt-to-editable

Convert image-only PPTX, PNG, and screenshot files into editable PowerPoint presentations using OCR.

Community
Advanced
otto-poblyshotto-poblysh

PDF Processing

Extract text and tables from PDFs and fill forms via annotations.

Community
Advanced
anilcan-karaanilcan-kara

fastmcp

Scaffold, validate, and deploy Python MCP servers with FastMCP.

Community
Intermediate
adennngadennng
33

image-review

Extract text descriptions from local images via an external multi-modal service.

Community
Basic