CVClassificationSystem
Advanced CV classification and analysis system using multiple OCR extractors, NLP with spaCy/transformers, ML with scikit-learn, and local LLM via Ollama.
100% solo developer, Multi-OCR + ML + LLM pipeline
Quick Stats
Sep 2025
1 / 1
My commits / Total
0
Sole Developer
100%
Sole Developer
Project Metrics
Period
Sep 2025
Role
Sole Developer
Team
1 person
90%+
Text Extraction
85%+
Skill Precision
GDPR
Privacy
$0
API Cost
Tech Stack
Key Features
Multi-Extractor OCR
Tesseract, EasyOCR, Doctr with voting system for best results
NLP Pipeline
spaCy and transformers for named entity recognition
ML Classification
scikit-learn for skill categorization with confidence scoring
LLM Enhancement
Ollama local for contextual analysis with privacy
Geolocation
Automatic location detection from phone numbers
Web Dashboard
Flask UI for visualization and management
My Contribution
Role
Sole Developer
Key Contributions
- Multi-stage pipeline architecture
- 4 OCR extractor implementations
- spaCy and transformers integration
- ML scoring and classification system
- Flask web dashboard
Achievements
90%+
Text Extraction
85%+
Skill Precision
GDPR
Privacy
$0
API Cost