The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
Local-first OCR pipeline that converts scanned PDFs and images into validated Excel, CSV, and JSON. Built with Python, Tesseract, OpenCV, FastAPI, and automated quality checks. Includes confidence scores, review flags, audit logs, and a 100% field-accuracy result on the synthetic validation dataset.
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Challenges
View all
Related posts
Interactive 3D Product Visualization Gallery -
It shows 360° spaces, 3D product visualization, sustainability concepts, and product storytelling.
This is a great example of letting the environment carry the product story—the 360° spaces, gallery framing, and sustainability cues feel much more immersive than a standard catalog grid. The AptiCraft presentation also makes the transition from exploration to product detail feel especially natural.
Hi, I'm Rohan — a data analyst who turns messy data into clean dashboards and clear business insights 📊
Recently completed a 20-day end-to-end analytics pipeline (Excel → SQL → Python → Power BI) for a fictional retail chain — 4 interactive dashboards tracking sales, operations, HR & customer intelligence, with ₹1.79M in revenue analyzed across 200 orders.
I also work on HR analytics, real estate dashboards, and retail sales analysis — check out my full portfolio below 👇
Open to data cleaning, dashboard building, and SQL/analytics projects of any size. Let's turn your data into decisions!
#DataAnalytics #PowerBI #SQL #Excel #Python
I built ProofFace a visual provenance & content verification engine in Rust
I have been building ProofFace an end-to-end visual provenance and content verification engine built in Rust.
The idea is simple:
Finding an image online doesn’t prove that it’s authentic, original, or unchanged.
So I built a verification pipeline that goes from:
📸 Image input
→ 🧠 Neural face detection
→ 🔎 Web visual discovery
→ 🧬 Biometric similarity
→ 🔐 Deterministic SHA-256 fingerprinting
→ ⛓️ Polygon Amoy blockchain proof
→ ✅ Verification result
Some of the things I worked on:
• ONNX-based face detection
• 128-dimensional biometric embeddings
• Presentation attack detection
• Parallel visual candidate evaluation
• Cosine similarity matching
• RFC 8785 JSON canonicalization
• SHA-256 content fingerprinting
• Polygon smart-contract integration
• Automated unit & integration testing
The project currently has 30 passing tests.
What I enjoyed most was bringing several different areas together computer vision, Rust systems programming, cryptography, and blockchain into one reproducible verification workflow.
Would love to hear what you’d improve or add to a system like this.
