Back to Projects

Distributed OCR System

Academic Project • 2025

C++gRPCOpenCVTesseractDistributed SystemsMultithreading

Overview

A robust distributed system designed for high-throughput Optical Character Recognition (OCR). The system employs a client-server architecture using gRPC for communication. It features fault tolerance mechanisms and utilizes multithreading to parallelize image processing tasks using OpenCV and Tesseract, ensuring efficient text extraction even under heavy loads.

Gallery

Default View

Default View

Batch Processing

Batch Processing

Finished Processing

Finished Processing