| Titre : | Doc-IN: Automated Information Extraction and Insertion into Databases from Invoices |
| Auteurs : | Mohamed Ilyes GUERAOUI, Auteur ; Aymene Mokhtar BOUHELLAL, Auteur ; Mostefai abdelkader, Directeur de thèse |
| Type de document : | texte manuscrit |
| Editeur : | Université Saïda – Dr. Tahar Moulay – Faculté des Mathématiques, de l’Informatique et de Télécommunications, 2024/2025 |
| Format : | 58 ص |
| Accompagnement : | CD |
| Langues: | Anglais |
| Index. décimale : | BUC-M 003718 |
| Catégories : | |
| Résumé : |
Abstract
In today’s data-driven landscape, manual invoice processing remains a time-consuming and error-prone task for many Algerian businesses. This project presents Doc-IN, an AI-powered smart invoice reader designed to automatically extract and structure data from scanned Algerian invoices. By leveraging computer vision and machine learning techniques, Doc-IN significantly reduces human intervention in the invoice management process. The system operates through a lightweight software agent that processes invoice images, detects key fields such as supplier information, dates, product lines, quantities, and tax details, and inserts the structured data into a connected database. Doc-IN has been developed with adaptability in mind, making it compatible with commonly used relational database systems such as MySQL and PostgreSQL, widely adopted across Algerian enterprises. Additionally, Doc-IN is easy to integrate through its SDK with any stock management system, enabling seamless automation across existing workflows. Targeted at retail stores, warehouses, pharmacies, and similar institutions, Doc-IN addresses a critical need for automation in administrative tasks. The project integrates multiple disciplines, including computer vision, backend development, and intelligent system design, under the guidance of an academic supervisor. Ultimately, Doc-IN aims to enhance productivity, improve data accuracy, and mod- ernize invoice handling practices across Algeria. |
Exemplaires
| Code-barres | Cote | Support | Localisation | Section | Disponibilité |
|---|---|---|---|---|---|
| aucun exemplaire |
Documents numériques (1)
BUC-M 003718 Adobe Acrobat PDF |
