Real-time Image Inference Stream Processing with Apache Flink

Entity: Universitat Rovira i Virgili (URV)

Confidenciality: No

Education area(s): Enginyeria de la Seguretat Informàtica i Intel·ligència Artificial

APS: No

Title in different languages: Real-time Image Inference Stream Processing with Apache Flink

Abstract: In the Big Data era, real-time data stream processing is essential across domains like AI. This thesis investigates using Apache Flink for streaming machine learning inference, focusing on image classification. A workflow leveraging Flink's distributed processing includes preprocessing, real-time inference, and postprocessing with deep learning models. Results show the approach’s scalability and efficiency, making it suitable for scenarios demanding low-latency and high-performance data processing.

Subject: Aprenentatge automàtic

Academic year: 2023-2024

Language: en

Work's public defense date: 2024-09-12

Subject areas: Computer engineering

Student: Álvarez-Ruiz, Miquel

Department: Enginyeria Informàtica i Matemàtiques

Creation date in repository: 2025-10-23

Keywords: Machine learning, stream processing

Title in original language: Real-time Image Inference Stream Processing with Apache Flink

Access Rights: info:eu-repo/semantics/openAccess

Project director: Sanchez-Artigas, Marc