Real-time Image Inference Stream Processing with Apache Flink

Identifier:  TFM:2104

Handle: https://hdl.handle.net/20.500.11797/TFM2104

Authors:  Álvarez-Ruiz, Miquel

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.