Printing-defect inspection reproducibility package (YOLO-World + CLIP + ESN)

Read full text
Authors: Qianzheng Wang
Cited by: 0

Abstract

This record contains the reproducibility package for the manuscript “Similarity Detection of Light Industry Printing Images by Integrating Object Detection and Feature Enhancement”. It includes the source code, configuration files, and evaluation scripts for the YOLO-World + CLIP + Enhanced Siamese Network (ESN) pipeline. The full industrial dataset is not publicly distributable; a de-identified subset is released separately via the project repository/release as described in the manuscript.

Fields of Study & Subjects

Industrial Vision Systems and Defect Detection Advanced Neural Network Applications Advanced Image and Video Retrieval Techniques

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
15 January 2026