Physical Annotation for Automated Optical Inspection: A Concept for In-Situ, Pointer-Based Training Data Generation

TL;DR

This paper presents a physical annotation system using pointer-based in-situ interaction and projection to generate training data for automated optical inspection, improving accuracy and enabling non-experts to contribute.

Contribution

The paper introduces a novel physical annotation system that captures physical trajectories directly on objects, integrating pointer tracking and projection for efficient data labeling.

Findings

Feasibility of capturing detailed annotation trajectories

Integration with CVAT streamlines ML workflow

Enhanced accuracy with projector-based guidance

Abstract

This paper introduces a novel physical annotation system designed to generate training data for automated optical inspection. The system uses pointer-based in-situ interaction to transfer the valuable expertise of trained inspection personnel directly into a machine learning (ML) training pipeline. Unlike conventional screen-based annotation methods, our system captures physical trajectories and contours directly on the object, providing a more intuitive and efficient way to label data. The core technology uses calibrated, tracked pointers to accurately record user input and transform these spatial interactions into standardised annotation formats that are compatible with open-source annotation software. Additionally, a simple projector-based interface projects visual guidance onto the object to assist users during the annotation process, ensuring greater accuracy and consistency. The proposed concept bridges the gap between human expertise and automated data generation, enabling non-IT experts to contribute to the ML training pipeline and preventing the loss of valuable training samples. Preliminary evaluation results confirm the feasibility of capturing detailed annotation trajectories and demonstrate that integration with CVAT streamlines the workflow for subsequent ML tasks. This paper details the system architecture, calibration procedures and interface design, and discusses its potential contribution to future ML data generation for automated optical inspection.