Generative AI for Industrial Contour Detection: A Language-Guided Vision System

2025-08-29

AI Summary

Industrial computer vision suffers from insufficient robustness of conventional edge detectors under noise, material variability, and non-ideal imaging conditions. This paper proposes a language-guided generative framework for industrial vision, integrating conditional generative adversarial networks (cGANs) with multimodal vision-language models (GPT-image-1 and Gemini 2.0 Flash) to achieve end-to-end generation and refinement of CAD-level residual contours. We innovatively introduce human-editable standardized prompting and a text-image co-synthesis mechanism, overcoming limitations of handcrafted feature engineering and unimodal modeling. Evaluated on the private FabTrack dataset, our method significantly improves contour fidelity, edge continuity, and geometric alignment accuracy, substantially reducing manual tracing effort. Quantitative and qualitative analyses demonstrate that GPT-image-1 outperforms Gemini 2.0 Flash in structural accuracy and visual quality.

Technology Category

• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Machine Learning: Large Multimodal Models (LMMs)
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

Industrial computer vision systems often struggle with noise, material variability, and uncontrolled imaging conditions, limiting the effectiveness of classical edge detectors and handcrafted pipelines. In this work, we present a language-guided generative vision system for remnant contour detection in manufacturing, designed to achieve CAD-level precision. The system is organized into three stages: data acquisition and preprocessing, contour generation using a conditional GAN, and multimodal contour refinement through vision-language modeling, where standardized prompts are crafted in a human-in-the-loop process and applied through image-text guided synthesis. On proprietary FabTrack datasets, the proposed system improved contour fidelity, enhancing edge continuity and geometric alignment while reducing manual tracing. For the refinement stage, we benchmarked several vision-language models, including Google's Gemini 2.0 Flash, OpenAI's GPT-image-1 integrated within a VLM-guided workflow, and open-source baselines. Under standardized conditions, GPT-image-1 consistently outperformed Gemini 2.0 Flash in both structural accuracy and perceptual quality. These findings demonstrate the promise of VLM-guided generative workflows for advancing industrial computer vision beyond the limitations of classical pipelines.

Problem

• Detecting precise industrial contours under noisy conditions
• Overcoming material variability in manufacturing vision systems
• Achieving CAD-level precision with generative AI workflows

Innovation

• Conditional GAN for contour generation
• Vision-language modeling for refinement
• Human-in-the-loop prompt engineering