We propose a text-guided variational image generation method to address the challenge of getting clean data for anomaly detection in industrial manufacturing. Our method utilizes text information about the target object, learned from extensive text library documents, to generate non-defective data images resembling the input image. The proposed framework ensures that the generated non-defective images align with anticipated distributions derived from textual and image-based knowledge, ensuring stability and generality. Experimental results demonstrate the effectiveness of our approach, surpassing previous methods even with limited non-defective data. Our approach is validated through generalization tests across four baseline models and three distinct datasets. We present an additional analysis to enhance the effectiveness of anomaly detection models by utilizing the generated images.

Surface anomaly detection plays an important quality control role in many manufacturing industries to reduce scrap production. Machine-based visual inspections have been utilized in recent years to conduct this task instead of human experts. In particular, deep learning Convolutional Neural Networks (CNNs) have been at the forefront of these image processing-based solutions due to their predictive accuracy and efficiency. Training a CNN on a classification objective requires a sufficiently large amount of defective data, which is often not available. In this paper, we address that challenge by training the CNN on surface texture patches with a distance-based anomaly detection objective instead. A deep residual-based triplet network model is utilized, and defective training samples are synthesized exclusively from non-defective samples via random erasing techniques to directly learn a similarity metric between the same-class samples and out-of-class samples. Evaluation results demonstrate the approach's strength in detecting different types of anomalies, such as bent, broken, or cracked surfaces, for known surfaces that are part of the training data and unseen novel surfaces.