Hierarchical Image Transformation and Multi-Level Features for Anomaly Defect Detection

Isack Farady, Chia Chen Kuo, Hui Fuang Ng, Chih Yang Lin

Research output: Contribution to journalArticlepeer-review

7 Scopus citations

Abstract

Anomalies are a set of samples that do not follow the normal behavior of the majority of data. In an industrial dataset, anomalies appear in a very small number of samples. Currently, deep learning-based models have achieved important advances in image anomaly detection. However, with general models, real-world application data consisting of non-ideal images, also known as poison images, become a challenge. When the work environment is not conducive to consistently acquiring a good or ideal sample, an additional adaptive learning model is needed. In this work, we design a potential methodology to tackle poison or non-ideal images that commonly appear in industrial production lines by enhancing the existing training data. We propose Hierarchical Image Transformation and Multi-level Features (HIT-MiLF) modules for an anomaly detection network to adapt to perturbances from novelties in testing images. This approach provides a hierarchical process for image transformation during pre-processing and explores the most efficient layer of extracted features from a CNN backbone. The model generates new transformations of training samples that simulate the non-ideal condition and learn the normality in high-dimensional features before applying a Gaussian mixture model to detect the anomalies from new data that it has never seen before. Our experimental results show that hierarchical transformation and multi-level feature exploration improve the baseline performance on industrial metal datasets.

Original languageEnglish
Article number988
JournalSensors (Switzerland)
Volume23
Issue number2
DOIs
StatePublished - Jan 2023

Keywords

  • anomaly detection
  • feature vector
  • image transformation
  • metal defect
  • poison image

Fingerprint

Dive into the research topics of 'Hierarchical Image Transformation and Multi-Level Features for Anomaly Defect Detection'. Together they form a unique fingerprint.

Cite this