AIST, one of Japan’s largest research institutes, invented the feature extraction method combining
“High-order Local Auto-Correlation (HLAC)” and multivariate data analysis.
Adacotech has implemented this method into its original anomaly detection system and is applying it to various fields.
Models can be trained with much less anomaly data compared to deep-learning methods using autoencoder.
High speed processing is available on a normal PC due to simplified calculation.
Features are extracted in multiple steps focusing on geometric aspects making it is easy to explain.
HLAC is a feature extraction method used for the analysis and recognition of images, etc. It is versatile, high-speed, and has excellent recognition accuracy.
Since it can be calculated by product-sum operations, the object can be recognized instantly using a normal PC.
In addition, since it is position invariant (does not depend on the position of the object), segmentation is not required (segmentation free).
Furthermore, it has characteristics preferable for image recognition such as additivity
(if there are two objects in an image, the sum of the respective features result in the feature of the whole image).
After extracting the HLAC features of the data to be analyzed (image, video, sound, sensor data, etc.),
the range (subspace) of data that is considered “normal” is determined by principal component analysis,
and the distance of deviation from the subspace is determined as abnormal value.
Please refer to the below link for more information.
Nobuyuki Otsu “ARGUS: Adaptive Recognition for General Use System”
