Feature similarity measurement of cross-age face images based on a deep learning algorithm

Ge, Dong Yuan; Yao, Xiang; Xiang, Wen jiang; Liu, En chen; Xu, Zhi bin

doi:10.1504/ijbm.2021.114653

Cited by 1 publication

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the healthy class, nine images were erroneously detected as fan faults, and in the bearing fault class, two images were mistakenly classified as coil faults. The above issue might be a ributed to deviations in the viewing angle during detection and the presence of similar RGB colors in the images, resulting in a high degree of feature similarity between individual fault-type data [50]. The comparative experiments clearly demonstrate the importance of temperature-based normalization, as it enhances the distinctiveness of the data features.…”

Section: Validation Of the Detection Systemmentioning

confidence: 93%

A Novel Electric Motor Fault Diagnosis by Using a Convolutional Neural Network, Normalized Thermal Images and Few-Shot Learning

Li,

Wong,

Vong

et al. 2023

Electronics

View full text Add to dashboard Cite

Motors constitute one critical part of industrial production and everyday life. The effective, timely and convenient diagnosis of motor faults is constantly required to ensure continuous and reliable operations. Infrared imaging technology, a non-invasive industrial fault diagnosis method, is usually applied to detect the equipment status in extreme environments. However, conventional Infrared thermal images inevitably show a large amount of noise interference, which affects the analysis results. In addition, each motor may only possess a small amount of fault data in practice, as collecting an infinite amount of motor data to train the diagnostic system is impossible. To overcome these problems, a novel automatic fault diagnosis system is proposed in this study. Data features are enhanced by a normalization module based on color bars first, as the same color in various infrared thermal images represent different temperatures. Then, the few-shot learning method is used to diagnose the faults of unseen electric motors. In the few-shot learning method, the minimum dataset size required to expand system universality is fifteen pieces, effectively solving the universality problem of artificial-to-natural data migration. The method saves a large amount of training data resources and the experimental training data collection. The accuracy of the fault diagnosis system achieved 98.9% on similar motor datasets and 91.8% on the dataset of motors that varied a lot from the training motor, which proves the high reliability and universality of the system.

show abstract

Section: Validation Of the Detection Systemmentioning

confidence: 93%