DeepRFWT: Approach to mitigate defocus blur effects in DIC-based strain analysis

•DeepRFWT was proposed for defocused speckle image restoration in DIC.•MSFE, MTDED and FDST modules were designed for multi-domain feature processing.•The superiority of DeepRFWT was confirmed by dataset evaluation and mechanical tests. Digital Image Correlation (DIC) technology is confronted with c...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Optics and laser technology Ročník 192; s. 113944
Hlavní autori: Sui, Shunshun, Ma, Yancheng, Wen, Qingfeng, Chen, Yuze, Wang, Yaqi, Zhang, Zhongwei, Dai, Xiangjun
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Elsevier Ltd 01.12.2025
Predmet:
Deep learning
Defocus deblurring
Digital image correlation
Material characterization
Speckle pattern restoration
Deep learning
Material characterization
Digital image correlation
Defocus deblurring
Speckle pattern restoration
ISSN:0030-3992
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:•DeepRFWT was proposed for defocused speckle image restoration in DIC.•MSFE, MTDED and FDST modules were designed for multi-domain feature processing.•The superiority of DeepRFWT was confirmed by dataset evaluation and mechanical tests. Digital Image Correlation (DIC) technology is confronted with considerable challenges due to defocus blur in deformation measurements. Out-of-plane displacement-induced defocus degradation severely compromises DIC accuracy, particularly in microscopic applications requiring sub-pixel precision. To address this issue, DeepRFWT (Deep Residual Fourier-Wavelet Transform), a deep learning-based deblurring algorithm was specifically designed for speckle image restoration. The algorithm integrates three innovative components: 1) the Multi-Scale Feature Enhancement Module (MSFE) for spatial context preservation, 2) the Multi-Transform Domain Encoder-Decoder (MTDED) for dual-channel frequency-spatial domain processing, and 3) the Frequency Domain Spatial Transformer (FDST) for high-frequency information recovery. Comprehensive validations demonstrate superior performance over state-of-the-art methods, achieving 26.70 dB Peak Signal-to-Noise Ratio (PSNR)/0.829 Structural Similarity Index Measure (SSIM) on the Speckle Blur Dataset (SBD), and 26.21 dB PSNR/0.819 SSIM on the Dual-Pixel Defocus Deblurring Dataset (DPDD) with 11.49 M parameters. Micro-displacement experiments confirm exceptional robustness under varying defocus conditions (0.5–1.5 mm), yielding reconstruction errors in the 10−5 to 10−4 mm range. Engineering validation via polyurethane 90A tensile tests show DIC strain measurement relative errors below 1.65 %, verifying practical efficacy.
ISSN:0030-3992
DOI:10.1016/j.optlastec.2025.113944