[1] [1] LI H. Analysis and control of laser weld crack［C］//2020 3rd International Conference on Electron Device and Mechanical Engineering (ICEDME). New York,USA:IEEE, 2020: 192-195.

[2] [2] LI X, XIE J, ZHOU Y. Effects of oxygen contamination in the argon shielding gas in laser welding of commercially pure titanium thin sheet［J］. Journal of Materials Science, 2005, 40(13): 3437-3443.

[3] [3] HARWIG D D, FOUNTAIN C, ITTIWATTANA W, et al. Oxygen equivalent effects on the mechanical properties of titanium welds［J］. Welding Journal Research Supplement, 2000, 79(11): 305s-316s.

[4] [4] FAN L M, GENG N T, YANG L, et al. Progress of anti-oxidation protection technology in titanium alloy welding process［J］. Iron Steel Vanadium Titanium, 2021, 42(6): 43-50(in Chinese).

[5] [5] GUPTA S S, KWON T H, KIM K D. Color based image processing techniques to detect oxide film during welding［C］//2020 International Conference on Electronics, Information, and Communication (ICEIC). New York,USA:IEEE, 2020: 1-4.

[6] [6] HUA S, LI B, SHU L, et al. Defect detection method using laser vision with model-based segmentation for laser brazing welds on car body surface［J］. Measurement, 2021, 178: 109370.

[7] [7] QI J Y, LI J Y, LU Zh Y, et al. Application of improved Otsu algorithm to welding image segmentation［J］. Transaction of the China Welding Institution,2016,37(10):97-100(in Chinese).

[8] [8] MALARVEL M, SETHUMADHAVAN G, BHAGI P C R, et al. An improved version of Otsu’s method for segmentation of weld defects on X-radiography images［J］. Optik, 2017, 142: 109-118.

[9] [9] DAI X L, MAO Y Sh, ZHOU Y Q. Weld segmentation algorithm based on improved watershed［J］. Ship Engineer,2021,43(s1):428-433(in Chinese).

[10] [10] ANAND R S, KUMAR P. Flaw detection in radiographic weldment images using morphological watershed segmentation technique［J］. NDT & E International, 2009, 42(1): 2-8.

[11] [11] RADI D, ABO-ELSOUD M E A, KHALIFA F. Accurate segmentation of weld defects with horizontal shapes［J］. NDT & E International, 2022, 126: 102599.

[12] [12] XU H, YAN Z H, JI B W, et al. Defect detection in welding radiographic images based on semantic segmentation methods［J］. Measurement, 2022, 188: 110569.

[13] [13] GOLODOV V A, MALOSTEVA A A. Approach to weld segmentation and defect classification in radiographic images of pipe welds［J］. NDT & E International, 2022, 127: 102597.

[14] [14] CHANG Y, CHANG D J. Research on solder joint defect recognition algorithm based on improved convolutional neural network［J］. Laser Technology,2020,44(6):779-783.

[15] [15] RONNEBERGER O, FISCHER P, BROX T. U-net: Convolutional networks for biomedical image segmentation［C］//International Conference on Medical Image Computing and Computer-assisted Intervention. Munich, Germany: Springer, 2015: 234-241.

[16] [16] WU L, FU D Ch, CHENG Ch. Multi-attention brain tumor image segmentation algorithm based on Unet［J］. Computer Technology and Development, 2021,31(12):85-91(in Chinese).

[17] [17] SCHLEMPER J, OKTAY O, SCHAAP M, et al. Attention gated networks: Learning to leverage salient regions in medical images［J］. Medical Image Analysis, 2019, 53: 197-207.

[18] [18] LI D L, WAN J, ZHU H F, et al. Underwater image recognition technology research based on HSV color space［J］. Scientia Sinca Physica, Mechanica & Astronomica,2015,45(8):71-75(in Chin-ese).

[19] [19] ZHONG H, WANG R. A visual-degradation-inspired model with HSV color-encoding for contour detection［J］. Journal of Neuroscience Methods, 2021,369: 109423.

[20] [20] CHERNOV V, ALANDER J, BOCHKO V. Integer-based accurate conversion between RGB and HSV color spaces［J］. Computers & Electrical Engineering, 2015, 46: 328-337.

[21] [21] ZHANG Q, LI J F, ZHUO L. Vehicle color recognition using convolutional neural network for urban surveillance images［J］. Measurement and Control Technology,2017,36(10):11-14(in Chinese).

[22] [22] ZHOU X, LIU Sh D, PAN W, et al. Vehicle color recognition in natural traffic scene［J］. Computer Science,2021,48(s1):15-20(in Chinese).

[23] [23] BARGSHADY G, ZHOU X, DEO R C, et al. The modeling of human facial pain intensity based on Temporal Convolutional Networks trained with video frames in HSV color space［J］. Applied Soft Computing, 2020, 97: 106805.

[24] [24] SHELHAMER E, LONG J, DARRELL T. Fully convolutional networks for semantic segmentation［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(4): 640-651.

[25] [25] CHEN L Ch, PAPANDREOU G, KOKKINOS I, et al. DeepLab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018,40(4): 834-848.