{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,24]],"date-time":"2026-01-24T08:42:31Z","timestamp":1769244151447,"version":"3.49.0"},"reference-count":37,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2018,11,7]],"date-time":"2018-11-07T00:00:00Z","timestamp":1541548800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>For many decades, ultrasonic imaging inspection has been adopted as a principal method to detect multiple defects, e.g., void and corrosion. However, the data interpretation relies on an inspector\u2019s subjective judgment, thus making the results vulnerable to human error. Nowadays, advanced computer vision techniques reveal new perspectives on the high-level visual understanding of universal tasks. This research aims to develop an efficient automatic ultrasonic image analysis system for nondestructive testing (NDT) using the latest visual information processing technique. To this end, we first established an ultrasonic inspection image dataset containing 6849 ultrasonic scan images with full defect\/no-defect annotations. Using the dataset, we performed a comprehensive experimental comparison of various computer vision techniques, including both conventional methods using hand-crafted visual features and the most recent convolutional neural networks (CNN) which generate multiple-layer stacking for representation learning. In the computer vision community, the two groups are referred to as shallow and deep learning, respectively. Experimental results make it clear that the deep learning-enabled system outperformed conventional (shallow) learning schemes by a large margin. We believe this benchmarking could be used as a reference for similar research dealing with automatic defect detection in ultrasonic imaging inspection.<\/jats:p>","DOI":"10.3390\/s18113820","type":"journal-article","created":{"date-parts":[[2018,11,7]],"date-time":"2018-11-07T10:32:07Z","timestamp":1541586727000},"page":"3820","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":87,"title":["Computerized Ultrasonic Imaging Inspection: From Shallow to Deep Learning"],"prefix":"10.3390","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6680-1201","authenticated-orcid":false,"given":"Jiaxing","family":"Ye","sequence":"first","affiliation":[{"name":"National Metrology Institute of Japan (NMIJ), National Institute of Advanced Industrial Science and Technology (AIST), Tsukuba Central 2, Tsukuba 305-8568, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shunya","family":"Ito","sequence":"additional","affiliation":[{"name":"National Metrology Institute of Japan (NMIJ), National Institute of Advanced Industrial Science and Technology (AIST), Tsukuba Central 2, Tsukuba 305-8568, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9657-891X","authenticated-orcid":false,"given":"Nobuyuki","family":"Toyama","sequence":"additional","affiliation":[{"name":"National Metrology Institute of Japan (NMIJ), National Institute of Advanced Industrial Science and Technology (AIST), Tsukuba Central 2, Tsukuba 305-8568, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2018,11,7]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1177\/1475921703036169","article-title":"Health monitoring of civil infrastructure","volume":"2","author":"Chang","year":"2003","journal-title":"Struct. Health Monit."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Maierhofer, C., Reinhardt, H.W., and Dobmann, G. (2010). Non-Destructive Evaluation of Reinforced Concrete Structures: Non-Destructive Testing Methods, Elsevier.","DOI":"10.1533\/9781845699536"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1016\/S0963-8695(98)00009-7","article-title":"Developments for the non-destructive evaluation of highway bridges in the USA","volume":"31","author":"Washer","year":"1998","journal-title":"NDT E Int."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"525","DOI":"10.1016\/j.ndteint.2006.03.006","article-title":"Ultrasonic arrays for non-destructive evaluation: A review","volume":"39","author":"Drinkwater","year":"2006","journal-title":"NDT E Int."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"2069","DOI":"10.2320\/matertrans.M2010204","article-title":"Laser-Generation Based Imaging of Ultrasonic Wave Propagation on Welded Steel Plates and Its Application to Defect Detection","volume":"51","author":"Yashiro","year":"2010","journal-title":"Mater. Trans."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"ref_7","unstructured":"Goodfellow, I., Bengio, Y., Courville, A., and Bengio, Y. (2016). Deep Learning, MIT Press."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Farrar, C.R., and Worden, K. (2012). Structural Health Monitoring: A Machine Learning Perspective, John Wiley Sons.","DOI":"10.1002\/9781118443118"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1016\/S0263-2241(98)00075-X","article-title":"The use of neural networks in ultrasonic flaw detection","volume":"25","author":"Margrave","year":"1999","journal-title":"Measurement"},{"key":"ref_10","first-page":"184","article-title":"2D Gabor functions and FCMI algorithm for flaws detection in ultrasonic images","volume":"9","author":"Ahmed","year":"2005","journal-title":"World Acad. Sci. Eng. Technol."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Nosato, H., Sakanashi, H., Murakawa, M., Higuchi, T., Otsu, N., Terai, K., Hiruta, N., and Kameda, N. (2009, January 20\u201321). Histopathological diagnostic support technology using higher-order local autocorrelation features. Proceedings of the 2009 Symposium on Bio-Inspired Learning and Intelligent Systems for Security, Edingburgh, UK.","DOI":"10.1109\/BLISS.2009.29"},{"key":"ref_12","unstructured":"Krizhevsky, A., Sutskever, I., and Hinton, G.E. (2012, January 3\u20136). Imagenet classification with deep convolutional neural networks. Proceedings of the 25th International Conference on Neural Information Processing Systems, Lake Tahoe, NV, USA."},{"key":"ref_13","unstructured":"Bengio, Y. (2018, November 02). Deep Learning of Representations for Unsupervised and Transfer Learning. Available online: http:\/\/proceedings.mlr.press\/v27\/bengio12a\/bengio12a.pdf."},{"key":"ref_14","unstructured":"Ye, J., Iwata, M., Takumi, K., Murakawa, M., Tetsuya, H., Kubota, Y., Yui, T., and Mori, K. (2014, January 8\u201311). Statistical impact-echo analysis based on grassmann manifold learning: Its preliminary results for concrete condition assessment. Proceedings of the 7th European Workshop on Structural Health Monitoring (EWSHM), Nantes, France."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1104","DOI":"10.1016\/j.ultras.2013.02.005","article-title":"Decision support system for ultrasound inspection of fiber metal laminates using statistical signal processing and neural networks","volume":"53","author":"Souza","year":"2013","journal-title":"Ultrasonics"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1016\/j.ndteint.2015.12.001","article-title":"Flexible decision support system for ultrasound evaluation of fiber\u2013metal laminates implemented in a DSP","volume":"79","author":"Silva","year":"2016","journal-title":"NDT E Int."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.ultras.2016.08.017","article-title":"Efficient feature selection for neural network based detection of flaws in steel welded joints using ultrasound testing","volume":"73","author":"Cruz","year":"2017","journal-title":"Ultrasonics"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"271","DOI":"10.1016\/j.ultras.2015.05.027","article-title":"Feature selection for neural network based defect classification of ceramic components using high frequency ultrasound","volume":"62","author":"Kesharaju","year":"2015","journal-title":"Ultrasonics"},{"key":"ref_19","unstructured":"Lawson, S.W., and Parker, G.A. (2018, November 02). Automatic detection of defects in industrial ultrasound images using a neural network. Available online: https:\/\/pdfs.semanticscholar.org\/3009\/3dc2a6402e14cef4523caa708173d7de1acb.pdf."},{"key":"ref_20","unstructured":"C\u2019shekhar, N.S., Zahran, O., and Al-Nuaimy, W. (2007, January 11\u201314). Advanced neural-fuzzy and image processing techniques in the automatic detection and interpretation of weld defects using ultrasonic Time-of-Diffraction. Proceedings of the 4th International Conference on NDT, Hellenic Society for NDT, Chania, Greece."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"108","DOI":"10.1007\/s10921-011-0126-4","article-title":"Texture analysis for flaw detection in ultrasonic images","volume":"31","author":"Kechida","year":"2012","journal-title":"J. Nondestruct. Eval."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1016\/j.ultras.2014.12.005","article-title":"Robust ultrasonic damage detection under complex environmental conditions using singular value decomposition","volume":"58","author":"Liu","year":"2015","journal-title":"Ultrasonics"},{"key":"ref_23","unstructured":"Guarneri, G.A., Junior, F.N., and de Arruda, L.V. (2018, November 02). Weld Discontinuities Classification Using Principal Component Analysis and Support Vector Machine. Available online: http:\/\/www.sbai2013.ufc.br\/pdfs\/3606.pdf."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1604","DOI":"10.1109\/JPROC.2015.2481438","article-title":"Predictive guided wave models through sparse modal representations","volume":"104","author":"Harley","year":"2016","journal-title":"Proc. IEEE"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Chen, C.H., and Lee, G.G. (1993, January 27\u201330). Neural networks for ultrasonic NDE signal classification using time-frequency analysis. Proceedings of the 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing, Minneapolis, MN, USA.","DOI":"10.1109\/ICASSP.1993.319163"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"128","DOI":"10.1016\/j.neucom.2016.11.066","article-title":"Ultrasonic signal classification and imaging system for composite materials via deep convolutional neural networks","volume":"257","author":"Meng","year":"2017","journal-title":"Neurocomputing"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1615","DOI":"10.1109\/TPAMI.2005.188","article-title":"A performance evaluation of local descriptors","volume":"27","author":"Mikolajczyk","year":"2005","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_28","unstructured":"Christopher, M.B. (2006). Pattern Recognition and Machine Learning, Springer Science Business Media."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"509","DOI":"10.1109\/TGRS.1990.572934","article-title":"Texture unit, texture spectrum, and texture analysis","volume":"28","author":"He","year":"1990","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Kobayashi, T., and Ye, J. (2014, January 4\u20139). Acoustic feature extraction by statistics based local binary pattern for environmental sound classification. Proceedings of the 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Florence, Italy.","DOI":"10.1109\/ICASSP.2014.6854161"},{"key":"ref_31","unstructured":"Shinohara, Y., and Otsu, N. (2004, January 19). Facial expression recognition using fisher weight maps. Proceedings of the Sixth IEEE International Conference on Automatic Face and Gesture Recognition, Seoul, Korea."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Kobayashi, T., and Otsu, N. (2008). Image feature extraction using gradient local auto-correlations. European Conference on Computer Vision, Springer.","DOI":"10.1007\/978-3-540-88682-2_27"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1109\/MSP.2012.2205597","article-title":"Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups","volume":"29","author":"Hinton","year":"2012","journal-title":"IEEE Signal Process. Mag."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"599","DOI":"10.1007\/978-3-642-35289-8_32","article-title":"Neural networks: Tricks of the trade","volume":"7700","author":"Hinton","year":"2012","journal-title":"Lect. Notes Comput. Sci."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"2295","DOI":"10.1109\/JPROC.2017.2761740","article-title":"Efficient processing of deep neural networks: A tutorial and survey","volume":"105","author":"Sze","year":"2017","journal-title":"Proc. IEEE"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1016\/j.ndteint.2007.08.002","article-title":"A novel technique for visualizing ultrasonic waves in general solid media by pulsed laser scan","volume":"41","author":"Yashiro","year":"2008","journal-title":"NDT E Int."},{"key":"ref_37","unstructured":"Yosinski, J., Clune, J., Nguyen, A., Fuchs, T., and Lipson, H. (arXiv, 2015). Understanding neural networks through deep visualization, arXiv."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/18\/11\/3820\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T15:28:32Z","timestamp":1760196512000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/18\/11\/3820"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11,7]]},"references-count":37,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2018,11]]}},"alternative-id":["s18113820"],"URL":"https:\/\/doi.org\/10.3390\/s18113820","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,11,7]]}}}