{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T05:26:36Z","timestamp":1782969996938,"version":"3.54.5"},"reference-count":26,"publisher":"MDPI AG","issue":"10","license":[{"start":{"date-parts":[[2024,9,26]],"date-time":"2024-09-26T00:00:00Z","timestamp":1727308800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>Aiming at the problem that the surface defects of blAister tablets are difficult to detect correctly, this paper proposes a detection method based on the improved U2Net. First, the features extracted from the RSU module of U2Net are enhanced and adjusted using the large kernel attention mechanism, so that the U2Net model strengthens its ability to extract defective features. Second, a loss function combining the Gaussian Laplace operator and the cross-entropy function is designed to make the model strengthen its ability to detect edge defects on the surface of blister tablets. Finally, thresholds are adaptively determined using the local mean and OTSU(an adaptive threshold segmentation method) method to improve accuracy. The experimental results show that the method proposed in this paper can reach an average accuracy of 99% and an average precision rate of 96.3%; the model test only takes 50 ms per image, which can meet the rapid detection requirements. Minor surface defects can also be accurately detected, which is better than other algorithmic models of the same type, proving the effectiveness of this method.<\/jats:p>","DOI":"10.3390\/a17100429","type":"journal-article","created":{"date-parts":[[2024,9,26]],"date-time":"2024-09-26T06:55:52Z","timestamp":1727333752000},"page":"429","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Improved U2Net-Based Surface Defect Detection Method for Blister Tablets"],"prefix":"10.3390","volume":"17","author":[{"given":"Jianmin","family":"Zhou","sequence":"first","affiliation":[{"name":"School of Electromechanical and Vehicle Engineering, East China Jiaotong University, Nanchang 330013, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Electromechanical and Vehicle Engineering, East China Jiaotong University, Nanchang 330013, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jikang","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Electromechanical and Vehicle Engineering, East China Jiaotong University, Nanchang 330013, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingbo","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Electromechanical and Vehicle Engineering, East China Jiaotong University, Nanchang 330013, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2024,9,26]]},"reference":[{"key":"ref_1","unstructured":"World Health Organization (2019). Good Manufacturing Practices for Pharmaceutical Products: Main Principles, World Health Organization."},{"key":"ref_2","unstructured":"International Conference on Harmonisation (2005). ICH Harmonised Tripartite Guideline: Quality Risk Management (Q9), International Conference on Harmonisation of Technical Requirements for Pharmaceuticals for Human Use."},{"key":"ref_3","unstructured":"United States Pharmacopeia (2019). USP 42, NF 37, United States Pharmacopeial Convention. [3rd ed.]."},{"key":"ref_4","first-page":"123","article-title":"Blister packaging design for the protection and stability of pharmaceutical products","volume":"64","author":"Sugawara","year":"2010","journal-title":"J. Pharm. Sci. Technol."},{"key":"ref_5","first-page":"215","article-title":"Detection techniques for tablet blister packaging: Ensuring pharmaceutical quality and safety","volume":"5","author":"Yao","year":"2015","journal-title":"Int. J. Pharm. Qual. Assur."},{"key":"ref_6","first-page":"66","article-title":"Study on Real-time Tablets Image Detection and Processing System Based on Image Processing and Its Application","volume":"1","author":"Liu","year":"2013","journal-title":"Comput. Mod."},{"key":"ref_7","first-page":"2958","article-title":"Discrimination of Varieties of Tablets Using Near-Infrared Spectroscopy by Wavelet Clustering","volume":"30","author":"Fang","year":"2010","journal-title":"Spectrosc. Spectr. Anal."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"107404","DOI":"10.1016\/j.patcog.2020.107404","article-title":"U2-Net: Going deeper with nested U-structure for salient object detection","volume":"106","author":"Qin","year":"2020","journal-title":"Pattern Recognit."},{"key":"ref_9","first-page":"133","article-title":"Defect Detection Method for Drug Packaging with Aluminum Plastic Bubble Cap","volume":"40","author":"Fang","year":"2019","journal-title":"Packag. Eng."},{"key":"ref_10","first-page":"15","article-title":"Application of Improved Otsu Algorithm in the Defect Detection of Aluminium-plastic Blister Drugs","volume":"35","author":"Yu","year":"2014","journal-title":"Packag. Eng."},{"key":"ref_11","first-page":"67","article-title":"Edge Detection of Aluminum-Plastic Blister Drugs Based on Improved Canny Algorithm","volume":"28","author":"Wu","year":"2014","journal-title":"J. Hunan Univ. Technol."},{"key":"ref_12","first-page":"250","article-title":"Blister packaging drug defect identification based on integrated classifier","volume":"42","author":"Chen","year":"2021","journal-title":"Packag. Eng."},{"key":"ref_13","first-page":"857","article-title":"Capsule Defect Detection Method Based on Mask R-CNN","volume":"50","author":"Duan","year":"2020","journal-title":"Radio Eng."},{"key":"ref_14","unstructured":"Huang, Z. (2023). Study on Tablet Surface Defect Detection Based on Improved YOLOv5, Chongqing University of Science and Technology."},{"key":"ref_15","first-page":"004051752092860","article-title":"Mobile-Unet: An efficient convolutional neural network for fabric defect detection","volume":"92","author":"Jing","year":"2020","journal-title":"Text. Res. J."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"105897","DOI":"10.1016\/j.cmpb.2020.105897","article-title":"Coronary angiography image segmentation based on PSPNet","volume":"200","author":"Zhu","year":"2021","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_17","unstructured":"Vijay, B., Alex, K., and Roberto, C. (2015). SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation. arXiv."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"5416","DOI":"10.1177\/00405175231198266","article-title":"Pixel-level pruning deep supervision UNet++ for detecting fabric defects","volume":"93","author":"Zhang","year":"2023","journal-title":"Text. Res. J."},{"key":"ref_19","unstructured":"Wu, Z., Lan, Y., Li, L., Xiong, X., Qiao, W., and Wang, w. (2024). Metal bar scratch defect detection based on improved U2Net. Modul. Mach. Tool Autom. Manuf. Tech., 157\u2013167."},{"key":"ref_20","first-page":"413","article-title":"Metal surface defect detection algorithm based on U2-Net","volume":"59","author":"Wang","year":"2023","journal-title":"Nanjing Univ. Nat. Sci."},{"key":"ref_21","first-page":"159","article-title":"Surface crack detection of concrete structures based on improved U2Net model","volume":"55","author":"Cheng","year":"2024","journal-title":"Water Resour. Hydropower Eng."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"733","DOI":"10.1007\/s41095-023-0364-2","article-title":"Visual attention network","volume":"9","author":"Guo","year":"2023","journal-title":"Comput. Vis. Media"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"886","DOI":"10.1109\/TPAMI.2007.1027","article-title":"Laplacian operator-based edge detectors","volume":"29","author":"Wang","year":"2007","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Rybakova, E.O., Limonova, E.E., and Nikolaev, D.P. (2024). Fast Gaussian Filter Approximations Comparison on SIMD Computing Platforms. Appl. Sci., 14.","DOI":"10.3390\/app14114664"},{"key":"ref_25","first-page":"1","article-title":"Image Segmentation By Using Thresholding Techniques For Medical Images","volume":"6","author":"Senthilkumaran","year":"2016","journal-title":"Comput. Sci. Eng. Int. J."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"112624","DOI":"10.1109\/ACCESS.2020.3002545","article-title":"Automatic Early Broken-Rotor-Bar Detection and Classification Using Otsu Segmentation","volume":"8","author":"Misael","year":"2020","journal-title":"IEEE Access"}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/17\/10\/429\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T16:03:55Z","timestamp":1760112235000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/17\/10\/429"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,26]]},"references-count":26,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2024,10]]}},"alternative-id":["a17100429"],"URL":"https:\/\/doi.org\/10.3390\/a17100429","relation":{},"ISSN":["1999-4893"],"issn-type":[{"value":"1999-4893","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,26]]}}}