{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T00:40:25Z","timestamp":1760143225595,"version":"build-2065373602"},"reference-count":30,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2024,1,21]],"date-time":"2024-01-21T00:00:00Z","timestamp":1705795200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Taylor\u2019s University"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computers"],"abstract":"<jats:p>This study introduces a novel approach to address challenges in workpiece surface defect identification. It presents an enhanced Single Shot MultiBox Detector model, incorporating attention mechanisms and multi-feature fusion. The research methodology involves carefully curating a dataset from authentic on-site factory production, enabling the training of a model with robust real-world generalization. Leveraging the Single Shot MultiBox Detector model lead to improvements integrating channel and spatial attention mechanisms in the feature extraction network. Diverse feature extraction methods enhance the network\u2019s focus on crucial information, improving its defect detection efficacy. The proposed model achieves a significant Mean Average Precision (mAP) improvement, reaching 99.98% precision, a substantial 3% advancement over existing methodologies. Notably, the proposed model exhibits a tendency for the values of the P-R curves in object detection for each category to approach 1, which allows a better balance between the requirements of real-time detection and precision. Within the threshold range of 0.2 to 1, the model maintains a stable level of precision, consistently remaining between 0.99 and 1. In addition, the average running speed is 2 fps lower compared to other models, and the reduction in detection speed after the model improvement is kept within 1%. The experimental results indicate that the model excels in pixel-level defect identification, which is crucial for precise defect localization. Empirical experiments validate the algorithm\u2019s superior performance. This research represents a pivotal advancement in workpiece surface defect identification, combining technological innovation with practical efficacy.<\/jats:p>","DOI":"10.3390\/computers13010030","type":"journal-article","created":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T05:42:31Z","timestamp":1705902151000},"page":"30","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Improved Deep Learning Model for Workpieces of Rectangular Pipeline Surface Defect Detection"],"prefix":"10.3390","volume":"13","author":[{"given":"Changxing","family":"Chen","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Taylor\u2019s University, Subang Jaya 47500, Selangor, Malaysia"}]},{"given":"Afizan","family":"Azman","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Taylor\u2019s University, Subang Jaya 47500, Selangor, Malaysia"}]}],"member":"1968","published-online":{"date-parts":[[2024,1,21]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"106268","DOI":"10.1016\/j.engappai.2023.106268","article-title":"An automatic machine vision-based algorithm for inspection of hardwood flooring defects during manufacturing","volume":"123","author":"Truong","year":"2023","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Yang, J., Wang, K., Luan, F., Yin, Y., and Zhang, H. (2023). PreCaCycleGAN: Perceptual Capsule Cyclic Generative Adversarial Network for Industrial Defective Sample Augmentation. Electronics, 12.","DOI":"10.3390\/electronics12163475"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Behrouzi, S., Dix, M., Karampanah, F., Ates, O., Sasidharan, N., Chandna, S., and Vu, B. (2023). Improving Visual Defect Detection and Localization in Industrial Thermal Images Using Autoencoders. J. Imaging, 9.","DOI":"10.3390\/jimaging9070137"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"104686","DOI":"10.1016\/j.pnucene.2023.104686","article-title":"Defective PWR fuel rods detection and characterization using an Artificial Neural Network","volume":"160","author":"Verma","year":"2023","journal-title":"Prog. Nucl. Energy"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"121036","DOI":"10.1016\/j.eswa.2023.121036","article-title":"An improved lightweight small object detection framework applied to real-time autonomous driving","volume":"234","author":"Mahaur","year":"2023","journal-title":"Expert Syst. Appl."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"135313","DOI":"10.1016\/j.matlet.2023.135313","article-title":"Automatic recognition of surface defects of hot rolled strip steel based on deep parallel attention convolution neural network","volume":"353","author":"Zhao","year":"2023","journal-title":"Mater. Lett."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"121308","DOI":"10.1016\/j.eswa.2023.121308","article-title":"ESA-Net: An efficient scale-aware network for small crop pest detection","volume":"236","author":"Dong","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"3145","DOI":"10.1007\/s11760-023-02536-9","article-title":"FFR-SSD: Feature fusion and reconstruction single shot detector for multi-scale object detection","volume":"17","author":"Cheng","year":"2023","journal-title":"Signal Image Video Process."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"113244","DOI":"10.1016\/j.measurement.2023.113244","article-title":"Data-driven model SSD-BSP for multi-target coal-gangue detection","volume":"219","author":"Wang","year":"2023","journal-title":"Meas. J. Int. Meas. Confed."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"6265","DOI":"10.1007\/s00371-022-02727-4","article-title":"B-FPN SSD: An SSD algorithm based on a bidirectional feature fusion pyramid","volume":"39","author":"Liu","year":"2023","journal-title":"Vis. Comput."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Cong, P., Lv, K., Feng, H., and Zhou, J. (2022). Improved YOLOv3 Model for Workpiece Stud Leakage Detection. Electronics, 11.","DOI":"10.3390\/electronics11213430"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"6049013","DOI":"10.1155\/2022\/6049013","article-title":"Pipeline Multitype Artifact Recognition Method Based on Inception_Resnet _V2 Structure Improving SSD Network","volume":"2022","author":"Zheng","year":"2022","journal-title":"Adv. Multimed."},{"key":"ref_13","unstructured":"Xu, S., and Shao, Z. (2022). Association for Computing Machinery."},{"key":"ref_14","first-page":"148","article-title":"An augmentation method of defect detection dataset based on M-DCGAN","volume":"49","author":"Tang","year":"2023","journal-title":"Dalian Haishi Daxue Xuebao J. Dalian Marit. Univ."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"102035","DOI":"10.1016\/j.inffus.2023.102035","article-title":"Addressing data scarcity in protein fitness landscape analysis: A study on semi-supervised and deep transfer learning techniques","volume":"102","year":"2024","journal-title":"Inf. Fusion"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"121288","DOI":"10.1016\/j.eswa.2023.121288","article-title":"Deep multi-scale pyramidal features network for supervised video summarization","volume":"237","author":"Khan","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"121617","DOI":"10.1016\/j.eswa.2023.121617","article-title":"Android malware detection method based on graph attention networks and deep fusion of multimodal features","volume":"237","author":"Chen","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1186\/s13635-023-00141-4","article-title":"Network traffic classification model based on attention mechanism and spatiotemporal features","volume":"2023","author":"Hu","year":"2023","journal-title":"Eurasip J. Inf. Secur."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1007\/s44196-023-00286-7","article-title":"Improved Algorithm for Face Mask Detection Based on YOLO-v4","volume":"16","author":"Zhao","year":"2023","journal-title":"Int. J. Comput. Intell. Syst."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Jia, X., Bartlett, J., Chen, W., Song, S., Zhang, T., Cheng, X., Lu, W., Qiu, Z., and Duan, J. (2023, January 7\u201314). Fourier-Net: Fast Image Registration with Band-Limited Deformation. Proceedings of the 37th AAAI Conference on Artificial Intelligence, AAAI 2023, Washington, DC, USA.","DOI":"10.1609\/aaai.v37i1.25182"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"125141","DOI":"10.1088\/1361-6501\/acf781","article-title":"Feature fusion-based fiber-optic distributed acoustic sensing signal identification method","volume":"34","author":"Wang","year":"2023","journal-title":"Meas. Sci. Technol."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"115402","DOI":"10.1088\/1361-6501\/ace929","article-title":"An efficient method of pavement distress detection based on improved YOLOv7","volume":"34","author":"Yi","year":"2023","journal-title":"Meas. Sci. Technol."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1007\/978-3-031-39603-8_15","article-title":"Deep Learning-Based YOLO Network Model for Detecting Surface Cracks During Structural Health Monitoring","volume":"Volume 47","author":"Pratibha","year":"2024","journal-title":"RILEM Bookseries"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"121726","DOI":"10.1016\/j.eswa.2023.121726","article-title":"A lightweight surface defect detection framework combined with dual-domain attention mechanism","volume":"238","author":"Tang","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Shen, D., Liu, X., Shang, Y., and Tang, X. (2023). Deep Learning-Based Automatic Defect Detection Method for Sewer Pipelines. Sustainability, 15.","DOI":"10.3390\/su15129164"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"111066","DOI":"10.1016\/j.knosys.2023.111066","article-title":"GRA-Net: Global receptive attention network for surface defect detection","volume":"280","author":"Xiao","year":"2023","journal-title":"Knowl. Based Syst."},{"key":"ref_27","first-page":"63","article-title":"CAD Fabric Model Defect Detection Based on Improved Yolov5 Based on Self-Attention Mechanism","volume":"21","author":"Shen","year":"2024","journal-title":"Comput. Aided Des. Appl."},{"key":"ref_28","unstructured":"Sahoo, A.K., Behera, S., Maurya, S., and Kale, P. (2023). Lecture Notes in Electrical Engineering, Springer Nature."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Gudhe, N.R., Kosma, V.M., Behravan, H., and Mannermaa, A. (2023). Nuclei instance segmentation from histopathology images using Bayesian dropout based deep learning. BMC Med. Imaging, 23.","DOI":"10.1186\/s12880-023-01121-3"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Afshar, S., Braun, P.R., Han, S., and Lin, Y. (2023). A multimodal deep learning model to infer cell-type-specific functional gene networks. BMC Bioinform., 24.","DOI":"10.1186\/s12859-023-05146-x"}],"container-title":["Computers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-431X\/13\/1\/30\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T13:46:42Z","timestamp":1760104002000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-431X\/13\/1\/30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,21]]},"references-count":30,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,1]]}},"alternative-id":["computers13010030"],"URL":"https:\/\/doi.org\/10.3390\/computers13010030","relation":{},"ISSN":["2073-431X"],"issn-type":[{"type":"electronic","value":"2073-431X"}],"subject":[],"published":{"date-parts":[[2024,1,21]]}}}