{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T17:21:26Z","timestamp":1778001686984,"version":"3.51.4"},"reference-count":51,"publisher":"ASME International","issue":"10","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.asme.org\/publications-submissions\/publishing-information\/legal-policies"}],"content-domain":{"domain":["asmedigitalcollection.asme.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,1,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Iron ore pellets are one of the main raw materials in the metallurgical industry. To ensure the utilization rate of raw materials and the efficiency of industrial processes, it is often necessary to control the particle size distribution of the pellets. Computer vision-based methods for detecting iron ore pellet size distribution (PSD) have been developed. However, pellet shadowing, particle overlap, and uneven illumination pose significant challenges that severely compromise segmentation performance and particle size measurement accuracy. To address these challenges, we proposed an improved network structure called transformer-fused level set UNet3+ (TFL\u2212UNet3+). Specifically, UNet3+ provides multi-scale feature representations to automatically initialize the level set curve, while a reconstructed energy functional, substituting traditional pixel intensity terms with the discrepancy between the probability map and the ground truth mask, is embedded into the loss function for joint supervision of semantic and geometric constraints. Moreover, the level set evolution is reformulated as a temporal sequence, enabling the Transformer to capture long-range dependencies across iterations and thus alleviating degradation and instability of level set. Experimental evaluations on disc pelletizer discharge images demonstrate that the proposed TFL\u2212UNet3+ achieves superior segmentation accuracy, yielding relative improvements of 1.3% in intersection over union and 0.9% in boundary F1 score over state-of-the-art methods, while maintaining reliable PSD measurements validated.<\/jats:p>","DOI":"10.1115\/1.4071084","type":"journal-article","created":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T14:07:32Z","timestamp":1770732452000},"update-policy":"https:\/\/doi.org\/10.1115\/crossmarkpolicy-asme","source":"Crossref","is-referenced-by-count":0,"title":["Transformer-Fused Level Set UNet3+ for Monitoring of Iron Ore Pellet Size Distribution"],"prefix":"10.1115","volume":"26","author":[{"given":"Wenqing","family":"Deng","sequence":"first","affiliation":[{"name":"Beijing University of Technology Department of Computer Science, , No. 100 Pingleyuan, Jinsong Road, \u00a0 ,","place":["Beijing, China, 100124"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Tong","sequence":"additional","affiliation":[{"id":[{"id":"https:\/\/ror.org\/037b1pp87","id-type":"ROR","asserted-by":"publisher"}],"name":"Beijing University of Technology Department of Computer Science, , No. 100 Pingleyuan, Jinsong Road, \u00a0 ,","place":["Beijing, China, 100124"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Yu","sequence":"additional","affiliation":[{"id":[{"id":"https:\/\/ror.org\/037b1pp87","id-type":"ROR","asserted-by":"publisher"}],"name":"Beijing University of Technology Department of Computer Science, , No. 100 Pingleyuan, Jinsong Road, \u00a0 ,","place":["Beijing, China, 100124"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chuangbai","family":"Xiao","sequence":"additional","affiliation":[{"id":[{"id":"https:\/\/ror.org\/037b1pp87","id-type":"ROR","asserted-by":"publisher"}],"name":"Beijing University of Technology Department of Computer Science, , No. 100 Pingleyuan, Jinsong Road, \u00a0 ,","place":["Beijing, China, 100124"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"33","published-online":{"date-parts":[[2026,5,5]]},"reference":[{"key":"2026050513094655100_CIT0001","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1016\/j.powtec.2018.09.053","article-title":"Wet-Granulation Process: Phenomenological Analysis and Process Parameters Optimization","volume":"340","author":"De Simone","year":"2018","journal-title":"Powder Technol."},{"issue":"3","key":"2026050513094655100_CIT0002","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1016\/j.jmrt.2016.11.005","article-title":"Agglomeration Behaviour of Steel Plants Solid Waste and Its Effect on Sintering Performance","volume":"6","author":"Singh","year":"2017","journal-title":"J. Mater. Res. Technol."},{"issue":"1","key":"2026050513094655100_CIT0003","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1016\/j.powtec.2011.03.027","article-title":"Modeling of Iron Ore Pelletization Using 3 ** (k\u2013P) Factorial Design of Experiments and Polynomial Surface Regression Methodology","volume":"211","author":"Thella","year":"2011","journal-title":"Powder Technol."},{"issue":"5","key":"2026050513094655100_CIT0004","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1016\/j.ces.2013.02.043","article-title":"Development of an Image Measurement Technique for Size Distribution in Dense Bubbly Flows","volume":"94","author":"Lau","year":"2013","journal-title":"Chem. Eng. Sci."},{"key":"2026050513094655100_CIT0005","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1016\/j.dsp.2014.07.007","article-title":"Automatic Segmentation of Clustered Quantum Dots Based on Improved Watershed Transformation","volume":"34","author":"Xu","year":"2014","journal-title":"Digital Signal Process."},{"issue":"3","key":"2026050513094655100_CIT0006","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1080\/08827508.2021.1897586","article-title":"Iron Ore Pelletization: Part I. Fundamentals","volume":"43","author":"Kawatra","year":"2021","journal-title":"Mineral Process. Extract. Metallurgy Rev."},{"issue":"1","key":"2026050513094655100_CIT0007","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1080\/08827508.2016.1244058","article-title":"Study of Iron Ore Mixtures Behavior in the Grinding Pelletizing Process","volume":"38","author":"Casagrande","year":"2017","journal-title":"Mineral Process. Extract. Metallurgy Rev."},{"key":"2026050513094655100_CIT0008","first-page":"1254","article-title":"Smelting Reduction of Composite Pellets As Alternate Ironmaking","volume":"16","author":"Dutta","year":"2009","journal-title":"J. Iron Steel Res. Int."},{"key":"2026050513094655100_CIT0009","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2021.3052018","article-title":"Online Monitoring of Green Pellet Size Distribution in Haze-Degraded Images Based on VGG16-LU-Net and Haze Judgment","volume":"70","author":"Duan","year":"2021","journal-title":"IEEE Trans. Instrument. Meas."},{"issue":"11","key":"2026050513094655100_CIT0010","doi-asserted-by":"publisher","first-page":"2088","DOI":"10.2355\/isijinternational.ISIJINT-2018-384","article-title":"Image-Based Method for Measuring Pellet Size Distribution in the Stable Area of Disc Pelletizer","volume":"58","author":"Liu","year":"2018","journal-title":"ISIJ Int."},{"issue":"6","key":"2026050513094655100_CIT0011","doi-asserted-by":"publisher","first-page":"388","DOI":"10.1080\/08827508.2017.1323750","article-title":"Relationship Between Iron Ore Granulation Mechanisms, Granule Shapes, and Sinter Bed Permeability","volume":"38","author":"Nyembwe","year":"2017","journal-title":"Mineral Process. Extract. Metallurgy Rev."},{"key":"2026050513094655100_CIT0012","doi-asserted-by":"publisher","first-page":"260","DOI":"10.1016\/j.powtec.2016.09.020","article-title":"An Industrial Image Processing-Based Approach for Estimation of Iron Ore Green Pellet Size Distribution","volume":"303","author":"Heydari","year":"2016","journal-title":"Powder Technol."},{"issue":"6","key":"2026050513094655100_CIT0013","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1109\/34.87344","article-title":"Watersheds in Digital Spaces: An Efficient Algorithm Based on Immersion Simulations","volume":"13","author":"Vincent","year":"1991","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"4","key":"2026050513094655100_CIT0014","doi-asserted-by":"publisher","first-page":"532","DOI":"10.1109\/TPAMI.1987.4767941","article-title":"Image Analysis Using Mathematical Morphology","volume":"PAMI-9","author":"Haralick","year":"1987","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2026050513094655100_CIT0015","doi-asserted-by":"publisher","first-page":"186","DOI":"10.1016\/j.powtec.2019.03.007","article-title":"An Image-Based Method for Online Measurement of the Size Distribution of Iron Green Pellets Using Dual Morphological Reconstruction and Circle-Scan","volume":"347","author":"Wu","year":"2019","journal-title":"Powder Technol."},{"issue":"6","key":"2026050513094655100_CIT0016","doi-asserted-by":"publisher","first-page":"480","DOI":"10.1002\/cyto.a.v85.6","article-title":"A Color and Shape Based Algorithm for Segmentation of White Blood Cells in Peripheral Blood and Bone Marrow Images","volume":"85","author":"Arslan","year":"2014","journal-title":"Cytometry Part A"},{"issue":"7","key":"2026050513094655100_CIT0017","doi-asserted-by":"publisher","first-page":"2358","DOI":"10.1016\/j.patcog.2007.12.011","article-title":"A Constrained Region Growing Approach Based on Watershed for the Segmentation of Low Contrast Structures in Bone Micro-CT Images","volume":"41","author":"Peter","year":"2008","journal-title":"Pattern Recogn."},{"key":"2026050513094655100_CIT0018","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1016\/j.bspc.2017.07.014","article-title":"A Novel Segmentation of Cochlear Nerve Using Region Growing Algorithm","volume":"39","author":"Jeevakala","year":"2018","journal-title":"Biomed. Signal Process. Control"},{"issue":"2","key":"2026050513094655100_CIT0019","doi-asserted-by":"publisher","first-page":"e453","DOI":"10.7717\/peerj.453","article-title":"scikit-Image: Image Processing in Python","volume":"2","author":"Walt","year":"2014","journal-title":"PeerJ"},{"key":"2026050513094655100_CIT0020","doi-asserted-by":"publisher","first-page":"103120","DOI":"10.1016\/j.rcim.2025.103120","article-title":"LLM Based Autonomous Agent of Human-Robot Collaboration for Aerospace Wire Harnessing Assembly","volume":"97","author":"Wang","year":"2026","journal-title":"Rob. Comput.-Integr. Manuf."},{"issue":"11","key":"2026050513094655100_CIT0021","doi-asserted-by":"publisher","first-page":"114501","DOI":"10.1115\/1.4066170","article-title":"A Global Feature Reused Network for Defect Detection in Steel Images","volume":"24","author":"Yang","year":"2024","journal-title":"ASME J. Comput. Inf. Sci. Eng."},{"issue":"4","key":"2026050513094655100_CIT0022","doi-asserted-by":"publisher","first-page":"040801","DOI":"10.1115\/1.4049535","article-title":"Image-Based Surface Defect Detection Using Deep Learning: A Review","volume":"21","author":"Bhatt","year":"2021","journal-title":"ASME J. Comput. Inf. Sci. Eng."},{"issue":"1","key":"2026050513094655100_CIT0023","doi-asserted-by":"publisher","first-page":"471","DOI":"10.1007\/s00603-021-02657-y","article-title":"Prediction of Particle Size Distribution Curves of Dump Materials Using Convolutional Neural Networks","volume":"55","author":"Shrivastava","year":"2022","journal-title":"Rock Mech. Rock Eng."},{"issue":"2","key":"2026050513094655100_CIT0024","doi-asserted-by":"publisher","first-page":"386","DOI":"10.1109\/TPAMI.34","article-title":"Mask R-CNN","volume":"42","author":"He","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2026050513094655100_CIT0025","first-page":"936","article-title":"Feature Pyramid Networks for Object Detection","author":"Lin","year":"2017"},{"key":"2026050513094655100_CIT0026","doi-asserted-by":"publisher","first-page":"117673","DOI":"10.1016\/j.powtec.2022.117673","article-title":"TESN: Transformers Enhanced Segmentation Network for Accurate Nanoparticle Size Measurement of TEM Images","volume":"407","author":"Wang","year":"2022","journal-title":"Powder Technol."},{"key":"2026050513094655100_CIT0027","first-page":"234","article-title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","author":"Ronneberger","year":"2015"},{"issue":"10","key":"2026050513094655100_CIT0028","doi-asserted-by":"publisher","first-page":"5775","DOI":"10.1007\/s00521-019-04045-8","article-title":"Detection and Segmentation of Iron Ore Green Pellets in Images Using Lightweight U-Net Deep Learning Network","volume":"32","author":"Duan","year":"2020","journal-title":"Neural Comput. Appl."},{"key":"2026050513094655100_CIT0029","first-page":"448","article-title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","volume-title":"International Conference On Machine Learning","author":"Ioffe","year":"2015"},{"key":"2026050513094655100_CIT0030","doi-asserted-by":"publisher","first-page":"584","DOI":"10.1016\/j.powtec.2021.04.045","article-title":"Online Size Distribution Measurement of Dense Iron Green Pellets Using an Efficient and Multiscale Nested U-Net Method","volume":"387","author":"Wu","year":"2021","journal-title":"Powder Technol."},{"key":"2026050513094655100_CIT0031","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/978-3-030-00889-5_1","volume-title":"Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support","author":"Zhou","year":"2018"},{"issue":"3","key":"2026050513094655100_CIT0032","doi-asserted-by":"publisher","first-page":"031005","DOI":"10.1115\/1.4053078","article-title":"Segmentation of Additive Manufacturing Defects Using U-Net","volume":"22","author":"Wong","year":"2021","journal-title":"ASME J. Comput. Inf. Sci. Eng."},{"issue":"1","key":"2026050513094655100_CIT0033","doi-asserted-by":"publisher","first-page":"34149","DOI":"10.1038\/s41598-025-12390-z","article-title":"Federated Multi-Scale Vision Transformer with Adaptive Client Aggregation for Industrial Defect Detection","volume":"15","author":"Are","year":"2025","journal-title":"Sci. Rep."},{"key":"2026050513094655100_CIT0034","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2023.3317480","article-title":"DDR-Unet: A High-Accuracy and Efficient Ore Image Segmentation Method","volume":"72","author":"Li","year":"2023","journal-title":"IEEE Trans. Instrument. Meas."},{"issue":"2","key":"2026050513094655100_CIT0035","doi-asserted-by":"publisher","first-page":"266","DOI":"10.1109\/83.902291","article-title":"Active Contours Without Edges","volume":"10","author":"Chan","year":"2001","journal-title":"IEEE Trans. Image Process."},{"key":"2026050513094655100_CIT0036","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1016\/j.patrec.2019.03.004","article-title":"A Deep Learning-Shape Driven Level Set Synergism for Pulmonary Nodule Segmentation","volume":"123","author":"Roy","year":"2019","journal-title":"Pattern Recogn. Lett."},{"issue":"4","key":"2026050513094655100_CIT0037","doi-asserted-by":"publisher","first-page":"640","DOI":"10.1109\/cvpr.2015.7298965","article-title":"Fully Convolutional Networks for Semantic Segmentation","volume":"39","author":"Long","year":"2015","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2026050513094655100_CIT0038","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIP.2017.2700727","article-title":"Reformulating Level Sets As Deep Recurrent Neural Network Approach to Semantic Segmentation","author":"Le","year":"2017","journal-title":"IEEE Trans. Image Process."},{"issue":"1","key":"2026050513094655100_CIT0039","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1109\/TII.2023.3261889","article-title":"WDLS: Deep Level Set Learning for Weakly Supervised Aeroengine Defect Segmentation","volume":"20","author":"Qi","year":"2024","journal-title":"IEEE Trans.Ind. Inf."},{"key":"2026050513094655100_CIT0040","first-page":"1055","article-title":"UNet 3+: A Full-Scale Connected UNet for Medical Image Segmentation","author":"Huang","year":"2020"},{"issue":"1","key":"2026050513094655100_CIT0041","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1023\/A:1007979827043","article-title":"Geodesic Active Contours","volume":"22","author":"Caselles","year":"1997","journal-title":"Int. J. Comput. Vis."},{"issue":"6","key":"2026050513094655100_CIT0042","doi-asserted-by":"publisher","first-page":"755","DOI":"10.1109\/TPAMI.2003.1201824","article-title":"A Topology Preserving Level Set Method for Geometric Deformable Models","volume":"25","author":"Han","year":"2003","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2026050513094655100_CIT0043","volume-title":"Machine Learning: A Probabilistic Perspective","author":"Murphy","year":"2012"},{"key":"2026050513094655100_CIT0044","first-page":"565","article-title":"V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation","author":"Milletari","year":"2016"},{"issue":"2","key":"2026050513094655100_CIT0045","doi-asserted-by":"publisher","first-page":"1974","DOI":"10.1109\/TASE.2023.3253574","article-title":"Online Monitoring of Iron Ore Pellet Size Distribution Using Lightweight Convolutional Neural Network","volume":"21","author":"Deo","year":"2024","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"issue":"1\u20132","key":"2026050513094655100_CIT0046","doi-asserted-by":"publisher","first-page":"187","DOI":"10.3233\/FI-2000-411207","article-title":"The Watershed Transform: Definitions, Algorithms and Parallelization Strategies","volume":"41","author":"Roerdink","year":"2000","journal-title":"Fundamenta Informaticae"},{"issue":"12","key":"2026050513094655100_CIT0047","doi-asserted-by":"publisher","first-page":"2481","DOI":"10.1109\/TPAMI.34","article-title":"SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation","volume":"39","author":"Badrinarayanan","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2026050513094655100_CIT0048","author":"Lyakaap","year":"2017"},{"key":"2026050513094655100_CIT0049","doi-asserted-by":"publisher","first-page":"126798","DOI":"10.1016\/j.neucom.2023.126798","article-title":"Response Fusion Attention U-ConvNext for Accurate Segmentation of Optic Disc and Optic Cup","volume":"559","author":"Mallick","year":"2023","journal-title":"Neurocomputing"},{"issue":"8","key":"2026050513094655100_CIT0050","doi-asserted-by":"publisher","first-page":"510","DOI":"10.1007\/s10586-024-05085-z","article-title":"TransMA-Unet: Transformer and Multi-Scale Residual Connection Attention Network for Vessel Segmentation","volume":"28","author":"Zhang","year":"2025","journal-title":"Cluster Comput."},{"key":"2026050513094655100_CIT0051","doi-asserted-by":"publisher","first-page":"140","DOI":"10.1016\/j.powtec.2016.09.056","article-title":"Effect of Roundness on the Discharge Flow of Granular Particles","volume":"314","author":"Gui","year":"2017","journal-title":"Powder Technol."}],"container-title":["Journal of Computing and Information Science in Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/asmedigitalcollection.asme.org\/computingengineering\/article-pdf\/26\/10\/101004\/7590869\/jcise-25-1428.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/asmedigitalcollection.asme.org\/computingengineering\/article-pdf\/26\/10\/101004\/7590869\/jcise-25-1428.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T17:09:52Z","timestamp":1778000992000},"score":1,"resource":{"primary":{"URL":"https:\/\/asmedigitalcollection.asme.org\/computingengineering\/article\/26\/10\/101004\/1230517\/Transformer-Fused-Level-Set-UNet3-for-Monitoring"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,1]]},"references-count":51,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2026,1,1]]}},"URL":"https:\/\/doi.org\/10.1115\/1.4071084","relation":{},"ISSN":["1530-9827","1944-7078"],"issn-type":[{"value":"1530-9827","type":"print"},{"value":"1944-7078","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,1]]},"article-number":"101004"}}