{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,4]],"date-time":"2026-09-04T18:12:53Z","timestamp":1788545573312,"version":"build-2803163510"},"reference-count":32,"publisher":"MDPI AG","issue":"17","license":[{"start":{"date-parts":[[2026,9,4]],"date-time":"2026-09-04T00:00:00Z","timestamp":1788480000000},"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>Remote photoplethysmography (rPPG) estimates heart rate (HR) from facial color variations. In continuous wavelet transform (CWT) scalograms, HR is represented by position along the frequency axis, whereas global average pooling (GAP) does not retain this coordinate explicitly. We investigated whether a structured frequency-localizing readout improves HR estimation and analyzed the remaining errors. Leave-one-subject-out evaluations were conducted on three datasets (PURE, UBFC-rPPG, and BH-rPPG) using a fixed chrominance-based signal-extraction and CWT pipeline. The proposed model combined a frequency-preserving convolutional neural network backbone with a soft-argmax readout over HR coordinates. Using the same backbone and training protocol, soft-argmax reduced segment-pooled mean absolute error (MAE) relative to the matched GAP readout from 8.09 to 2.98 beats per minute on PURE and from 5.14 to 3.82 beats per minute on UBFC-rPPG, with significant subject-level improvements on both datasets. Residual analyses indicated that major errors could originate from color projection, non-cardiac spectral components, motion, and HR-range mismatch. On BH-rPPG, the proposed model achieved the lowest MAE under low illumination, while the evaluated CWT-based estimators showed smaller illumination-induced degradation than the evaluated fast Fourier transform (FFT)-based estimators. These findings support structured soft-argmax readout design and highlight the need to detect or mitigate degraded input signals.<\/jats:p>","DOI":"10.3390\/s26175637","type":"journal-article","created":{"date-parts":[[2026,9,4]],"date-time":"2026-09-04T17:25:56Z","timestamp":1788542756000},"page":"5637","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Frequency-Preserving Readout Design and Error Characterization for CWT-Based rPPG Heart-Rate Estimation"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-1734-9522","authenticated-orcid":false,"given":"Kota","family":"Toyama","sequence":"first","affiliation":[{"name":"Graduate School of Informatics, Chiba University, 1-33 Yayoi, Inage, Chiba 263-8522, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2734-1326","authenticated-orcid":false,"given":"Masato","family":"Takahashi","sequence":"additional","affiliation":[{"name":"Graduate School of Informatics, Chiba University, 1-33 Yayoi, Inage, Chiba 263-8522, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Norimichi","family":"Tsumura","sequence":"additional","affiliation":[{"name":"Graduate School of Informatics, Chiba University, 1-33 Yayoi, Inage, Chiba 263-8522, Japan"},{"name":"Hiroshima University Hospital, Hiroshima University, Hiroshima 734-8551, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,9,4]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"21434","DOI":"10.1364\/OE.16.021434","article-title":"Remote plethysmographic imaging using ambient light","volume":"16","author":"Verkruysse","year":"2008","journal-title":"Opt. Express"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3558518","article-title":"Camera measurement of physiological vital signs","volume":"55","author":"McDuff","year":"2023","journal-title":"ACM Comput. Surv."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"10762","DOI":"10.1364\/OE.18.010762","article-title":"Non-contact, automated cardiac pulse measurements using video imaging and blind source separation","volume":"18","author":"Poh","year":"2010","journal-title":"Opt. Express"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"2878","DOI":"10.1109\/TBME.2013.2266196","article-title":"Robust pulse rate from chrominance-based rPPG","volume":"60","author":"Jeanne","year":"2013","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1479","DOI":"10.1109\/TBME.2016.2609282","article-title":"Algorithmic principles of remote PPG","volume":"64","author":"Wang","year":"2017","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Chen, W., and McDuff, D. (2018, January 8\u201314). DeepPhys: Video-based physiological measurement using convolutional attention networks. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01216-8_22"},{"key":"ref_7","unstructured":"Yu, Z., Li, X., and Zhao, G. (2019, January 9\u201312). Remote photoplethysmograph signal measurement from facial videos using spatio-temporal networks. Proceedings of the British Machine Vision Conference (BMVC), Cardiff, UK."},{"key":"ref_8","first-page":"19400","article-title":"Multi-task temporal shift attention networks for on-device contactless vitals measurement","volume":"33","author":"Liu","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Liu, X., Hill, B., Jiang, Z., Patel, S., and McDuff, D. (2023, January 3\u20137). EfficientPhys: Enabling simple, fast and accurate camera-based cardiac measurement. Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI, USA.","DOI":"10.1109\/WACV56688.2023.00498"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Yu, Z., Shen, Y., Shi, J., Zhao, H., Torr, P.H.S., and Zhao, G. (2022, January 18\u201324). PhysFormer: Facial video-based physiological measurement with temporal difference transformer. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.00415"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"4007710","DOI":"10.1109\/TIM.2023.3287243","article-title":"Time\u2013frequency learning framework for rPPG signal estimation using scalogram-based feature map of facial video data","volume":"72","author":"Das","year":"2023","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"2409","DOI":"10.1109\/TIP.2019.2947204","article-title":"RhythmNet: End-to-end heart rate estimation from face via spatial-temporal representation","volume":"29","author":"Niu","year":"2020","journal-title":"IEEE Trans. Image Process."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Gideon, J., and Stent, S. (2021, January 10\u201317). The way to my heart is through contrastive learning: Remote photoplethysmography from unlabelled video. Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada.","DOI":"10.1109\/ICCV48922.2021.00396"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Sun, Z., and Li, X. (2022, January 23\u201327). Contrast-Phys: Unsupervised video-based remote physiological measurement via spatiotemporal contrast. Proceedings of the European Conference on Computer Vision (ECCV), Tel Aviv, Israel.","DOI":"10.1007\/978-3-031-19775-8_29"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"68485","DOI":"10.52202\/075280-2995","article-title":"rPPG-Toolbox: Deep remote PPG toolbox","volume":"36","author":"Liu","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_16","unstructured":"Qian, W., Guo, D., Zhou, J., Zou, B., Yu, Z., and Wang, M. (2026). FreqPhys: Repurposing implicit physiological frequency prior for robust remote photoplethysmography. arXiv."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Vance, N., Speth, J., Sporrer, B., and Flynn, P. (2023, January 18\u201322). Promoting generalization in cross-dataset remote photoplethysmography. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Vancouver, BC, Canada.","DOI":"10.1109\/CVPRW59228.2023.00637"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Lu, H., Yu, Z., Niu, X., and Chen, Y.-C. (2023, January 18\u201322). Neuron structure modeling for generalizable remote physiological measurement. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada.","DOI":"10.1109\/CVPR52729.2023.01783"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Du, J., Liu, S.-Q., Zhang, B., and Yuen, P.C. (2023, January 18\u201322). Dual-bridging with adversarial noise generation for domain adaptive rPPG estimation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada.","DOI":"10.1109\/CVPR52729.2023.00998"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Paruchuri, A., Liu, X., Pan, Y., Patel, S., McDuff, D., and Sengupta, S. (2024, January 3\u20138). Motion matters: Neural motion transfer for better camera physiological measurement. Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI, USA.","DOI":"10.1109\/WACV57701.2024.00583"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"R155","DOI":"10.1088\/0967-3334\/26\/5\/R01","article-title":"Wavelet transforms and the ECG: A review","volume":"26","author":"Addison","year":"2005","journal-title":"Physiol. Meas."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Honari, S., Molchanov, P., Tyree, S., Vincent, P., Pal, C., and Kautz, J. (2018, January 18\u201322). Improving landmark localization with semi-supervised learning. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00167"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Luvizon, D.C., Picard, D., and Tabia, H. (2018, January 18\u201322). 2D\/3D pose estimation and action recognition using multitask deep learning. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00539"},{"key":"ref_24","unstructured":"Nibali, A., He, Z., Morgan, S., and Prendergast, L. (2018). Numerical coordinate regression with convolutional neural networks. arXiv."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Stricker, R., M\u00fcller, S., and Gross, H.-M. (2014, January 25\u201329). Non-contact video-based pulse rate measurement on a mobile service robot. Proceedings of the IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN), Edinburgh, UK.","DOI":"10.1109\/ROMAN.2014.6926392"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1016\/j.patrec.2017.10.017","article-title":"Unsupervised skin tissue segmentation for remote photoplethysmography","volume":"124","author":"Bobbia","year":"2019","journal-title":"Pattern Recognit. Lett."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Yang, Z., Wang, H., and Lu, F. (2021). Assessment of deep learning-based heart rate estimation using remote photoplethysmography under different illuminations. arXiv.","DOI":"10.1109\/THMS.2022.3207755"},{"key":"ref_28","unstructured":"Lugaresi, C., Tang, J., Nash, H., McClanahan, C., Uboweja, E., Hays, M., Zhang, F., Chang, C.-L., Yong, M.G., and Lee, J. (2019). MediaPipe: A framework for building perception pipelines. arXiv."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1016\/S0140-6736(86)90837-8","article-title":"Statistical methods for assessing agreement between two methods of clinical measurement","volume":"327","author":"Bland","year":"1986","journal-title":"Lancet"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Elgendi, M. (2016). Optimal signal quality index for photoplethysmogram signals. Bioengineering, 3.","DOI":"10.3390\/bioengineering3040021"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Liu, I., Ni, S., and Peng, K. (2020). Enhancing the robustness of smartphone photoplethysmography: A signal quality index approach. Sensors, 20.","DOI":"10.3390\/s20071923"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1038\/s44328-024-00002-1","article-title":"Optimal signal quality index for remote photoplethysmogram sensing","volume":"1","author":"Elgendi","year":"2024","journal-title":"npj Biosens."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/17\/5637\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,4]],"date-time":"2026-09-04T17:29:01Z","timestamp":1788542941000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/17\/5637"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,4]]},"references-count":32,"journal-issue":{"issue":"17","published-online":{"date-parts":[[2026,9]]}},"alternative-id":["s26175637"],"URL":"https:\/\/doi.org\/10.3390\/s26175637","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,4]]}}}