{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,19]],"date-time":"2026-09-19T13:34:33Z","timestamp":1789824873595,"version":"4.0.1"},"reference-count":29,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2017,11,27]],"date-time":"2017-11-27T00:00:00Z","timestamp":1511740800000},"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>A thermal camera captures the temperature distribution of a scene as a thermal image. In thermal images, facial appearances of different people under different lighting conditions are similar. This is because facial temperature distribution is generally constant and not affected by lighting condition. This similarity in face appearances is advantageous for face detection. To detect faces in thermal images, cascade classifiers with Haar-like features are generally used. However, there are few studies exploring the local features for face detection in thermal images. In this paper, we introduce two approaches relying on local features for face detection in thermal images. First, we create new feature types by extending Multi-Block LBP. We consider a margin around the reference and the generally constant distribution of facial temperature. In this way, we make the features more robust to image noise and more effective for face detection in thermal images. Second, we propose an AdaBoost-based training method to get cascade classifiers with multiple types of local features. These feature types have different advantages. In this way we enhance the description power of local features. We did a hold-out validation experiment and a field experiment. In the hold-out validation experiment, we captured a dataset from 20 participants, comprising 14 males and 6 females. For each participant, we captured 420 images with 10 variations in camera distance, 21 poses, and 2 appearances (participant with\/without glasses). We compared the performance of cascade classifiers trained by different sets of the features. The experiment results showed that the proposed approaches effectively improve the performance of face detection in thermal images. In the field experiment, we compared the face detection performance in realistic scenes using thermal and RGB images, and gave discussion based on the results.<\/jats:p>","DOI":"10.3390\/s17122741","type":"journal-article","created":{"date-parts":[[2017,11,27]],"date-time":"2017-11-27T11:07:08Z","timestamp":1511780828000},"page":"2741","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":27,"title":["Adapting Local Features for Face Detection in Thermal Image"],"prefix":"10.3390","volume":"17","author":[{"given":"Chao","family":"Ma","sequence":"first","affiliation":[{"name":"Graduate School of Information Science and Electrical Engineering, Kyushu University, 744, Motooka, Nishi-ku, Fukuoka 819-0395, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ngo","family":"Trung","sequence":"additional","affiliation":[{"name":"The Institute of Scientific and Industrial Research, Osaka University, 8-1 Mihogaoka, Ibaraki, Osaka 567-0047, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hideaki","family":"Uchiyama","sequence":"additional","affiliation":[{"name":"Graduate School of Information Science and Electrical Engineering, Kyushu University, 744, Motooka, Nishi-ku, Fukuoka 819-0395, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hajime","family":"Nagahara","sequence":"additional","affiliation":[{"name":"Institute for Datability Science, Osaka University, 2-8, Yamadaoka, Suita, Osaka 565-0871, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Atsushi","family":"Shimada","sequence":"additional","affiliation":[{"name":"Graduate School of Information Science and Electrical Engineering, Kyushu University, 744, Motooka, Nishi-ku, Fukuoka 819-0395, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rin-ichiro","family":"Taniguchi","sequence":"additional","affiliation":[{"name":"Graduate School of Information Science and Electrical Engineering, Kyushu University, 744, Motooka, Nishi-ku, Fukuoka 819-0395, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2017,11,27]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.cviu.2015.03.015","article-title":"Survey on face detection in the wild: Past, present and future","volume":"138","author":"Zafeiriou","year":"2015","journal-title":"Comput. Vis. Image Underst."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Wilber, M.J., Shmatikov, V., and Belongie, S. (2016, January 7\u20139). Can we still avoid automatic face detection?. Proceedings of the 2016 IEEE Winter Conference on Applications of Computer Vision (WACV 2016), Lake Placid, NY, USA.","DOI":"10.1109\/WACV.2016.7477452"},{"key":"ref_3","first-page":"82","article-title":"Face recognition performance comparison of fake faces with real faces in relation to lighting","volume":"4","author":"Cho","year":"2014","journal-title":"J. Internet Serv. Inf. Secur."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Vollmer, M., and M\u00f6llmann, K.P. (2010). Infrared Thermal Imaging: Fundamentals, Research and Applications, John Wiley & Sons.","DOI":"10.1002\/9783527630868"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"250","DOI":"10.1016\/0300-5712(90)90022-7","article-title":"Measurement of facial skin temperature","volume":"18","author":"Ariyaratnam","year":"1990","journal-title":"J. Dent."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Lu, Y., Nagahara, H., and Taniguchi, R. (2014, January 24\u201328). Anonymous camera for privacy protection. Proceedings of the 2014 22nd International Conference on Pattern Recognition (ICPR 2014), Stockholm, Sweden.","DOI":"10.1109\/ICPR.2014.715"},{"key":"ref_7","unstructured":"Reese, K., Zheng, Y., and Elmaghraby, A. (2012, January 7\u20138). A comparison of face detection algorithms in visible and thermal spectrums. Proceedings of the International Conference on Advances in Computer Science and Application, Amsterdam, The Netherlands."},{"key":"ref_8","unstructured":"Zhang, L., Chu, R., Xiang, S., Liao, S., and Li, S.Z. (2007, January 27\u201329). Face detection based on multi-block lbp representation. Proceedings of the 2007 International Conference on Biometrics (ICB 2007), Crystal City, VA, USA."},{"key":"ref_9","unstructured":"Dalal, N., and Triggs, B. (2005, January 20\u201326). Histograms of oriented gradients for human detection. Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2005), San Diego, CA, USA."},{"key":"ref_10","first-page":"127","article-title":"Facial feature detection using Haar classifiers","volume":"21","author":"Wilson","year":"2006","journal-title":"J. Comput. Sci. Coll."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Wang, X., Han, T.X., and Yan, S. (October, January 27). An HOG-LBP human detector with partial occlusion handling. Proceedings of the 2009 IEEE 12th International Conference on Computer Vision (ICCV 2009), Kyoto, Japan.","DOI":"10.1109\/ICCV.2009.5459207"},{"key":"ref_12","unstructured":"OpenCV Dev. Team (2017, October 19). OpenCV 2.4.9.0 Documentation. Available online: https:\/\/docs.opencv.org\/2.4.9\/modules\/objdetect\/doc\/cascade_classification.html#featureevaluator-calcord."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Xia, C., Sun, S.F., Chen, P., Luo, H., and Dong, F.M. (2014, January 1\u20134). Haar-like and HOG fusion based object tracking. Proceedings of the 2014 Pacific Rim Conference on Multimedia (PCM 2014), Kuching, Malaysia.","DOI":"10.1007\/978-3-319-13168-9_18"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1016\/0031-3203(95)00067-4","article-title":"A comparative study of texture measures with classification based on featured distributions","volume":"29","author":"Ojala","year":"1996","journal-title":"Pattern Recognit."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1635","DOI":"10.1109\/TIP.2010.2042645","article-title":"Enhanced local texture feature sets for face recognition under difficult lighting conditions","volume":"19","author":"Tan","year":"2010","journal-title":"IEEE Trans. Image Process."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Ma, C., Trung, N.T., Uchiyama, H., Nagahara, H., Shimada, A., and Taniguchi, R. (2017, January 14\u201316). Mixed features for face detection in thermal image. Proceedings of the 2017 Thirteenth International Conference on Quality Control by Artificial Vision (QCAV 2017), Tokyo, Japan.","DOI":"10.1117\/12.2266836"},{"key":"ref_17","unstructured":"Viola, P., and Jones, M. (2001, January 8\u201314). Rapid object detection using a boosted cascade of simple features. Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2001), Kauai, HI, USA."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Jia, H.X., and Zhang, Y.J. (2007, January 22\u201324). Fast human detection by boosting histograms of oriented gradients. Proceedings of the Fourth International Conference on Image and Graphics (ICIG 2007), Chengdu, China.","DOI":"10.1109\/ICIG.2007.53"},{"key":"ref_19","unstructured":"Salas, Y.S., Bermudez, D.V., Pe\u00f1a, A.M.L., Gomez, D.G., and Gevers, T. (2012, January 4\u20137). Improving hog with image segmentation: Application to human detection. Proceedings of the 2012 14th International Conference on Advanced Concepts for Intelligent Vision Systems, Brno, Czech Republic."},{"key":"ref_20","unstructured":"Liao, S., Zhu, X., Lei, Z., Zhang, L., and Li, S.Z. (2007, January 27\u201329). Learning multi-scale block local binary patterns for face recognition. Proceedings of the 2007 International Conference on Biometrics (ICB 2007), Crystal City, VA, USA."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Jia, X., Yang, X., Zang, Y., Zhang, N., Dai, R., Tian, J., and Zhao, J. (2013, January 4\u20137). Multi-scale block local ternary patterns for fingerprints vitality detection. Proceedings of the 2013 International Conference on Biometrics (ICB 2013), Phuket, Thailand.","DOI":"10.1109\/ICB.2013.6612964"},{"key":"ref_22","unstructured":"Jiang, Y., and Ma, J. (2015, January 8\u201310). Combination features and models for human detection. Proceedings of the 2015 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2015), Boston, MA, USA."},{"key":"ref_23","unstructured":"Mita, T., Kaneko, T., and Hori, O. (2005, January 15\u201321). Joint haar-like features for face detection. Proceedings of the 2005 IEEE 10th International Conference on Computer Vision (ICCV 2005), Beijing, China."},{"key":"ref_24","unstructured":"Jin, H., Liu, Q., Lu, H., and Tong, X. (2004, January 18\u201320). Face detection using improved LBP under Bayesian framework. Proceedings of the 2004 Third International Conference on Image and Graphics (ICIG 2004), Hong Kong, China."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"2445","DOI":"10.1016\/j.patcog.2012.01.001","article-title":"A comparative study of thermal face recognition methods in unconstrained environments","volume":"45","author":"Hermosilla","year":"2012","journal-title":"Pattern Recognit."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"682","DOI":"10.1109\/TMM.2010.2060716","article-title":"A natural visible and infrared facial expression database for expression recognition and emotion inference","volume":"12","author":"Wang","year":"2010","journal-title":"IEEE Trans. Multimedia"},{"key":"ref_27","unstructured":"Karlinsky, L., Dinerstein, M., Levi, D., and Ullman, S. (2008, January 17\u201318). Combined model for detecting, localizing, interpreting and recognizing faces. Proceedings of the Workshop on Faces in \u2019Real-Life\u2019 Images: Detection, Alignment, and Recognition, Marseille, France."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Howse, J. (2014, January 10\u201312). Training detectors and recognizers in Python and OpenCV. Proceedings of the 2014 IEEE International Symposium on Mixed and Augmented Reality (ISMAR 2014), Munich, Germany.","DOI":"10.1109\/ISMAR.2014.6948516"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Puttemans, S., Can, E., and Goedem\u00e9, T. (March, January 27). Improving Open Source Face Detection by Combining an Adapted Cascade Classification Pipeline and Active Learning. Proceedings of the VISAPP 2017, Porto, Protugal.","DOI":"10.5220\/0006256003960404"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/17\/12\/2741\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T18:51:32Z","timestamp":1760208692000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/17\/12\/2741"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,11,27]]},"references-count":29,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2017,12]]}},"alternative-id":["s17122741"],"URL":"https:\/\/doi.org\/10.3390\/s17122741","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,11,27]]}}}