PKT: fast color-based spatial model for human skin detection
Authors: 
Grace L. Samson, Joan LuAuthors Info & Claims
Pages 32807 - 32839
Abstract
We present a new detection method for color-based object detection, which can improve the performance of learning procedures in terms of speed, accuracy, and efficiency, using spatial inference, and algorithm. We applied the model to human skin detection from an image; however, the method can also work for other machine learning tasks involving image pixels. We propose (1) an improved RGB/HSL human skin color threshold to tackle darker human skin color detection problem. (2), we also present a new rule-based fast algorithm (packed k-dimensional tree --- PKT) that depends on an improved spatial structure for human skin/face detection from colored 2D images. We also implemented a novel packed quad-tree (PQT) to speed up the quad-tree performance in terms of indexing. We compared the proposed system to traditional pixel-by-pixel (PBP)/pixel-wise (PW) operation, and quadtree based procedures. The results show that our proposed spatial structure performs better (with a very low false hit rate, very high precision, and accuracy rate) than most state-of-the-art models.
References
[1]
Abbas A R, Farooq A O (2018) Human skin colour detection using bayesian rough decision tree. In: Al-mamory S, Alwan J, Hussein A (eds) New trends in information and communications technology applications. NTICT 2018. Communications in computer and information science, vol 938. Springer, Cham.
[2]
Albiol A, Torres L, Delp E J (2001) Optimum color spaces for skin detection. In proceedings 2001 780international conference on image processing. IEEE, (cat. No. 01CH37205), (1):122–124. https://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.1.6402&rep=rep1&type=pdf
[3]
Ali A, El-Hafeez T, Mohany Y (2019) A robust and efficient system to detect human faces based on facial features. Asian Journal of Research in Computer Science 2(4):1–12
[4]
Ban Y, Kim S K, Kim S, Toh K A, Lee S (2014) Face detection based on skin color likelihood. Pattern Recogn 47(4):1573–1585.
[5]
Baskan S, Bulut MM, and Atalay V Projection based method for segmentation of human face and its evaluation Pattern Recogn Lett 2002 23 14 1623-1629
[6]
Bentley JL Multidimensional binary search trees used for associative searching Commun ACM 1975 18 9 509
[7]
Berchtold S, Keim D A, Kriegel H P (2002) The X-tree: An index structure for high-dimensional data. Editted by Kevin Jeffay, Hongjiang Zhang, in the morgan kaufmann series in multimedia information and systems, readings in multimedia computing and networking, morgan kaufmann, pp 451–462.
[8]
Buolamwini J, Gebru T (2018) Gender shades: intersectional accuracy disparities in commercial gender classification. Conference on fairness, accountability and transparency, p 77–91. http://proceedings.mlr.press/v81/buolamwini18a.html
[9]
Bush I J, Abiyev R, Ma’aitah M K S, Altıparmak H (2018) Integrated artificial intelligence algorithm for skin detection. ITM Web of conferences, EDP Sciences, (16): p. 02004.
[10]
Chen J, Chen Y, Yu J, and Yang Z (2011) Comparisons with spatial autocorrelation and spatial association rule mining. Proceedings 2011 IEEE international conference on spatial data mining and geographical knowledge services, pp 32–37.
[11]
Chen HH, Ding JJ, and Sheu HT Image retrieval based on quadtree classified vector quantization Multimed Tools Appl 2014 72 2 1961-1984
[12]
Chen W, Wang K, Jiang H, and Li M Skin color modelling for face detection and segmentation: a review and a new approach Multimed Tools Appl 2016 75 2 839-862
[13]
Conci OVA (2009) A skin detection using HSV color space, Pedrini, & J. Marques de Carvalho, Workshops of Sibgrapi p 1–2
[14]
Dastane T, Rao V, Shenoy K, and Vyavaharkar D An effective pixel-wise approach for skin color segmentation-using pixel Neighbourhood technique Int J Recent Innov Trends Comput Commun 2018 6 3 182-186
[15]
Developers (2019) Classification: accuracy. Machine Learning Crash Course. https://developers.google.com/machine-learning/crash-course/classification/accuracy
[16]
ElFkihi S, DaoudiM, Aboutajdine D A (2006) A tree distribution for skin detection. The second international symposium on communications, control and signal processing (ISCCSP’06). https://www.eurasip.org/Proceedings/Ext/ISCCSP2006/defevent/papers/cr1259.pdf
[17]
Faria R A D, Hirata Jr R (2018) Combined correlation rules to detect skin based on dynamic color clustering. In proceedings of the 13th international joint conference on computer vision, imaging and computer graphics theory and applications (VISIGRAPP 2018) - Volume 5: VISAPP, pp 309–316.
[18]
Hassan E, Hilal A R, Basir O, (2017) Using ga to optimize the explicitly defined skin regions for human skin color detection, 30th IEEE Canadian conference on electrical and computer engineering, (CCECE 2017), p. 1–4., https://ieeexplore.ieee.org/abstract/document/7946699
[19]
Hua R, Wang Y (2017) Skin color detection based on super pixel. In proceedings of the 3rd IEEE international conference on computer and communications (ICCC), Chengdu, 2017, pp 1756–1760.
[20]
Jablonski NG Skin: a natural history 2006 Berkeley University of California Press
[21]
Jati H, Dominic D D (2008) Human skin detection using defined skin region. In 2008 international symposium on information technology. IEEE, (1) p. 1–4)
[22]
Kakumanu P, Makrogiannis S, and Bourbakis N A survey of skin-color modeling and detection methods Pattern Recogn 2007 40 3 1106-1122
[23]
Kawulok M, Kawulok J, Nalepa J (2014) Spatial-based skin detection using discriminative skin-presence features. Pattern Recogn Lett 41:3–13.
[24]
Khan R, Hanbury A, Stoettinger J (2010) Skin detection: a random forest approach. 2010 IEEE Int Conf Image Process 4613–4616
[25]
Kolkur S, Kalbande D, Shimpi P, Bapat C, Jatakia J 2017 Human skin detection using RGB, HSV and YCbCr color models., (arXiv preprint arXiv:1708.02694)
[26]
Legendre P (1993) Spatial autocorrelation: trouble or new paradigm? Ecology 74:1659–1673.
[27]
Khan R, Hanbury A, Stoettinger J (2010) Skin detection: A random forest approach. 2010 IEEE international conference on image processing, p 4613–4616. https://ieeexplore.ieee.org/document/5651638
[28]
Mahmoodi M R, Sayedi S M, Karimi F (2017) Color-based skin segmentation in videos using a multi-step spatial method. Multimed Tools Appl 76, 9785–9801.
[29]
Mark S, Alberto S (2020) Region-based analysis, in feature extraction and image processing for computer vision (fourth edition). Academic press. Pp 399-432. ISBN 9780128149768.
[30]
Mortazavi T M, Ebadati E O M (2019) An improved human skin detection and localization by using machine-learning techniques in RGB and YCbCr color spaces, PeerJ reprints
[31]
Nguyen-Trang T (2018) A new efficient approach to detect skin in color image using Bayesian classifier and connected component algorithm, Mathematical Problems in Engineering
[32]
Nikolskaia K, Ezhova N, Sinkov A, Medvedev M (2018) Skin detection technique based on HSV color model and SLIC segmentation method⋆ in proceedings of the 4th Ural workshop on parallel, distributed, and cloud computing for young scientists, Ural-PDC (pp. 123–135)
[33]
Nishad PM (2013) Various color spaces and color space conversion. J Global Res Comput Sci 4(1):44–48
[34]
National institute of standards and Technology (2011) Accessed [Online] Available at: https://www.nist.gov/itl/iad/imagegroup/colorferet-database. Accessed 23 March 2019
[35]
Omer M A, Junaid J M, Bilal A H, Adnan M K 2018 Implementation of NOGIE and NOWGIE for human skin detection, Int J Adv Comput Sci Appl (IJACSA), 9(7)
[36]
Patil P M, Patil Y M (2012) Robust skin color detection and tracking algorithm, Int J Eng Res Technol 1 (8)
[37]
Peer P, Solina F (1999) An automatic human face detection method. In Computer vision - CVWW'99: proceedings of the computer vision winter workshop, Rastenfeld, Austria, 8-10 February 1999. - Str. 122–130. https://plus.si.cobiss.net/opac7/bib/ferlj/1456724#full
[38]
Phung S L, Bouzerdoum A, Chai D (2002) A novel skin color model in ycbcr color space and its application to human face detection, IEEE international conference on image processing (ICIP’ 2002), (1) p.289–292
[39]
Ren X, Malik J (2003) Learning a classification model for segmentation proceedings of the 9th IEEE international conference on computer vision. IEEE Computer Society, Washington DC, pp 10–17., https://ieeexplore.ieee.org/document/1238308
[40]
Roheda S A multi-scale approach to skin pixel detection Electron Imaging 2017 4 18-23
[41]
Rossi J P, Queneherv P (1998) Relating species density to environmental variables in presence of spatial autocorrelation: a study case on soil nematodes distribution. Ecography. (21) p. 117–123
[42]
Samson GL and Lu J Pańkowska MR PaX-Dbscan: a proposed algorithm for improved clustering Studia Ekonomiczne. Zeszyty Naukowe, (269524th ed.) 2016 Katowice Wydawnictwo Uniwersytetu Ekonomicznego w Katowicach Retrieved from www.sbc.org.pl/Content/269524
[43]
Samson G L, Lu J (2018) Spatial clustering in large databases using packed X-tree. Egypt Comput Sci J 42(2):68–79. http://ecsjournal.org/Archive/Volume42_Issue2.aspx
[44]
Samson GL, Lu J, Showole AA (2014) “Mining Complex Spatial Patterns: Issues and Techniques”, Journal of Information & Knowledge Management (JIKM), World Scientific Publishing Co. Pte. Ltd., 13(02): 1–20.
[45]
Samson GL, Lu J, Usman MM, and Xu Q Lu J and Xu Q Spatial databases: an overview Ontologies and big data considerations for effective intelligence 2017 Hershey, PA IGI Global 111-149
[46]
Samson GL, Usman MM, Showole AA, Lu J, and Jazzaa H Large spatial database indexing with aX-tree Int J Sci Res Comput Sci Eng Inf Technol (IJSRCSEIT) 2018 3 3 759-773
[47]
Saxen F, Al-Hamadi A (2014). Superpixels for skin segmentation. In 20. Workshop Farbbildverarbeitung, Wuppertal (20), pp. 153-159.
[48]
Shen J, Zuo X, Li J, Yang W, and Ling H A novel pixel neighborhood differential statistic feature for pedestrian and face detection Pattern Recogn 2017 1 63 127-138
[49]
Simonite T (2018) Photo algorithms ID white men fine—black women, Not So Much, Wired. (https://www.wired.com/story/photo-lgorithms-id-white-men-fineblack-women-not-so-much)
[50]
Smit AJ, Smit JM, Botterblom GJ, and Mulder DJ Skin autofluorescence based decision tree in detection of impaired glucose tolerance and diabetes PLoS One 2013 8 6 e65592
[51]
Sun H-M Skin detection for single images using dynamic skin color modelling Pattern Recogn 2010 43 4 1413-1420
[52]
Tan W R, Chan C S, Pratheepan Y, Condell J (2012) A fusion approach for efficient human skin detection. IEEE trans Ind Inf 8(1):138–147 (T-II 2012)., https://ieeexplore.ieee.org/document/6051482
[53]
Tan WR, Chan CS, Yogarajah P, and Condell J A fusion approach for efficient human skin detection IEEE Trans Ind Inf 2012 8 1 138-147
[54]
Tavallali P, Yazdi M, and Khosravi MR Robust cascaded skin detector based on AdaBoost Multimed Tools Appl 2019 78 2 2599-2620
[55]
Thakkar D, (2018) Top five biometrics: face, Fingerprint, Iris, Palm and Voice, Bayometric. (https://www.bayometric.com/biometrics-face-finger-iris-palm-voice)
[56]
Vezhnevets V, Sazonov V, Andreeva A (2003) A survey on pixel-based skin color detection techniques, Proc. Graphicon 3:85–92. https://www.semanticscholar.org/paper/A-Survey-on-Pixel-Based-Skin-Color-Detection-Vezhnevets-Sazonov/bc1b5ff4fdb70c10a9aa0e9b8f6b260b2e1f4fed
[57]
Xu T, Wang Y, and Zhang Z Pixel-wise skin color detection based on flexible neural tree IET Image Process 2013 7 8 751-761
[58]
Zhang J, Wang H, Davoine F, Pan C (2012) Skin detection via linear regression tree. 21st IEEE international conference on pattern recognition. (ICPR2012), p. 1711–1714
[59]
Zortea M, Flores E, and Scharcanski J A simple weighted thresholding method for the segmentation of pigmented skin lesions in macroscopic images Pattern Recogn 2017 64 92-104
Index Terms
- PKT: fast color-based spatial model for human skin detection
Index terms have been assigned to the content through auto-classification.
Recommendations
Color based skin classification
Skin detection is used in applications ranging from face detection, tracking body parts and hand gesture analysis, to retrieval and blocking objectionable content. In this paper, we investigate and evaluate (1) the effect of color space transformation on ...
Combinatorial Color Space Models for Skin Detection in Sub-continental Human Images
IVIC '09: Proceedings of the 1st International Visual Informatics Conference on Visual Informatics: Bridging Research and PracticeAmong different color models HSV, HLS, YIQ, YCbCr, YUV, etc. have been most popular for skin detection. Most of the research done in the field of skin detection has been trained and tested on human images of African, Mongolian and Anglo-Saxon ethnic ...
Combining image and global pixel distribution model for skin colour segmentation
A local skin distribution model utilizing image pixel distribution.A fusion rule for combining local and the global skin pixel distribution model.Dynamic region growing to grow skin regions dynamically to minimize false detection error. Skin colour ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
© The Author(s) 2021.
Publisher
Kluwer Academic Publishers
United States
Publication History
Published: 01 September 2021
Accepted: 14 April 2021
Revision received: 03 February 2021
Received: 21 June 2019
Author Tags
Qualifiers
- Research-article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 30 Jan 2025