成功大學博碩士論文系統

簡易檢索 / 詳目顯示

回結果列表

研究生：	彭柏翔 Peng, Po-Hsiang
論文名稱：	智慧型人臉膚色截取模式之建構研究 An intelligent model for facial skin color detection
指導教授：	蕭世文 Hsiao, Shih-Wen
學位類別：	碩士 Master
系所名稱：	規劃與設計學院 - 工業設計學系 Department of Industrial Design
論文出版年：	2017
畢業學年度：	105
語文別：	英文
論文頁數：	63
中文關鍵詞：	人臉偵測、膚色擷取、灰界白平衡理論、光譜儀
外文關鍵詞：	face detection, gray world white balance theory, skin color capture, spectrometer
相關次數：	點閱：156 下載：1
分享至:	分享至facebook 分享至twitter

查詢本校圖書館目錄查詢臺灣博碩士論文知識加值系統勘誤回報

在現代的數位攝影世界裏，改變相片的顏色很容易，其中一個方法便是控制相機的白平衡來達到目的，很多的相機和手機都有著自動白平衡的功能，卻不適用人像相片，導致人臉有色彩偏差的問題產生，而有效的白平衡可使色彩回到人眼視覺所見之原狀。有鑒於此，本文提出一套基於膚色橢圓體的智慧膚色擷取方法。首先採用正視臉部的彩色大頭照，搭配兩眼與嘴巴三角點做膚色偵測搭配人臉偵測定位影像中人臉的位置，透過卷積神經網路建立準確的人臉特徵模型，以利找出影像中人臉的位置。透過膚色橢圓體的訓練結果，得以建立膚色模型，接著透過自創的灰界白平衡理論，檢視與修正照片中的膚色，以符合現實所視。藉由膚色規則與CIE 2000色差公式做修正完成，並以此相關理論建構出最優化的iMake-up程式。最後，利用數位光譜儀與自創程式交互驗證，透過相關性分析了解兩兩資料的相關程度為95%。本研究結果與儀器測試之結果相互是吻合。此方法可推廣至欲自主購買彩妝品者可以用影像搭配本研究程式，即可知道自己的實際膚色，而不需要購買昂貴精密儀器。實驗結果顯示，本文提出智慧型擷取膚色之方法相較於其他的方法與儀器能更快速有效率的了解自己皮膚顏色。

It is quite easy to change the color of photos in the modern world of digital photography; one of the methods is to control the white balance of cameras. Many cameras and mobile phones provide the function of automatic white balance. However, it is not suitable for portrait photos, as it causes color deviation of the human face. However, effective white balance can restore the color to the original state visible to the human eye. In view of this, this study proposes a set of intelligent skin color capture methods based on skin color ellipse. The front-view color mug shot was adopted first to match the facial triangle formed by the eyes and the mouth for skin color detection, so as to locate the position of the face in the image by means of human face detection. The accurate facial feature model was then established through convolutional neural networks (CNN) in order to help locate the position of the human face in the images. The skin color model was established by means of the training results of skin color ellipse, and the self-created gray world white balance theory was then used to review and correct the skin color in the photo to conform to what is seen in reality. The correction was completed by means of skin color planning, the CIE 2000 color difference formula and the most optimal iMake-up formula constructed in accordance with relevant theories. Finally, a digital spectrometer and self-created program were utilized for cross-validation, and the correlation analysis showed that the correlation of the data was 95%. The results of this study conform to the results tested by the instrument. The method can be popularized for those who plan to purchase cosmetics independently. They can use the images in combination with the study’s program to know their own actual skin color without needing to purchase an expensive precision instrument. The results show that the intelligent skin color capture method proposed in this study can help people understand their own skin color more rapidly and effectively compared to other methods and instruments.

TABLE OF CONTENTS
摘要	I
SUMMARY	II
ACKNOWLEDGEMENTS	III
TABLE OF CONTENTS	IV
LIST OF TABLES	VI
LIST OF FIGURES	VII
LIST OF SYMBOLS AND ABBREVIATIONS	IX
CHAPTER 1 INTRODUCTION	1
1.1 General Background Information	1
1.2 Purpose of the Study	2
1.3 Research Framework	3
1.4 Limitations of the Study	5
CHAPTER 2 LITERATURE REVIEW	6
2.1 RGB color space	6
2.2 CIE Lab color space	7
2.2.1 CIEDE2000 General Structure	9
2.3 Skin modeling	9
2.3.1 Application of color space in skin color model	10
2.4 Color detection	12
2.4.1 Face ++ face feature point positioning system	14
2.4.2 Eye and mouth detection related research	15
2.5 Spectrometer	17
2.5.1 The main function of the spectrometer	17
2.5.2 Ocean Optics USB4000	18
2.6 Panton color	19
CHAPTER 3 METHODS	21
3.1 Ellipsoid skin color	21
3.2 Triangle points study	22
3.3 The application of neural network method on the extraction point location in the eye and mouth area	23
3.3.1 A brief introduction to basic neural networks	24
3.3.2 Convolution layer	26
3.3.3 Sub-sampling layer	26
3.3.4 Fully connected layer	27
3.4 Skin rule	28
3.5 Gauss distribution	28
3.6 Gray world white balance theory	30
3.7 CIE 2000	31
3.8 Correlation analysis	33
CHAPTER 4 RESEARCH PROCESS	35
4.1 Skin color data collection	35
4.2 iMake- up Program Construction	36
4.2.1 iMake- up Program Presentation	36
4.2.2 Experimental Design of the Spectrometer	37
4.3 Automatic White Balance Construction of the Face	40
CHAPTER 5 RESULTS/ DISCUSSION	43
5.1 Presentation of Experimental Results	43
5.2 Discussion on the Experimental Results	48
CHAPTER 6 CONCLUSIONS	54
REFERENCE	55
Appendix 1 Skin color data collection	59
Appendix 2 The experimental results.	60
Appendix 3 Experimental results of skin color rule	61
Appendix 4 PANTONE SkinTone Guide	62
Appendix 5 The color application of VDL+ PANTONE	63
                                    

Alajel, K. M., Xiang, W., & Leis, J. (2011). Face detection based on skin color modeling and modified Hausdorff distance. Paper presented at the 2011 IEEE Consumer Communications and Networking Conference (CCNC), pp 399-404.
Chakraborty, B. K., Bhuyan, M., & Kumar, S. (2016). A Weighted Skin Probability Map for skin color segmentation. Paper presented at the Wireless Communications, Signal Processing and Networking (WiSPNET), International Conference on, pp 2133-2136.
Chihaoui, M., Elkefi, A., Bellil, W., & Amar, C. B. (2015). Implementation of skin color selection prior to Gabor filter and neural network to reduce execution time of face detection. Paper presented at the Intelligent Systems Design and Applications (ISDA), 2015 15th International Conference on, pp 341-346.
Dahal, B., Alsadoon, A., Prasad, P., & Elchouemi, A. (2016). Incorporating skin color for improved face detection and tracking system. Paper presented at the 2016 IEEE Southwest Symposium on Image Analysis and Interpretation (SSIAI), pp 173-176.
Garrett M. Johnson, Mark D. Fairchild (2003). A Top Down Description of S-CIELAB and CIEDE2000. Color Research & Application, 28, pp 425–435
Geng, J., Miao, Z., Liang, Q., & Wang, S. (2015). Rotation invariant ellipsoid projection for domain transfer in human skin detection. Paper presented at the Multimedia Signal Processing (MMSP), 2015 IEEE 17th International Workshop on, pp 1-5.
Hsiao, S. W., & Tsai, C. J. (2015). Transforming the natural colors of an image into product design: A computer‐aided color planning system based on fuzzy pattern recognition. Color Research & Application, 40(6), pp 612-625.
Hsu, R.-L., Abdel-Mottaleb, M., & Jain, A. K. (2002). Face detection in color images. IEEE transactions on pattern analysis and machine intelligence, 24(5), pp 696-706.
Hwang, I., Lee, S. H., Min, B., & Cho, N. I. (2013). Luminance adapted skin color modeling for the robust detection of skin areas. Paper presented at the 2013 IEEE International Conference on Image Processing, pp 2622-2625.
James, John (2007), Spectrograph Design Fundamentals. Cambridge University Press. ISBN 0-521-86463-1
Katz., Mitchell H. (2006) Multivariable Analysis - A Practical Guide for Clinicians. 2nd Edition. Cambridge University Press. ISBN 9780521549851. ISBN 052154985X doi:10.2277/052154985X
Khandelwal, G., Anandi, V., Deepak, M., Prasad, V. N., Manikantan, K., & Francis, F. (2015). Pedestrian detection using single box convergence with iterative DCT based haar cascade detector and skin color segmentation. Paper presented at the 2015 IEEE International Conference on Research in Computational Intelligence and Communication Networks (ICRCICN), pp 32-37.
Kheirkhah, E., & Tabatabaie, Z. S. (2015). A hybrid face detection approach in color images with complex background. Indian Journal of Science and Technology, 8(1), pp 49.
Kovac, J., Peer, P., & Solina, F. (2003, 22-24 Sept. 2003). Human skin color clustering for face detection. Paper presented at the The IEEE Region 8 EUROCON 2003. Computer as a Tool.
Lawrence, S., Giles, C. L., Ah Chung, T., & Back, A. D. (1997). Face recognition: a convolutional neural-network approach. IEEE Transactions on Neural Networks, 8(1), 98-113. doi: 10.1109/72.554195, pp 98-113
Lin, C.-F., Wu, C.-C., Yang, P.-H., & Kuo, T.-Y. (2009). Application of Taguchi method in light-emitting diode backlight design for wide color gamut displays. Journal of Display Technology, 5(8), pp 323-330.
Maia, D., & Trindade, R. (2016). Face Detection and Recognition in Color Images under Matlab. International Journal of Signal Processing, Image Processing and Pattern Recognition, 9(2), pp 13-24.
Milczarski, P., & Stawska, Z. (2014). Complex colour detection methods used in skin detection systems. Information Systems in Management, 3, pp 20-37.
Praseetha, V., & Vadivel, S. (2016). Face Extraction Using Skin Color and PCA Face Recognition in a Mobile Cloudlet Environment. Paper presented at the 2016 4th IEEE International Conference on Mobile Cloud Computing, Services, and Engineering (MobileCloud), pp 41-45.
Rahman, M. H., & Afrin, J. (2013). Human Face Detection in Color Images with Complex Background using Triangular Approach. Global Journal of Computer Science and Technology, 13(4).
Rout, S. K., Sahani, M., & Mohanty, M. N. (2015). Modified Color Brightness Preserving Bi-histogram Equalization with Variable Enhancement Degree for Restoration of Skin Color. Paper presented at the 2015 International Conference on Information Technology (ICIT), pp 88-93.
Satone, S., & Kharate, G. (2011). Face detection and recognition in color images. IJCSI, pp 467
Soriano, M., Martinkauppi, B., Huovinen, S., & Laaksonen, M. (2003). Adaptive skin color modeling using the skin locus for selecting training pixels. Pattern Recognition, 36(3), pp 681-690.
Sun, Y., Wang, X., & Tang, X. (2013). Deep Convolutional Network Cascade for Facial Point Detection. Paper presented at the Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference on, pp 3476-3483.
Sun, Y., Wang, X., & Tang, X. (2014). Deep learning face representation from predicting 10,000 classes. Paper presented at the Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 1891-1898
Tin, H. H. K. (2012). Robust Algorithm for face detection in color images. International Journal of Modern Education and Computer Science, 4(2), pp 31.
Tuchina, D. K., Bashkatov, A. N., Genina, E. A., & Tuchin, V. V. (2012). Glycerol diffusion in skin at glucose impact on tissue. Paper presented at the Communications and Photonics Conference (ACP), pp 1-1.
Verma, A., Raj, S. A., Midya, A., & Chakraborty, J. (2014). Face detection using skin color modeling and geometric feature. Paper presented at the Informatics, Electronics & Vision (ICIEV), 2014 International Conference on, pp 1-6.
Yoshikawa, H., Kikuchi, K., Yaguchi, H., Mizokami, Y., & Takata, S. (2012). Effect of chromatic components on facial skin whiteness. Color Research & Application, 37(4), pp 281-291.
Zeng, H., & Luo, M. (2011). Skin color modeling of digital photographic images. Journal of Imaging Science and Technology, 55(3), pp 30201-30201-30201-30212.
Zhou, E., Fan, H., Cao, Z., Jiang, Y., & Yin, Q. (2013). Extensive facial landmark localization with coarse-to-fine convolutional network cascade. Paper presented at the Proceedings of the IEEE International Conference on Computer Vision Workshops, pp 386-391.
Zhou, E., Fan, H., Cao, Z., Jiang, Y., & Yin, Q. (2013). Extensive facial landmark localization with coarse-to-fine convolutional network cascade. Paper presented at the Proceedings of the IEEE International Conference on Computer Vision Workshops, pp 386-391.

校內：2022-06-22公開
校外：2022-06-22公開

簡易檢索 / 詳目顯示

相關論文