光散射学报, 2022, 34 (3): 231, 网络出版: 2023-02-04  

基于多光谱成像技术的面部痤疮识别研究

The Identification Research of Facial Acne Based on Multispectral Imaging Technology
作者单位
长春理工大学物理学院 吉林省光谱探测科学与技术重点实验室,吉林 长春 130022
摘要
痤疮是属于丙酸杆菌皮肤病脉的一种慢性炎症, 它危害着人体健康。虽然市面上存在痤疮识别手段, 但其仪器较大且费用昂贵, 目前尚无民用级别的痤疮识别系统投入使用。本文提出一种基于多光谱成像技术的面部痤疮识别方案, 即利用多光谱相机设备, 分别对面部正常与不同严重程度痤疮皮肤进行多光谱图像信息采集, 通过图像处理方法对采集的信息进行多光谱图像分析, 并通过光谱反演算法获取光谱信息。然后将反演出的正常和不同严重程度痤疮皮肤的反射率谱线, 与高精度光谱仪在同等实验条件下探测的谱线趋势进行对比。最后建立支持向量机(support vector machine, SVM)面部痤疮三度四级分类模型, 准确率为90%, 验证了基于多光谱成像技术对面部痤疮无创识别与分类的可行性。
Abstract
Acne is a chronic inflammation of the skin veins of Propionibacterium, which endangers human health. Although there are acne identification methods on the market, their instruments are large and expensive, and there is currently no civilian-level acne identification system in use. This paper proposes a facial acne recognition scheme based on multispectral imaging technology, that is, using multispectral camera equipment to collect multispectral image information for normal and acne skin of different severity on the face, multispectral image analysis of the collected information by image processing method, and obtain spectral information through spectral inversion algorithm. The reflectance lines of normal and acne of different severities are then compared with the trend of the lines detected by the high-precision spectrometer under the same experimental conditions. Finally, a three-degree and four-level classification model of facial acne in the support vector machine was established with an accuracy rate of 90%, which verified the feasibility of non-invasive identification and classification of facial acne based on multispectral imaging technology.
参考文献

[1] Roshaslinie Ramli,Aamir Saeed Malik,et al. Acne analysis, grading and computational assessment methods: an overview[J]. Skin Research and Technology 2012,18(1): 1-14.

[2] SHEN Xiaolei, ZHANG Jiachi, et al. An Automatic Diagnosis Method of Facial Acne Vulgaris Based on Convolutional Neural Network[J]. Scientific Reports, 2018,8(11):5839.

[3] 刘慧. VISIA对痤疮患者面部皮损评价的研究及痤疮患者认知度调查[D].南方医科大学,2019.(Liu Hui,VISIA's study on the evaluation of facial lesions in acne patients and the investigation of awareness of acne patients[D].Southern Medical University,2019.)

[4] 郭静,李林峰.痤疮临床分级方法及其评价[J].中华医学美学美容杂志,2002(05):48-49.(Guo Jing, Li Linfeng.Clinical grading methods for acne and its evaluation[J].Chinese Journal of Medical Aesthetics and Cosmetology,2002(05):48-49.)

[5] InGle JrJD,Crouch SR.Spectrochemical analysis[J].1988.

[6] 郭长青. 基于多光谱成像的皮肤检测算法研究[D].北京交通大学,2014.(Guo Changqing.Research on skin detection algorithm based on multispectral imaging[D].Beijing Jiaotong University,2014.)

[7] 万友铭. 基于多光谱的面部肤质测评系统的设计与实现[D].华中科大学,2019.(Wan Youming.Design and implementation of multi-spectral facial skin assessment system[D].Huazhong University of Science and Technology,2019.)

[8] Shen X, Zhang J, Yan C, et al. An Automatic Diagnosis Method of Facial Acne Vulgaris Based on Convolutional Neural Network[J]. Sci Rep, 2017, 8(1).

[9] Tighe-Smart S. Skin Revitalisation: An Exploration of the Methods Used in Aesthetic Dermatology. Journal of Aesthetic Nursing[J]. 2018,7(5): 248-254.

[10] 胡妙春. 多光谱人脸活体检测特征的研究[D].北京交通大学,2015.(Hu Miaochun.Study on the characteristics of multispectral face in vivo detection[D].Beijing Jiaotong University,2015.)

[11] 孟如松,蔡瑞康,赵广,姜志国,周付根,史勤检.多光谱皮肤图像分析管理系统的研究与应用[J].解放军医学志,1999(06):469-471.(Meng Rusong, Cai Ruikang, Zhao Guang, JiangZhiguo, Zhou Fufen, Shi Qinjian.Research and application of multispectral skin image analysis management system[J].Medical Journal of the People's Liberation Army,1999(06):469-471.)

[12] 邱雁.漫反射光谱的理论与应用研究[D].上海:同济大学, 2007.(Qiu Yan.Theoretical and applied research on diffuse reflectance spectroscopy[D].Shanghai:Tongji University,2007.)

[13] 周园松.人脸肤质检测与评价系统的研究[D].南京理工大学,2020.(Zhou Yuansong.Research on human skin quality detection and evaluation system[D].Nanjing University of Science and Technology,2020.)

[14] 单晓峰. 5-氨基乙酰丙酸乳剂短程、靶向接触联合LED红光照射治疗轻中度炎症性痤疮的研究[D].安徽医科大学,2016.(Shan Xiaofeng. A study of 5-aminolevulinic acid emulsion with short-course, targeted exposure combined with LED red light irradiation for mild to moderate inflammatory acne[D].Anhui Medical University,2016.)

[15] 黄文慧,王宏伟,赵永亮.寻常型痤疮和脂溢性皮炎患者面部紫外线诱导红色荧光物质的荧光光谱学研究[J].中华医学美学美容杂志,2015,21(01):37-40.(Huang Wenhui, Wang Hongwei, Zhao Yongliang.Fluorescence spectroscopy of UV-induced red fluorescent substances in the face of patients with acne vulgaris and seborrheic dermatitis[J].Chinese Journal of Medical Aesthetics and Cosmetology,2015,21(01):37-40.)

[16] 曹璞.近红外光谱分析在医学上的应用[J].光机电信息,2006(09):51-53.(Cao Pu.Application of near-infrared spectroscopy in medicine[J].Opto-electromechanical information,2006(09):51-53.)

[17] 王慢想,李强.卟啉及其衍生物的紫外-可见光谱[J].光谱实验室,2011,28(03):1165-1169.(Wang Manxiang, Li Qiang.UV-Vis spectrum of porphyrins and their derivatives[J].Spectroscopy Laboratory,2011,28(03):1165-1169.)

[18] 裴经和. 卟啉衍生物自组装纳米粒子的制备及其性能研究[D].长春理工大学,2021.(Pei Jinghe. Preparation and properties of porphyrin derivatives self-assembled nanoparticles[D].Changchun University of Science and Technology,2021.)

[19] 陶伟森. 基于支持向量机的羊毛与羊绒纤维识别研究[D].湖北工业大学,2018.(Tao Weisen.Research on wool and cashmere fiber identification based on support vector machine[D].Hubei University of Technology,2018.)

[20] 庞惠文, 张增红.基于数字图像处理的条码图像二值化处理研究[A].轻工科技, 2021.(Pang Huiwen, Zhang Zenghong.Research on binary processing of barcode images based on digital image processing[A].Light Industry Technology,2021.)()

孙哲, 任玉, 蔡红星, 周建伟, 蒋雨鹏. 基于多光谱成像技术的面部痤疮识别研究[J]. 光散射学报, 2022, 34(3): 231. SUN Zhe, REN Yu, CAI Hongxing, ZHOU Jianwei, JIANG Yupeng. The Identification Research of Facial Acne Based on Multispectral Imaging Technology[J]. The Journal of Light Scattering, 2022, 34(3): 231.

关于本站 Cookie 的使用提示

中国光学期刊网使用基于 cookie 的技术来更好地为您提供各项服务,点击此处了解我们的隐私策略。 如您需继续使用本网站,请您授权我们使用本地 cookie 来保存部分信息。
全站搜索
您最值得信赖的光电行业旗舰网络服务平台!