北京生物醫(yī)學(xué)工程

基于舌圖像深度特征融合的中醫(yī)體質(zhì)分類方法研究

Preliminary study on traditional Chinese medicine constitution classification method based on tongue image feature fusion

作者：周浩胡廣芹張新峰

單位：北京工業(yè)大學(xué)信息學(xué)部（北京 100124）

關(guān)鍵詞：卷積神經(jīng)網(wǎng)絡(luò)；特征融合；舌圖像；體質(zhì)類型分類；中醫(yī)

分類號： R318.04

出版年·卷·期（頁碼）：2020·39·3（221-226）

摘要：

目的在基于舌圖像的中醫(yī)體質(zhì)類型分類中，舌圖像的類間距小，傳統(tǒng)手工特征提取時存在底層特征不能夠充分表達(dá)舌圖像所包含的全部信息等問題。因此本文提出一種基于深度網(wǎng)絡(luò)特征層融合的體質(zhì)類型分類方法，以提高體質(zhì)類型分類的準(zhǔn)確率。方法通過比較不同網(wǎng)絡(luò)模型對舌圖像的分類表現(xiàn)，及對不同網(wǎng)絡(luò)層的特征表達(dá)能力的分析，選取將淺層特征與高層語義特征進(jìn)行融合的方法。該深度特征融合方法基于Alexnet網(wǎng)絡(luò)進(jìn)行改進(jìn)，依據(jù)誤差權(quán)重，對各層特征進(jìn)行融合。并采用983張舌圖像，對氣虛質(zhì)、痰濕質(zhì)和濕熱質(zhì)三種體質(zhì)類型的分類問題進(jìn)行仿真實驗。結(jié)果相比傳統(tǒng)特征提取與原始深度網(wǎng)絡(luò)，本文方法的準(zhǔn)確率由傳統(tǒng)分類方法的54.3%提高到了77%。結(jié)論基于深度特征融合的方法將淺層特征與深度特征融合，充分表達(dá)了圖像的語義信息，對中醫(yī)輔助辨識、臨床、教學(xué)和科研具有極其重要的研究意義。

Objective The traditional manual feature extraction is mainly based on the bottom features, which can not adequately express all the information contained in the tongue image. In order to improve the accuracy of physique classification, a method of physique classification based on feature layer fusion of deep network is proposed in this paper. Methods Different network models have different classification performance for tongue images, and different network layers have different feature description capabilities. This method fuses shallow features with high-level semantic features, avoides the interference of human factors in traditional special extraction. The method of depth feature fusion is improved on Alexnet network. According to the error weight, the features of each layer are fused. Based on 983 tongue image data sets, this paper discusses the classification of three constitutional types: Qi deficiency, phlegm-dampness and damp-heat. Results The simulation results show that compared with the traditional feature extraction and the original depth network, the accuracy of this method is improved from 54.3% to 77%. Conclusion The method based on depth feature fusion is proposed to fuse shallow features with depth features, which fully expresses the semantic information of images. It is of great significance to the research of assistant identification, clinical, teaching and scientific research of traditional Chinese medicine.

參考文獻(xiàn)：

[1]李曉彥.治未病理念在體檢亞健康人群健康指導(dǎo)中的應(yīng)用效果探析[J].護(hù)理研究,2018,32(20):3309-3310. Li XY.Probe into efect of concept of zhiweibing for health examination of sub-health crowds[J].Chinese Nursing Resarch ,2018,32(20):3309-3310.

[2]俞若熙,王琦,王濟(jì),等.體質(zhì)辨識應(yīng)用研究現(xiàn)狀分析[J].中國中醫(yī)藥信息雜志,2013,20(2):107-109.

[3]洪樂,葉雙林,劉婷婷,等.基于舌象分析的中醫(yī)體質(zhì)辨識系統(tǒng)的研究思路[J].中國中醫(yī)藥現(xiàn)代遠(yuǎn)程教育,2016,14(2):34-36. Hong L,Ye SL,Liu TT, et al.Research on constitution of traditional Chinese medicine identification system based on tongue manifestation[J].Chinese Medicine Modern Distance Education Of China,2016,14(2):34-36.

[4]王琦.9種基本中醫(yī)體質(zhì)類型的分類及其診斷表述依據(jù).北京中醫(yī)藥大學(xué)學(xué)報,2005,28(4):1-8. Wang Q,Classification and diagnosis basis of nine basic constitutions in Chinese medicine[J].Journal of Beijing University of Traditional Chinese Medicine,2005,28(4):1-8.

[5]李博聰,黃慶梅,陳松鶴,等.基于CIELAB空間的中醫(yī)舌色分析方法[J].世界科學(xué)技術(shù)中醫(yī)藥現(xiàn)代化,2007,9(3):28-32. Li BC,Huang QM,Chen SH, et al. CIELAB color space based classification of tongue colors[J].World Science and Technology Modernization of Traditional Chinese Medicine and Materia Medical,2007,9(3):28-32.

[6]張新峰,沈蘭蓀,劉垚巍,等.基于粗糙集與SVM概率輸出的中醫(yī)舌象特征融合方法研究[J].世界科學(xué)技術(shù)：中醫(yī)藥現(xiàn)代化,2007,9(5):122-128. Zhang XF,Shen LS,Liu YW,et al.Ａ Study of tongue manifestation feature fusion using rough set and SVM probability[J].World Science and Technology Modernization of Traditional Chinese Medicine and Materia Medical,2007,9(5):122-128.

[7]胡繼禮,闞紅星.基于卷積神經(jīng)網(wǎng)絡(luò)的舌象分類[J].安慶師范大學(xué)學(xué)報(自然科學(xué)版),2018(4):44-49. Hu JL,Kan XH.Tongue classification based on convolutional neural network[J].Journal of Anqing Normal University(Natural Science Edition),2018(4):44-49.

[8]楊晶東,張朋.基于遷移學(xué)習(xí)的全連接神經(jīng)網(wǎng)絡(luò)舌象分類方法[J].第二軍醫(yī)大學(xué)學(xué)報,2018,39(8):897-902. Yang JD,Zhang P. Tongue image classification method based on transfer learning and fully connected neural network[J]. Academic Journal of Second Military Medical University, 2018,39(8):897-902.

[9]Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks[C]//International Conference on Neural Information Processing Systems. Red Hook, NY:Curran Associates Inc,2012:1097-1105.

[10]Szegedy C , Liu N W , Jia N Y , et al. Going deeper with convolutions[C]// 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Boston：IEEE Computer Society, 2015.

[11]He K,Zhang X, Ren S,et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. Las Vegas：IEEE, 2016: 770-778.

[12]韓立博, 胡廣芹, 張新峰, 等.基于直方圖均衡化的伽馬校正和K-means聚類的舌象苔質(zhì)分離方法[J]. 北京生物醫(yī)學(xué)工程, 2019,38(1):1-6. Han LB,Hu GQ,Zhang XF,et al. Separation method of tongue coating and body of tongue image based on histogram equalization and gamma correction and K-means clustering[J].Beijing Biomedical Engineering,2019,38(1):1-6.

[13]劉斌, 胡廣芹, 張新峰, 等. 一種改進(jìn)的中醫(yī)舌苔厚度自動描述方法[J]. 北京生物醫(yī)學(xué)工程, 2018, 37(2): 157-163. Liu B,Hu GQ,Zhang XF,,et al. An improved automatic description method of tongue coating thickness in Chinese medicine[J] .Beijing Biomedical Engineering,2018, 37(2): 157-163.

服務(wù)與反饋：

【文章下載】【加入收藏】

提示：您還未登錄，請登錄！點此登錄

51黑料吃瓜在线观看,51黑料官网|51黑料捷克街头搭讪_51黑料入口最新视频