雷锋网 AI 科技评论按:7 月 12 日-7 月 14 日,2019 第四届全球人工智能与机器人峰会(CCF-GAIR 2019)于深圳正式召开。峰会由中国计算机学会(CCF)主办,雷锋网、香港中文大学(深圳)承办,深圳市人工智能与机器人研究院协办,得到了深圳市政府的大力指导,是国内人工智能和机器人学术界、工业界及投资界三大领域的顶级交流博览盛会,旨在打造国内人工智能领域极具实力的跨界交流合作平台。
7 月 12 日,香港中文大学(深圳)校长讲席教授、香港理工大学讲座教授、深圳人工智能与机器人研究院中心主任、IEEE Fellow 张大鹏教授为 CCF-GAIR 2019 主会场「中国人工智能四十年专场 」做了题为「生物特征识别的新进展-纪念中国人工智能40年」的大会报告。以下为张大鹏教授所做的大会报告全文,感谢张大鹏教授的修改与确认。
非常高兴受邀参加本次会议,让我有机会汇报我的最新工作。今天我的讲题是“纪念中国人工智能40周年”,而我本人是中国学位法公布后首届入学的研究生,也是哈工大毕业的首个计算机博士,从 1980 年入学开始算起,我基本见证了中国人工智能这 40 年的发展历程。
这是我研究生期间所能找到最早的一篇论文,选题与指纹识别有关。 1984 年,陈光熙教授是我的博士生导师,图片展示的是当年哈工大进行博士学位论文答辩的场景。
以下为哈工大计算机学科博士名录,我排在首位。
1985年,我到清华担任博士后,因此有幸成为常迵院士的学生。随后,我到中科院待了几个月时间,中科院当时给我颁发的一份聘书,我觉得非常有意义,因为该聘书将我的专业定性为图象处理、模式识别和人工智能,这在当时是非常少见的,一般都会称为计算机应用。
1988 年,我在加拿大拿到我的第二个博士学位,一直到 1995 年才来到香港,这时候已经过去了 23 年,这是我在香港工作时期的一些成果。
当下流行的人工智能,当年一般都称为模式识别,总的来说,模式识别是人工智能的重要组成部分,它与许多领域息息相关,是人工智能最流行的组成部分。模式识别是人工智能的重要组成部分,而生物特征识别又是模式识别的典型应用,因此,今天我将趁机汇报我们在这个领域的相关工作。
简而言之,我们将模式识别、图象处理做成了一个平台,紧接着通过该平台进行生物特征识别。我们在这方面做了许多新方法、新技术和新应用的探讨。其中,我们研发了 2DPCA 方法,截止目前引用率已经高达 3900 多次;此外,我们还在生物特征识别的鉴定方法上做了许多工作;鉴于生物特征识别主要更多是二维以及可见光的,我们又接着探讨三维以及波光谱的研究;针对三维生物特征识别上的工作,我们还发表了一本书。
我国首套掌纹系统
新技术方面,我们是国际上首个研究掌纹识别的团队。目前的生物特征识别手段主要是指纹、人脸、虹膜等,但它们却依然存在着诸多问题:
指纹——
作为接触式的生物特征识别方式,缺点包括有 5% 的人无法通过指纹进行识别,国际上也承认该方法的防伪能力存在缺陷。
人脸——
年纪增长和整容都可能给人脸带来极大的变化。
虹膜——
一旦患上眼疾便无法取得较理想的虹膜图像,且东方人的虹膜信息量整体不如西方人有效。
因此,掌纹识别被我们认为是值得探讨的方向,而且这是中国人独创的方法,受到了传统手相学的启发。我们发现,掌纹识别包含诸多新特征,当中包括几何信息、细节点信息、线特征、纹理信息、掌脉信息等,而且由于掌纹够复杂,因而防伪能力上也能有所保障。即便不小心沾上污渍,掌纹也能被有效地识别,这又是另外一项优点。
掌纹识别研究发展至今,我们有很多文章被发表,同时也获得了诸多奖项的肯定。比如,我们在 1998 年首次在国际上发表的掌纹识别文章,还出过掌纹识别的总结性书籍。国际上相关的 13篇文章中,我们占了其中 2 篇。这也是我国研发的首套掌纹系统。
系统落地——中医 & 美学
新应用方面,我想从两方面来展开。
一个是如何将生物特征识别运用至医学领域,尤其是与中医的结合。我们希望能够找到一种新方法,能将中医量化、客观化,进而把中医推向国际。我们主要从四个方面开展研究:视觉感知、嗅觉感知、听觉感知、触觉感知,以及综合性的融合感知。
首先是视觉感知,我们主要分析的舌像,通过颜色、纹理、形状等指标全方位对舌相进行探讨。比如针对特舌像的颜色,我们利用舌像的12个分布点创建了舌相主空间。针对舌头表面的反光点,包括润燥指数、淤斑淤点等,皆为有效信息。至于纹路,也是中医俗称的薄苔厚苔,我们也通过量化的方法进行了有效定义。随着库的体量变大,搜集到的特征变多,我们能借此进行亚健康以及病变判断。
文献清单:
– Book:TongueImageAnalysis,SpringerSingapore,306pp.2017(舌像分析)
– Book:TongueDiagnostics,AcademicPress.650p,2011(舌像分析)
– “Robusttonguesegmentationbyfusingregion-based&edge-basedapproaches”Expert Systems with Applications 21, 42, Nov, 8027-38. 2015. (舌像分割)
– “DetectingDiabetesMellitusandNonproliferativeDiabeticRetinopathyUsing Tongue Color, Texture, and Geometry Features”, IEEE Trans. on Biom. Eng. 2, 61, 491-501, 2014. (舌像应用)
– “StatisticalAnalysisofTongueimageforFeatureExtractionanddiagnostics”IEEE Trans. on Image Processing, 22 (12), 5336-47, 2013. (舌色分析 )
– “Ahighqualitycolorimagingsystemforcomputerizedtongueimageanalysis,”
– ExpertSystemwithApplications4,15,5854-66.2013.(仪器设计)
–“ANewTongueColorcheckerDesignbySpaceRepresentationforPreciseCorrection,”IEEEJournalofBiomedical&Health Informatics 2, 17, 381-391, 2013. (舌色校正)
– “TongueColorAnalysisforMedicalApplication,”Evidence-BasedComple-&Alter-Medi-,ID264742,11p,2013(舌色分析).
–“Fastmarchingoverthe2DGabormagnitudedomainfortonguebodysegmentation,”EURASIPJ.Adv.Sig.Proc.190.2013. (舌像分割)
– “Automatic tongue image segmentation based on gradient vector flow and region merging,” Neural Computing and Applications 8, 21, 1819-26, 2012. (舌像分割)
– “Tongueprint:AnovelbiometricsIdentifier,”PatternRecognition3,43,1071-1082,2010.(舌像应用)
– “Anoptimizedtongueimagecolorcorrectionscheme,”IEEETrans.onInf.Tech.inBio.6,14,1355-64,2010.(舌色校正)
– “Tongueshapeclassificationbygeometricfeatures,”Infor.Sci.2,180,312-324,2010.(舌型分析)
– “A snake-based approach to automated segmentation of tongue image using polar edge detector”, Inter.Journal of Image System & Technology 4, 16,103-112, 2007. (舌像分割)
– “Automatedtonguesegmentationinhyperspectralimagesformedicine,”AppliedOptics34,46,8328-34,2007.(舌像分割)
– “Classification of hyperspectral medical tongue images for tongue diagnosis,” Com. Med. Imaging & Graphics 31, 672-678,2007. (舌像应用)
– “TheBi-ellipticalDeformableContouranditsApplicationtoAutomatedTongueSegmentationinChineseMedicine,”IEEE Trans. on Medi. Ima. 8, 24, 946-56, 2005. (舌像分割)
–“ComputerizedDiagnosisfromTongueAppearanceusingQuantitativeFeatureClassification,”TheAmericanJournalofChinese Medicine (AJCM) 6, 33, 859-66, 2005. (舌像分析)
– TongueImageAnalysisforAppendicitisDiagnosis,Infor.Sci.3,175,160-176,2005.(舌像分析)
– ComputerizedTongueDiagnosisBasedonBayesianNetworks,IEEETrans.onBio.Eng.10,51,1803-10,2004.
第二个是嗅觉感知,指的是口腔气味,我们可以借此判断潜在的病理信息。我们创建了可以捕捉人体内部气味的传感器阵列,最终发现不同的类型的疾病会得到不同类型的波形。通过我们的研究,我们认为糖尿病与血检、呼吸等皆有一定关联,于是我们进一步探讨糖尿病的无损检测研究,对于是否患上糖尿病以及糖尿病等级都做了相应探讨。
文献清单:
– Book: Electronic Nose: Algorithmic Challenges, Springer, 2018. – Book: Breath Analysis for Medical Applications, Springer, 2017.
– “Breath analysis for detecting disea. on respiratory, metabolic & digestive system,” Journal of Biomedical Science and Engineering, 2019
– “Learning domain-invariant subspace using domain features & indepe- Maxmization,” IEEE Trans. on Cybernetics 2017
– “A novel medical e-nose signal analysis system,” Sensors 4,17,402.2017– “Efficient solutions for discreteness, drift & disturbance (3D) in electronic olfaction,” IEEE Trans. on SMC: Part A. 2017 (气味分析)
– “Temperature modulated gas sensing e-nose for low-cost/fast detection,” IEEE Journal 2,16,464-74,2016– “Calibration transfer & drift compensation of e-noses via coupled task learning,” Sensors & Actuators: B.225, 31, 288-297. 2016(气味分析)
– “Correcting instrumental variation & time-varying drift: A transfer learning approach with autoencoders,”IEEE TIM 9, 65, 2012-22. 2016(系统设计)
– “A novel semi-supervised learning approach in artificial olfaction for e-nose application,” IEEE Sensor
Journal 12, 16, 4919-31. 2016(系统设计)
– “Improving the transfer ability of prediction models for electronic noses,” Sensors & Actuators: B.Chemical 220, 115-124. 2015(仪器设计)
– “Domain adaptation extreme learning machines for drift compensation in e-nose systems,” IEEE Trans.on IM 7, 64, 1790-1801. 2015(气味分析)– “Feature selection and analysis on correlated gas sensor data with recursive feature elimination,” Sensors & Actuators: B. Chemical, 212, 353-363. 2015(气味分析)
– “Design of breath analysis system for diabetes diagnosis & blood glucose level prediction”, IEEE Trans. on Biomedical Engineering 11, 61. 2014(仪器设计)
– “Non-invasive Blood Glucose Monitoring for Diabetics by Means of Breath Signal Analysis,” Sensors & Actuators B 173,106-113, 2012 (气味分析)
– “Sparse representation-based classification for Breath sample identification,” Sensors & Actuators B
1,158, 43-53, 2011(气味分析)
– “A LDA based sensor selection approach in breath system,” Sensors & Actuators B 157, 265-274, 2011
– “A novel breath analysis system based on electronic olfaction,” IEEE TBE 11, 57, 2753–63, 2010
第三个是触觉感知,我们按照中医的三部九侯思路设计了相应系统。鉴于脉象是血流通过内脏器官流到人的末梢,带有内脏器官的病理信息,因此我们一直坚定脉象无法被ECG取代。我们通过生物特征识别技术对大量特征进行提取,然后进行优化,最终形成了对不同波形的分析。
文献清单:
– Book: Computational Pulse Signal Analysis, Springer, Singapore, 2018
– “Radial artery pulse waveform analysis based on curve fitting using discrete Fourier series”
Computer Methods and Programs in Biomedicine 2019
– “A Robust Pulse Acquisition on Multisensor & Signal Quality Assessment,” IEEE TIM, 2019
– “Generalized Feature Extraction for Wrist Pulse Analysis: from 1-D Time Series to 2-D Matrix,” IEEE JBHI 4, 21, 978-985. 2017(脉象分析)
– “A Robust Signal Preprocessing Framework for Wrist Pulse Analysis,” Biomedical Signal Processing and Control 23, 62-75. 2016(脉象分析)
– “Comparison of Three Different Types of Wrist Pulse Signals by Their Physical Meanings and Diagnosis Performance,” IEEE JBHI 1, 20, 119-127. 2016 (系统设计)
– “A novel multi-channel wrist pulse system with different sensor arrays,” IEEE TCM 7, 64, 2020-34. 2015
– “An Optimal Pulse System Design by Multi-channel Sensors Fusion,” IEEE Journal of Biomedical and Health Informatics (J-BHI) 2, 20, 450-9, 2015(系统设计)
– “A Compound Pressure Signal Acquisition System for Multi-Channel Wrist Pulse Analysis”, IEEE Trans. TIM 6, 63, 1556-65, 2014(仪器设计)
– “Combination of heterogeneous features for wrist pulse blood flow signal diagnosis via multiple kernel learning”, IEEE Trans. Infor. Tech. in BioMedicine 4, 16, 598-606, 2012(脉象分析)
– “Computerized wrist pulse signal diagnosis using modified auto-regressive models,” Journal of Medical Systems 35(3): 321-328, 2011(脉象分析)
– “Classification of Pulse Waveforms Using Edit Distance with Real Penalty.” EURASIP J. on Advances in Signal Pro., 303140: 1-9, 2010(脉象分析)
– “Wrist Blood Flow Signal-based Computerized Pulse Diagnosis Using Spatial and Spectrum Features.” Journal of Biomedical Science and Engineering, 3(4): 361-366, 2010(脉象分析)
– “Wrist Pulse Signal Diagnosis using Modified Gaussian Models and Fuzzy C-Means Classification,” Medical Eng. & Phy. 31, 1283-1289, 2009(脉象分析)
– “Baseline Wander Correction in Pulse Waveforms Using Wavelet-based Cascaded Adaptive Filter”, Computers in Biology and Medicine 37, 5, 716-731, 2007(脉象分析)
– “Arrhythmia Pulses Detection by Ziv-Lempel Complexity Analysis”, RURASIP Journal on Applied Signal Processing 2006, 1-12, 2006(脉象分析)
– “Wavelet-based Cascaded Adaptive Filter for Removing Baseline Drift in Pulse Waveforms,” IEEE Trans. on Biome. Eng. 52,11,1973-1975, 2005(脉象分析)
– “Modern researcher on Traditional Chinese Pulse Diagnosis”, European Journal of Oriental Medicine 4, 5, 46-54, 2004(脉象分析)
– “Objectifying Researches on Traditional Chinese Pulse Diagnosis”, Informatics Medical Slovenica, August, 56-63, 2003(脉象分析)
最后一个是听觉感知。我们希望通过我们的技术,可以找到对话中隐含的病理信息,因此我们系统探讨了它与发音、疾病之间的关系。这个工作相应来说进行得较晚,直到17年才有第一篇论文,而这几年也陆续有文章发表。
文献清单:
– Book: Voice Analysis for Medical Applications, Springer, 2019
– “Joint Learning for Voice Based Disease Detection,” Pattern Recognition 87,130-39, 2019.
– “Computerized voice analysis in biomedical field & its open challenges,” IEEE Access, 2018.
– “Influence of sampling rate on voice analysis for the detection of
Parkinson‘s disease,” The Journal of the Acoustical Society of America, 2018.– “Learning acoustic features to detect Parkinson’s disease,” Neurocomputing, 2018.
– “GMAT: Glottal closure instants detection based on the Multiresolution Absolute TKEO,” Digital Signal Processing 69, 286-299. 2017.
中医强调“望闻问切”,所以我们在融合感知方面也展开了许多工作,将单一的舌、脉等感知经过融合达到更好的效果。我们将之作为当下的重点工作进行了相应研发。
文献清单:
– Book:InformationFusion:TechnologiesandApplications,Springer,2019
–“Visual Classification With Multikernel Shared Gaussian Process Latent Variable Model,” IEEE Trans. on Cybernetics 8, 49, 2886-99, 2019.
–“Generative Multi-view and Multi-feature Learning for Classification,” Information Fusion 41, 215-26, 2019. –“Body Surface Feature-based Multi-modal Learning for Diabetes Mellitus Detection,” Information Sciences.472, Jan. 1-14. 2019.
–“Shared Auto-encoder Gaussian Process Latent Variable Model for Visual Classification,” IEEE TNNLS 9,29, 4272-86. 2018
–“Joint discriminative and collaborative representation for fatty liver disease diagnosis,” Expert Systems
with Applications 89, Dec., 31-40. 2017
–“Joint Similar and Specific Learning for Diabetes Mellitus and Impaired Glucose Regulation Detection,” Information Science 384, 191-204. 2017
此外,生物特征识别作为一个平台,我们还希望将它应用至美学鉴别领域。
尽管每个人对美的看法不尽相同,但我们认为美是具有公认特征的,因此我们希望通过捕捉公认特征来实现美的客观化。在这过程中,我们成功解决了所谓的平均脸问题,即用于进行美的鉴别的标准。我们通过对61个国家的人脸库进行分析,获得所有关于美的规则,其中包括了中国人的三庭五眼,以及西方人的黄金比例等,以找到最接近美的公共标准。
我们最终建立了一个窗口,让人们得以实时对这些规则进行调整。
最后,跟大家强调一下,我们现在成立了深圳市人工智能与机器人研究中心,主要致力于这方面的研究,希望能有更多人加盟到我们的队伍中来。谢谢大家。
雷锋网 AI 科技评论