0
本文作者: 黃善清 | 2019-07-16 10:55 | 專題:CCF-GAIR 2019 |
雷鋒網(wǎng) AI 科技評論按:7 月 12 日-7 月 14 日,2019 第四屆全球人工智能與機(jī)器人峰會(huì)(CCF-GAIR 2019)于深圳正式召開。峰會(huì)由中國計(jì)算機(jī)學(xué)會(huì)(CCF)主辦,雷鋒網(wǎng)、香港中文大學(xué)(深圳)承辦,深圳市人工智能與機(jī)器人研究院協(xié)辦,得到了深圳市政府的大力指導(dǎo),是國內(nèi)人工智能和機(jī)器人學(xué)術(shù)界、工業(yè)界及投資界三大領(lǐng)域的頂級交流博覽盛會(huì),旨在打造國內(nèi)人工智能領(lǐng)域極具實(shí)力的跨界交流合作平臺(tái)。
7 月 12 日,香港中文大學(xué)(深圳)校長講席教授、香港理工大學(xué)講座教授、深圳人工智能與機(jī)器人研究院中心主任、IEEE Fellow 張大鵬教授為 CCF-GAIR 2019 主會(huì)場「中國人工智能四十年專場 」做了題為「生物特征識(shí)別的新進(jìn)展-紀(jì)念中國人工智能40年」的大會(huì)報(bào)告。以下為張大鵬教授所做的大會(huì)報(bào)告全文,感謝張大鵬教授的修改與確認(rèn)。
非常高興受邀參加本次會(huì)議,讓我有機(jī)會(huì)匯報(bào)我的最新工作。今天我的講題是“紀(jì)念中國人工智能40周年”,而我本人是中國學(xué)位法公布后首屆入學(xué)的研究生,也是哈工大畢業(yè)的首個(gè)計(jì)算機(jī)博士,從 1980 年入學(xué)開始算起,我基本見證了中國人工智能這 40 年的發(fā)展歷程。
這是我研究生期間所能找到最早的一篇論文,選題與指紋識(shí)別有關(guān)。 1984 年,陳光熙教授是我的博士生導(dǎo)師,圖片展示的是當(dāng)年哈工大進(jìn)行博士學(xué)位論文答辯的場景。
以下為哈工大計(jì)算機(jī)學(xué)科博士名錄,我排在首位。
1985年,我到清華擔(dān)任博士后,因此有幸成為常迵院士的學(xué)生。隨后,我到中科院待了幾個(gè)月時(shí)間,中科院當(dāng)時(shí)給我頒發(fā)的一份聘書,我覺得非常有意義,因?yàn)樵撈笗鴮⑽业膶I(yè)定性為圖象處理、模式識(shí)別和人工智能,這在當(dāng)時(shí)是非常少見的,一般都會(huì)稱為計(jì)算機(jī)應(yīng)用。
1988 年,我在加拿大拿到我的第二個(gè)博士學(xué)位,一直到 1995 年才來到香港,這時(shí)候已經(jīng)過去了 23 年,這是我在香港工作時(shí)期的一些成果。
當(dāng)下流行的人工智能,當(dāng)年一般都稱為模式識(shí)別,總的來說,模式識(shí)別是人工智能的重要組成部分,它與許多領(lǐng)域息息相關(guān),是人工智能最流行的組成部分。模式識(shí)別是人工智能的重要組成部分,而生物特征識(shí)別又是模式識(shí)別的典型應(yīng)用,因此,今天我將趁機(jī)匯報(bào)我們在這個(gè)領(lǐng)域的相關(guān)工作。
簡而言之,我們將模式識(shí)別、圖象處理做成了一個(gè)平臺(tái),緊接著通過該平臺(tái)進(jìn)行生物特征識(shí)別。我們在這方面做了許多新方法、新技術(shù)和新應(yīng)用的探討。其中,我們研發(fā)了 2DPCA 方法,截止目前引用率已經(jīng)高達(dá) 3900 多次;此外,我們還在生物特征識(shí)別的鑒定方法上做了許多工作;鑒于生物特征識(shí)別主要更多是二維以及可見光的,我們又接著探討三維以及波光譜的研究;針對三維生物特征識(shí)別上的工作,我們還發(fā)表了一本書。
我國首套掌紋系統(tǒng)
新技術(shù)方面,我們是國際上首個(gè)研究掌紋識(shí)別的團(tuán)隊(duì)。目前的生物特征識(shí)別手段主要是指紋、人臉、虹膜等,但它們卻依然存在著諸多問題:
指紋——
作為接觸式的生物特征識(shí)別方式,缺點(diǎn)包括有 5% 的人無法通過指紋進(jìn)行識(shí)別,國際上也承認(rèn)該方法的防偽能力存在缺陷。
人臉——
年紀(jì)增長和整容都可能給人臉帶來極大的變化。
虹膜——
一旦患上眼疾便無法取得較理想的虹膜圖像,且東方人的虹膜信息量整體不如西方人有效。
因此,掌紋識(shí)別被我們認(rèn)為是值得探討的方向,而且這是中國人獨(dú)創(chuàng)的方法,受到了傳統(tǒng)手相學(xué)的啟發(fā)。我們發(fā)現(xiàn),掌紋識(shí)別包含諸多新特征,當(dāng)中包括幾何信息、細(xì)節(jié)點(diǎn)信息、線特征、紋理信息、掌脈信息等,而且由于掌紋夠復(fù)雜,因而防偽能力上也能有所保障。即便不小心沾上污漬,掌紋也能被有效地識(shí)別,這又是另外一項(xiàng)優(yōu)點(diǎn)。
掌紋識(shí)別研究發(fā)展至今,我們有很多文章被發(fā)表,同時(shí)也獲得了諸多獎(jiǎng)項(xiàng)的肯定。比如,我們在 1998 年首次在國際上發(fā)表的掌紋識(shí)別文章,還出過掌紋識(shí)別的總結(jié)性書籍。國際上相關(guān)的 13篇文章中,我們占了其中 2 篇。這也是我國研發(fā)的首套掌紋系統(tǒng)。
系統(tǒng)落地——中醫(yī) & 美學(xué)
新應(yīng)用方面,我想從兩方面來展開。
一個(gè)是如何將生物特征識(shí)別運(yùn)用至醫(yī)學(xué)領(lǐng)域,尤其是與中醫(yī)的結(jié)合。我們希望能夠找到一種新方法,能將中醫(yī)量化、客觀化,進(jìn)而把中醫(yī)推向國際。我們主要從四個(gè)方面開展研究:視覺感知、嗅覺感知、聽覺感知、觸覺感知,以及綜合性的融合感知。
首先是視覺感知,我們主要分析的舌像,通過顏色、紋理、形狀等指標(biāo)全方位對舌相進(jìn)行探討。比如針對特舌像的顏色,我們利用舌像的12個(gè)分布點(diǎn)創(chuàng)建了舌相主空間。針對舌頭表面的反光點(diǎn),包括潤燥指數(shù)、淤斑淤點(diǎn)等,皆為有效信息。至于紋路,也是中醫(yī)俗稱的薄苔厚苔,我們也通過量化的方法進(jìn)行了有效定義。隨著庫的體量變大,搜集到的特征變多,我們能借此進(jìn)行亞健康以及病變判斷。
文獻(xiàn)清單:
– 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. (舌像應(yīng)用)
– “StatisticalAnalysisofTongueimageforFeatureExtractionanddiagnostics”IEEE Trans. on Image Processing, 22 (12), 5336-47, 2013. (舌色分析 )
– “Ahighqualitycolorimagingsystemforcomputerizedtongueimageanalysis,”
– ExpertSystemwithApplications4,15,5854-66.2013.(儀器設(shè)計(jì))
–“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.(舌像應(yīng)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. (舌像應(yīng)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.
第二個(gè)是嗅覺感知,指的是口腔氣味,我們可以借此判斷潛在的病理信息。我們創(chuàng)建了可以捕捉人體內(nèi)部氣味的傳感器陣列,最終發(fā)現(xiàn)不同的類型的疾病會(huì)得到不同類型的波形。通過我們的研究,我們認(rèn)為糖尿病與血檢、呼吸等皆有一定關(guān)聯(lián),于是我們進(jìn)一步探討糖尿病的無損檢測研究,對于是否患上糖尿病以及糖尿病等級都做了相應(yīng)探討。
文獻(xiàn)清單:
– 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 (氣味分析)
– “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(氣味分析)
– “Correcting instrumental variation & time-varying drift: A transfer learning approach with autoencoders,”IEEE TIM 9, 65, 2012-22. 2016(系統(tǒng)設(shè)計(jì))
– “A novel semi-supervised learning approach in artificial olfaction for e-nose application,” IEEE Sensor
Journal 12, 16, 4919-31. 2016(系統(tǒng)設(shè)計(jì))
– “Improving the transfer ability of prediction models for electronic noses,” Sensors & Actuators: B.Chemical 220, 115-124. 2015(儀器設(shè)計(jì))
– “Domain adaptation extreme learning machines for drift compensation in e-nose systems,” IEEE Trans.on IM 7, 64, 1790-1801. 2015(氣味分析)– “Feature selection and analysis on correlated gas sensor data with recursive feature elimination,” Sensors & Actuators: B. Chemical, 212, 353-363. 2015(氣味分析)
– “Design of breath analysis system for diabetes diagnosis & blood glucose level prediction”, IEEE Trans. on Biomedical Engineering 11, 61. 2014(儀器設(shè)計(jì))
– “Non-invasive Blood Glucose Monitoring for Diabetics by Means of Breath Signal Analysis,” Sensors & Actuators B 173,106-113, 2012 (氣味分析)
– “Sparse representation-based classification for Breath sample identification,” Sensors & Actuators B
1,158, 43-53, 2011(氣味分析)
– “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
第三個(gè)是觸覺感知,我們按照中醫(yī)的三部九侯思路設(shè)計(jì)了相應(yīng)系統(tǒng)。鑒于脈象是血流通過內(nèi)臟器官流到人的末梢,帶有內(nèi)臟器官的病理信息,因此我們一直堅(jiān)定脈象無法被ECG取代。我們通過生物特征識(shí)別技術(shù)對大量特征進(jìn)行提取,然后進(jìn)行優(yōu)化,最終形成了對不同波形的分析。
文獻(xiàn)清單:
– 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(脈象分析)
– “A Robust Signal Preprocessing Framework for Wrist Pulse Analysis,” Biomedical Signal Processing and Control 23, 62-75. 2016(脈象分析)
– “Comparison of Three Different Types of Wrist Pulse Signals by Their Physical Meanings and Diagnosis Performance,” IEEE JBHI 1, 20, 119-127. 2016 (系統(tǒng)設(shè)計(jì))
– “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(系統(tǒng)設(shè)計(jì))
– “A Compound Pressure Signal Acquisition System for Multi-Channel Wrist Pulse Analysis”, IEEE Trans. TIM 6, 63, 1556-65, 2014(儀器設(shè)計(jì))
– “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(脈象分析)
– “Computerized wrist pulse signal diagnosis using modified auto-regressive models,” Journal of Medical Systems 35(3): 321-328, 2011(脈象分析)
– “Classification of Pulse Waveforms Using Edit Distance with Real Penalty.” EURASIP J. on Advances in Signal Pro., 303140: 1-9, 2010(脈象分析)
– “Wrist Blood Flow Signal-based Computerized Pulse Diagnosis Using Spatial and Spectrum Features.” Journal of Biomedical Science and Engineering, 3(4): 361-366, 2010(脈象分析)
– “Wrist Pulse Signal Diagnosis using Modified Gaussian Models and Fuzzy C-Means Classification,” Medical Eng. & Phy. 31, 1283-1289, 2009(脈象分析)
– “Baseline Wander Correction in Pulse Waveforms Using Wavelet-based Cascaded Adaptive Filter”, Computers in Biology and Medicine 37, 5, 716-731, 2007(脈象分析)
– “Arrhythmia Pulses Detection by Ziv-Lempel Complexity Analysis”, RURASIP Journal on Applied Signal Processing 2006, 1-12, 2006(脈象分析)
– “Wavelet-based Cascaded Adaptive Filter for Removing Baseline Drift in Pulse Waveforms,” IEEE Trans. on Biome. Eng. 52,11,1973-1975, 2005(脈象分析)
– “Modern researcher on Traditional Chinese Pulse Diagnosis”, European Journal of Oriental Medicine 4, 5, 46-54, 2004(脈象分析)
– “Objectifying Researches on Traditional Chinese Pulse Diagnosis”, Informatics Medical Slovenica, August, 56-63, 2003(脈象分析)
最后一個(gè)是聽覺感知。我們希望通過我們的技術(shù),可以找到對話中隱含的病理信息,因此我們系統(tǒng)探討了它與發(fā)音、疾病之間的關(guān)系。這個(gè)工作相應(yīng)來說進(jìn)行得較晚,直到17年才有第一篇論文,而這幾年也陸續(xù)有文章發(fā)表。
文獻(xiàn)清單:
– 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.
中醫(yī)強(qiáng)調(diào)“望聞問切”,所以我們在融合感知方面也展開了許多工作,將單一的舌、脈等感知經(jīng)過融合達(dá)到更好的效果。我們將之作為當(dāng)下的重點(diǎn)工作進(jìn)行了相應(yīng)研發(fā)。
文獻(xiàn)清單:
– 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,生物特征識(shí)別作為一個(gè)平臺(tái),我們還希望將它應(yīng)用至美學(xué)鑒別領(lǐng)域。
盡管每個(gè)人對美的看法不盡相同,但我們認(rèn)為美是具有公認(rèn)特征的,因此我們希望通過捕捉公認(rèn)特征來實(shí)現(xiàn)美的客觀化。在這過程中,我們成功解決了所謂的平均臉問題,即用于進(jìn)行美的鑒別的標(biāo)準(zhǔn)。我們通過對61個(gè)國家的人臉庫進(jìn)行分析,獲得所有關(guān)于美的規(guī)則,其中包括了中國人的三庭五眼,以及西方人的黃金比例等,以找到最接近美的公共標(biāo)準(zhǔn)。
我們最終建立了一個(gè)窗口,讓人們得以實(shí)時(shí)對這些規(guī)則進(jìn)行調(diào)整。
最后,跟大家強(qiáng)調(diào)一下,我們現(xiàn)在成立了深圳市人工智能與機(jī)器人研究中心,主要致力于這方面的研究,希望能有更多人加盟到我們的隊(duì)伍中來。謝謝大家。
雷鋒網(wǎng) AI 科技評論
雷峰網(wǎng)原創(chuàng)文章,未經(jīng)授權(quán)禁止轉(zhuǎn)載。詳情見轉(zhuǎn)載須知。
本專題其他文章