Pattern recognition - Revision history

imported>Belbury: /* Uses */ move wikilink

2025-12-21T09:33:46Z

Uses: move wikilink

← Previous revision		Revision as of 09:33, 21 December 2025
Line 65:		Line 65:

	===Frequentist or Bayesian approach to pattern recognition===		===Frequentist or Bayesian approach to pattern recognition===
	The first pattern classifier – the linear discriminant presented by [[Fisher discriminant analysis\|Fisher]] – was developed in the [[Frequentist inference\|frequentist]] tradition. The frequentist approach entails that the model parameters are considered unknown, but objective. The parameters are then computed (estimated) from the collected data. For the linear discriminant, these parameters are precisely the mean vectors and the [[covariance matrix]]. Also the probability of each class <math>p({\rm label}\|\boldsymbol\theta)</math> is estimated from the collected dataset. Note that the usage of '[[Bayes rule]]' in a pattern classifier does not make the classification approach Bayesian.		The first pattern classifier – the linear discriminant presented by [[Fisher discriminant analysis\|Fisher]] – was developed in the [[Frequentist inference\|frequentist]] tradition. The frequentist approach entails that the model parameters are considered unknown, but objective. The parameters are then computed (estimated) from the collected data. For the linear discriminant, these parameters are precisely the mean vectors and the [[covariance matrix]]. Also the probability of each class <math>p({\rm label}\|\boldsymbol\theta)</math> is estimated from the collected dataset. Note that the usage of '[[Bayes' rule]]' in a pattern classifier does not make the classification approach Bayesian.

	[[Bayesian inference\|Bayesian statistics]] has its origin in Greek philosophy where a distinction was already made between the '[[A priori and a posteriori\|a priori]]' and the '[[A priori and a posteriori\|a posteriori]]' knowledge. Later [[A priori and a posteriori#Immanuel Kant\|Kant]] defined his distinction between what is a priori known – before observation – and the empirical knowledge gained from observations. In a Bayesian pattern classifier, the class probabilities <math>p({\rm label}\|\boldsymbol\theta)</math> can be chosen by the user, which are then a priori. Moreover, experience quantified as a priori parameter values can be weighted with empirical observations – using e.g., the [[Beta distribution\|Beta-]] ([[Conjugate prior distribution\|conjugate prior]]) and [[Dirichlet distribution\|Dirichlet-distributions]]. The Bayesian approach facilitates a seamless intermixing between expert knowledge in the form of subjective probabilities, and objective observations.		[[Bayesian inference\|Bayesian statistics]] has its origin in Greek philosophy where a distinction was already made between the '[[A priori and a posteriori\|a priori]]' and the '[[A priori and a posteriori\|a posteriori]]' knowledge. Later [[A priori and a posteriori#Immanuel Kant\|Kant]] defined his distinction between what is a priori known – before observation – and the empirical knowledge gained from observations. In a Bayesian pattern classifier, the class probabilities <math>p({\rm label}\|\boldsymbol\theta)</math> can be chosen by the user, which are then a priori. Moreover, experience quantified as a priori parameter values can be weighted with empirical observations – using e.g., the [[Beta distribution\|Beta-]] ([[Conjugate prior distribution\|conjugate prior]]) and [[Dirichlet distribution\|Dirichlet-distributions]]. The Bayesian approach facilitates a seamless intermixing between expert knowledge in the form of subjective probabilities, and objective observations.
Line 72:		Line 72:

	==Uses==		==Uses==
	[[File:800px-Cool Kids of Death Off Festival p 146-face selected.jpg\|thumb\|~~200px\|~~[[~~Face~~ recognition~~\|The face was automatically detected~~]] ~~by special software.~~]]		[[File:800px-Cool Kids of Death Off Festival p 146-face selected.jpg\|thumb\|A face detected by [[facial recognition software]]]]
	Within medical science, pattern recognition is the basis for [[computer-aided diagnosis]] (CAD) systems. CAD describes a procedure that supports the doctor's interpretations and findings. Other typical applications of pattern recognition techniques are automatic [[speech recognition]], [[speaker identification]], [[document classification\|classification of text into several categories]] (e.g., spam or non-spam email messages), the [[handwriting recognition\|automatic recognition of handwriting]] on postal envelopes, automatic [[image recognition\|recognition of images]] of human faces, or handwriting image extraction from medical forms.<ref>{{cite journal\|last=Milewski\|first=Robert\|author2=Govindaraju, Venu\|title=Binarization and cleanup of handwritten text from carbon copy medical form images\|journal=Pattern Recognition\|date=31 March 2008\|volume=41\|issue=4\|pages=1308–1315\|doi=10.1016/j.patcog.2007.08.018\|bibcode=2008PatRe..41.1308M\|url=http://dl.acm.org/citation.cfm?id=1324656\|access-date=26 October 2011\|archive-date=10 September 2020\|archive-url=https://web.archive.org/web/20200910174840/https://dl.acm.org/doi/10.1016/j.patcog.2007.08.018\|url-status=live\|url-access=subscription}}</ref><ref>{{cite journal		Within medical science, pattern recognition is the basis for [[computer-aided diagnosis]] (CAD) systems. CAD describes a procedure that supports the doctor's interpretations and findings. Other typical applications of pattern recognition techniques are automatic [[speech recognition]], [[speaker identification]], [[document classification\|classification of text into several categories]] (e.g., spam or non-spam email messages), the [[handwriting recognition\|automatic recognition of handwriting]] on postal envelopes, automatic [[image recognition\|recognition of images]] of human faces, or handwriting image extraction from medical forms.<ref>{{cite journal\|last=Milewski\|first=Robert\|author2=Govindaraju, Venu\|title=Binarization and cleanup of handwritten text from carbon copy medical form images\|journal=Pattern Recognition\|date=31 March 2008\|volume=41\|issue=4\|pages=1308–1315\|doi=10.1016/j.patcog.2007.08.018\|bibcode=2008PatRe..41.1308M\|url=http://dl.acm.org/citation.cfm?id=1324656\|access-date=26 October 2011\|archive-date=10 September 2020\|archive-url=https://web.archive.org/web/20200910174840/https://dl.acm.org/doi/10.1016/j.patcog.2007.08.018\|url-status=live\|url-access=subscription}}</ref><ref>{{cite journal
	\|last=Sarangi\|first=Susanta \|author2=Sahidullah, Md \|author3=Saha, Goutam		\|last=Sarangi\|first=Susanta \|author2=Sahidullah, Md \|author3=Saha, Goutam

imported>OAbot: Open access bot: url-access=subscription updated in citation with #oabot.

2025-10-13T02:57:33Z

Open access bot: url-access=subscription updated in citation with #oabot.

imported>OAbot: Open access bot: url-access updated in citation with #oabot.

2025-06-19T22:19:21Z

Open access bot: url-access updated in citation with #oabot.

← Previous revision		Revision as of 22:19, 19 June 2025
Line 73:		Line 73:
	==Uses==		==Uses==
	[[File:800px-Cool Kids of Death Off Festival p 146-face selected.jpg\|thumb\|200px\|[[Face recognition\|The face was automatically detected]] by special software.]]		[[File:800px-Cool Kids of Death Off Festival p 146-face selected.jpg\|thumb\|200px\|[[Face recognition\|The face was automatically detected]] by special software.]]
	Within medical science, pattern recognition is the basis for [[computer-aided diagnosis]] (CAD) systems. CAD describes a procedure that supports the doctor's interpretations and findings. Other typical applications of pattern recognition techniques are automatic [[speech recognition]], [[speaker identification]], [[document classification\|classification of text into several categories]] (e.g., spam or non-spam email messages), the [[handwriting recognition\|automatic recognition of handwriting]] on postal envelopes, automatic [[image recognition\|recognition of images]] of human faces, or handwriting image extraction from medical forms.<ref>{{cite journal\|last=Milewski\|first=Robert\|author2=Govindaraju, Venu\|title=Binarization and cleanup of handwritten text from carbon copy medical form images\|journal=Pattern Recognition\|date=31 March 2008\|volume=41\|issue=4\|pages=1308–1315\|doi=10.1016/j.patcog.2007.08.018\|bibcode=2008PatRe..41.1308M\|url=http://dl.acm.org/citation.cfm?id=1324656\|access-date=26 October 2011\|archive-date=10 September 2020\|archive-url=https://web.archive.org/web/20200910174840/https://dl.acm.org/doi/10.1016/j.patcog.2007.08.018\|url-status=live}}</ref><ref>{{cite journal		Within medical science, pattern recognition is the basis for [[computer-aided diagnosis]] (CAD) systems. CAD describes a procedure that supports the doctor's interpretations and findings. Other typical applications of pattern recognition techniques are automatic [[speech recognition]], [[speaker identification]], [[document classification\|classification of text into several categories]] (e.g., spam or non-spam email messages), the [[handwriting recognition\|automatic recognition of handwriting]] on postal envelopes, automatic [[image recognition\|recognition of images]] of human faces, or handwriting image extraction from medical forms.<ref>{{cite journal\|last=Milewski\|first=Robert\|author2=Govindaraju, Venu\|title=Binarization and cleanup of handwritten text from carbon copy medical form images\|journal=Pattern Recognition\|date=31 March 2008\|volume=41\|issue=4\|pages=1308–1315\|doi=10.1016/j.patcog.2007.08.018\|bibcode=2008PatRe..41.1308M\|url=http://dl.acm.org/citation.cfm?id=1324656\|access-date=26 October 2011\|archive-date=10 September 2020\|archive-url=https://web.archive.org/web/20200910174840/https://dl.acm.org/doi/10.1016/j.patcog.2007.08.018\|url-status=live\|url-access=subscription}}</ref><ref>{{cite journal
	\|last=Sarangi\|first=Susanta \|author2=Sahidullah, Md \|author3=Saha, Goutam		\|last=Sarangi\|first=Susanta \|author2=Sahidullah, Md \|author3=Saha, Goutam
	\|title=Optimization of data-driven filterbank for automatic speaker verification		\|title=Optimization of data-driven filterbank for automatic speaker verification
Line 158:		Line 158:

	==See also==		==See also==
	{{~~Div col~~\|~~colwidth=30em}}~~		* {{annotated link\|Adaptive resonance theory}}
	* [[Adaptive resonance theory]]		* {{annotated link\|Black box}}
	* [[Black box]]		* {{annotated link\|Cache language model}}
	* [[Cache language model]]		* {{annotated link\|Compound-term processing}}
	* [[Compound-term processing]]		* {{annotated link\|Computer-aided diagnosis}}
	* [[Computer-aided diagnosis]]		* {{annotated link\|Contextual image classification}}
	* [[Data mining]]		* {{annotated link\|Data mining}}
	* [[Deep learning]]		* {{annotated link\|Deep learning}}
	* [[~~Information theory~~]]		* {{annotated link\|Grey box model}}
			* {{annotated link\|Information theory}}
			* [[List of datasets for machine learning research]]
	* [[List of numerical-analysis software]]		* [[List of numerical-analysis software]]
	* [[List of numerical libraries]]		* [[List of numerical libraries]]
	* [[Neocognitron]]		* {{annotated link\|Neocognitron}}
	* [[Perception]]		* {{annotated link\|Perception}}
	* [[Perceptual learning]]		* {{annotated link\|Perceptual learning}}
	* [[Predictive analytics]]		* {{annotated link\|Predictive analytics}}
	* [[Prior knowledge for pattern recognition]]		* {{annotated link\|Prior knowledge for pattern recognition}}
	* [[Sequence mining]]		* {{annotated link\|Sequence mining}}
	* [[Template matching]]		* {{annotated link\|Template matching}}
	* [[Contextual image classification]]
	* [[List of datasets for machine learning research]]
	~~{{div col end~~}}

	==References==		==References==

imported>TTWIDEE: /* See also */ Fixed capitalisation

2025-04-25T17:23:30Z

← Previous revision		Revision as of 02:57, 13 October 2025
Line 7:		Line 7:
	Pattern recognition systems are commonly trained from labeled "training" data. When no [[labeled data]] are available, other algorithms can be used to discover previously unknown patterns. [[Data mining\|KDD]] and data mining have a larger focus on unsupervised methods and stronger connection to business use. Pattern recognition focuses more on the signal and also takes acquisition and [[signal processing]] into consideration. It originated in [[engineering]], and the term is popular in the context of [[computer vision]]: a leading computer vision conference is named [[Conference on Computer Vision and Pattern Recognition]].		Pattern recognition systems are commonly trained from labeled "training" data. When no [[labeled data]] are available, other algorithms can be used to discover previously unknown patterns. [[Data mining\|KDD]] and data mining have a larger focus on unsupervised methods and stronger connection to business use. Pattern recognition focuses more on the signal and also takes acquisition and [[signal processing]] into consideration. It originated in [[engineering]], and the term is popular in the context of [[computer vision]]: a leading computer vision conference is named [[Conference on Computer Vision and Pattern Recognition]].

	In [[machine learning]], pattern recognition is the assignment of a label to a given input value. In statistics, [[Linear discriminant analysis\|discriminant analysis]] was introduced for this same purpose in 1936. An example of pattern recognition is [[classification (machine learning)\|classification]], which attempts to assign each input value to one of a given set of ''classes'' (for example, determine whether a given email is "spam"). Pattern recognition is a more general problem that encompasses other types of output as well. Other examples are [[regression analysis\|regression]], which assigns a [[real number\|real-valued]] output to each input;<ref>{{Cite journal\|last=Howard\|first=W.R.\|date=2007-02-20\|title=Pattern Recognition and Machine Learning\|journal=Kybernetes\|volume=36\|issue=2\|~~pages~~=275\|doi=10.1108/03684920710743466\|issn=0368-492X}}</ref> [[sequence labeling]], which assigns a class to each member of a sequence of values<ref>{{Cite web\|url=https://pubweb.eng.utah.edu/~cs6961/slides/seq-labeling1.4ps.pdf\|title=Sequence Labeling\|website=utah.edu\|access-date=2018-11-06\|archive-date=2018-11-06\|archive-url=https://web.archive.org/web/20181106171837/https://pubweb.eng.utah.edu/~cs6961/slides/seq-labeling1.4ps.pdf\|url-status=live}}</ref> (for example, [[part of speech tagging]], which assigns a [[part of speech]] to each word in an input sentence); and [[parsing]], which assigns a [[parse tree]] to an input sentence, describing the [[syntactic structure]] of the sentence.<ref>{{Cite book\|title=Mathematical logic, p. 34\|last=Ian.\|first=Chiswell\|date=2007\|publisher=Oxford University Press\|isbn=~~9780199215621~~\|oclc=799802313}}</ref>		In [[machine learning]], pattern recognition is the assignment of a label to a given input value. In statistics, [[Linear discriminant analysis\|discriminant analysis]] was introduced for this same purpose in 1936. An example of pattern recognition is [[classification (machine learning)\|classification]], which attempts to assign each input value to one of a given set of ''classes'' (for example, determine whether a given email is "spam"). Pattern recognition is a more general problem that encompasses other types of output as well. Other examples are [[regression analysis\|regression]], which assigns a [[real number\|real-valued]] output to each input;<ref>{{Cite journal\|last=Howard\|first=W.R.\|date=2007-02-20\|title=Pattern Recognition and Machine Learning\|journal=Kybernetes\|volume=36\|issue=2\|page=275\|doi=10.1108/03684920710743466\|issn=0368-492X}}</ref> [[sequence labeling]], which assigns a class to each member of a sequence of values<ref>{{Cite web\|url=https://pubweb.eng.utah.edu/~cs6961/slides/seq-labeling1.4ps.pdf\|title=Sequence Labeling\|website=utah.edu\|access-date=2018-11-06\|archive-date=2018-11-06\|archive-url=https://web.archive.org/web/20181106171837/https://pubweb.eng.utah.edu/~cs6961/slides/seq-labeling1.4ps.pdf\|url-status=live}}</ref> (for example, [[part of speech tagging]], which assigns a [[part of speech]] to each word in an input sentence); and [[parsing]], which assigns a [[parse tree]] to an input sentence, describing the [[syntactic structure]] of the sentence.<ref>{{Cite book\|title=Mathematical logic, p. 34\|last=Ian.\|first=Chiswell\|date=2007\|publisher=Oxford University Press\|isbn=978-0-19-921562-1\|oclc=799802313}}</ref>

	Pattern recognition algorithms generally aim to provide a reasonable answer for all possible inputs and to perform "most likely" matching of the inputs, taking into account their statistical variation. This is opposed to ''[[pattern matching]]'' algorithms, which look for exact matches in the input with pre-existing patterns. A common example of a pattern-matching algorithm is [[regular expression]] matching, which looks for patterns of a given sort in textual data and is included in the search capabilities of many [[text editor]]s and [[word processor]]s.		Pattern recognition algorithms generally aim to provide a reasonable answer for all possible inputs and to perform "most likely" matching of the inputs, taking into account their statistical variation. This is opposed to ''[[pattern matching]]'' algorithms, which look for exact matches in the input with pre-existing patterns. A common example of a pattern-matching algorithm is [[regular expression]] matching, which looks for patterns of a given sort in textual data and is included in the search capabilities of many [[text editor]]s and [[word processor]]s.
Line 77:		Line 77:
	\|title=Optimization of data-driven filterbank for automatic speaker verification		\|title=Optimization of data-driven filterbank for automatic speaker verification
	\|journal=Digital Signal Processing \|date=September 2020 \|volume=104		\|journal=Digital Signal Processing \|date=September 2020 \|volume=104
	\|~~page~~=102795 \|doi= 10.1016/j.dsp.2020.102795\|arxiv=2007.10729\|bibcode=2020DSP...10402795S \|s2cid=220665533 }}</ref> The last two examples form the subtopic [[image analysis]] of pattern recognition that deals with digital images as input to pattern recognition systems.<ref name=duda2001>{{cite book\|author=[[Richard O. Duda]], [[Peter E. Hart]], [[David G. Stork]]\|year=2001\|title=Pattern classification\|edition=2nd\|publisher=Wiley, New York\|isbn=978-0-471-05669-0\|url=https://books.google.com/books?id=Br33IRC3PkQC\|access-date=2019-11-26\|archive-date=2020-08-19\|archive-url=https://web.archive.org/web/20200819004737/https://books.google.com/books?id=Br33IRC3PkQC\|url-status=live}}</ref><ref>R. Brunelli, ''Template Matching Techniques in Computer Vision: Theory and Practice'', Wiley, {{ISBN\|978-0-470-51706-2}}, 2009</ref>		\|article-number=102795 \|doi= 10.1016/j.dsp.2020.102795\|arxiv=2007.10729\|bibcode=2020DSP...10402795S \|s2cid=220665533 }}</ref> The last two examples form the subtopic [[image analysis]] of pattern recognition that deals with digital images as input to pattern recognition systems.<ref name=duda2001>{{cite book\|author=[[Richard O. Duda]], [[Peter E. Hart]], [[David G. Stork]]\|year=2001\|title=Pattern classification\|edition=2nd\|publisher=Wiley, New York\|isbn=978-0-471-05669-0\|url=https://books.google.com/books?id=Br33IRC3PkQC\|access-date=2019-11-26\|archive-date=2020-08-19\|archive-url=https://web.archive.org/web/20200819004737/https://books.google.com/books?id=Br33IRC3PkQC\|url-status=live}}</ref><ref>R. Brunelli, ''Template Matching Techniques in Computer Vision: Theory and Practice'', Wiley, {{ISBN\|978-0-470-51706-2}}, 2009</ref>

	Optical character recognition is an example of the application of a pattern classifier. The method of signing one's name was captured with stylus and overlay starting in 1990.{{citation needed\|date=January 2011}} The strokes, speed, relative min, relative max, acceleration and pressure is used to uniquely identify and confirm identity. Banks were first offered this technology, but were content to collect from the FDIC for any bank fraud and did not want to inconvenience customers.{{citation needed\|date=January 2011}}		Optical character recognition is an example of the application of a pattern classifier. The method of signing one's name was captured with stylus and overlay starting in 1990.{{citation needed\|date=January 2011}} The strokes, speed, relative min, relative max, acceleration and pressure is used to uniquely identify and confirm identity. Banks were first offered this technology, but were content to collect from the FDIC for any bank fraud and did not want to inconvenience customers.{{citation needed\|date=January 2011}}

	Pattern recognition has many real-world applications in image processing. Some examples include:		Pattern recognition has many real-world applications in image processing. Some examples include:
	* identification and authentication: e.g., [[license plate recognition]],<ref>[http://anpr-tutorial.com/ The Automatic Number Plate Recognition Tutorial] {{Webarchive\|url=https://web.archive.org/web/20060820175245/http://www.anpr-tutorial.com/ \|date=2006-08-20 }} http://anpr-tutorial.com/ </ref> fingerprint analysis, [[face detection]]/verification,<ref>[https://www.cs.cmu.edu/afs/cs.cmu.edu/usr/mitchell/ftp/faces.html Neural Networks for Face Recognition] {{Webarchive\|url=https://web.archive.org/web/20160304065030/http://www.cs.cmu.edu/afs/cs.cmu.edu/usr/mitchell/ftp/faces.html \|date=2016-03-04 }} Companion to Chapter 4 of the textbook Machine Learning.</ref> and [[voice-based authentication]].<ref>{{cite journal\|last=Poddar\|first=Arnab\|author2=Sahidullah, Md\|author3=Saha, Goutam\|title=Speaker Verification with Short Utterances: A Review of Challenges, Trends and Opportunities\|journal=IET Biometrics\|date=March 2018\|volume=7\|issue=2\|pages=91–101\|doi=10.1049/iet-bmt.2017.0065\|url=https://ieeexplore.ieee.org/document/8302747\|access-date=2019-08-27\|archive-date=2019-09-03\|archive-url=https://web.archive.org/web/20190903174139/https://ieeexplore.ieee.org/document/8302747/~~\|url-status=dead~~}}</ref>		* identification and authentication: e.g., [[license plate recognition]],<ref>[http://anpr-tutorial.com/ The Automatic Number Plate Recognition Tutorial] {{Webarchive\|url=https://web.archive.org/web/20060820175245/http://www.anpr-tutorial.com/ \|date=2006-08-20 }} http://anpr-tutorial.com/ {{Webarchive\|url=https://web.archive.org/web/20060820175245/http://www.anpr-tutorial.com/ \|date=2006-08-20 }}</ref> fingerprint analysis, [[face detection]]/verification,<ref>[https://www.cs.cmu.edu/afs/cs.cmu.edu/usr/mitchell/ftp/faces.html Neural Networks for Face Recognition] {{Webarchive\|url=https://web.archive.org/web/20160304065030/http://www.cs.cmu.edu/afs/cs.cmu.edu/usr/mitchell/ftp/faces.html \|date=2016-03-04 }} Companion to Chapter 4 of the textbook Machine Learning.</ref> and [[voice-based authentication]].<ref>{{cite journal\|last=Poddar\|first=Arnab\|author2=Sahidullah, Md\|author3=Saha, Goutam\|title=Speaker Verification with Short Utterances: A Review of Challenges, Trends and Opportunities\|journal=IET Biometrics\|date=March 2018\|volume=7\|issue=2\|pages=91–101\|doi=10.1049/iet-bmt.2017.0065\|url=https://ieeexplore.ieee.org/document/8302747\|access-date=2019-08-27\|archive-date=2019-09-03\|archive-url=https://web.archive.org/web/20190903174139/https://ieeexplore.ieee.org/document/8302747/}}</ref>
	* medical diagnosis: e.g., screening for cervical cancer (Papnet),<ref>[http://health-asia.org/papnet-for-cervical-screening/ PAPNET For Cervical Screening] {{webarchive\|url=https://archive.today/20120708211332/http://health-asia.org/papnet-for-cervical-screening/ \|date=2012-07-08 }}</ref> breast tumors or heart sounds;		* medical diagnosis: e.g., screening for cervical cancer (Papnet),<ref>[http://health-asia.org/papnet-for-cervical-screening/ PAPNET For Cervical Screening] {{webarchive\|url=https://archive.today/20120708211332/http://health-asia.org/papnet-for-cervical-screening/ \|date=2012-07-08 }}</ref> breast tumors or heart sounds;
	* defense: various navigation and guidance systems, [[automatic target recognition\|target recognition]] systems, shape recognition technology etc.		* defense: various navigation and guidance systems, [[automatic target recognition\|target recognition]] systems, shape recognition technology etc.
	* mobility: [[Advanced driver-assistance systems\|advanced driver assistance systems]], [[Self-driving car\|autonomous vehicle technology]], etc.<ref>{{Cite journal\|url=https://saemobilus.sae.org/content/2018-01-0035\|title=Development of an Autonomous Vehicle Control Strategy Using a Single Camera and Deep Neural Networks (2018-01-0035 Technical Paper)- SAE Mobilus\|website=saemobilus.sae.org\|date=3 April 2018 \|doi=10.4271/2018-01-0035 \|language=en\|access-date=2019-09-06\|archive-date=2019-09-06\|archive-url=https://web.archive.org/web/20190906084436/https://saemobilus.sae.org/content/2018-01-0035\|url-status=live}}</ref><ref>{{Cite journal\|last1=Gerdes\|first1=J. Christian\|last2=Kegelman\|first2=John C.\|last3=Kapania\|first3=Nitin R.\|last4=Brown\|first4=Matthew\|last5=Spielberg\|first5=Nathan A.\|date=2019-03-27\|title=Neural network vehicle models for high-performance automated driving\|journal=Science Robotics\|language=en\|volume=4\|issue=28\|~~pages~~=eaaw1975\|doi=10.1126/scirobotics.aaw1975\|pmid=33137751\|s2cid=89616974\|issn=2470-9476\|doi-access=free}}</ref><ref>{{Cite web\|url=https://www.theengineer.co.uk/ai-autonomous-cars/\|title=How AI is paving the way for fully autonomous cars\|last=Pickering\|first=Chris\|date=2017-08-15\|website=The Engineer\|language=en-UK\|access-date=2019-09-06\|archive-date=2019-09-06\|archive-url=https://web.archive.org/web/20190906084433/https://www.theengineer.co.uk/ai-autonomous-cars/\|url-status=live}}</ref><ref>{{Cite journal\|last1=Ray\|first1=Baishakhi\|last2=Jana\|first2=Suman\|last3=Pei\|first3=Kexin\|last4=Tian\|first4=Yuchi\|date=2017-08-28\|title=DeepTest: Automated Testing of Deep-Neural-Network-driven Autonomous Cars\|language=en\|arxiv=1708.08559\|bibcode=2017arXiv170808559T}}</ref><ref>{{Cite journal\|last1=Sinha\|first1=P. K.\|last2=Hadjiiski\|first2=L. M.\|last3=Mutib\|first3=K.\|date=1993-04-01\|title=Neural Networks in Autonomous Vehicle Control\|journal=IFAC Proceedings Volumes\|series=1st IFAC International Workshop on Intelligent Autonomous Vehicles, Hampshire, UK, 18–21 April\|volume=26\|issue=1\|pages=335–340\|doi=10.1016/S1474-6670(17)49322-0\|issn=1474-6670}}</ref>		* mobility: [[Advanced driver-assistance systems\|advanced driver assistance systems]], [[Self-driving car\|autonomous vehicle technology]], etc.<ref>{{Cite journal\|url=https://saemobilus.sae.org/content/2018-01-0035\|title=Development of an Autonomous Vehicle Control Strategy Using a Single Camera and Deep Neural Networks (2018-01-0035 Technical Paper)- SAE Mobilus\|website=saemobilus.sae.org\|date=3 April 2018 \|doi=10.4271/2018-01-0035 \|language=en\|access-date=2019-09-06\|archive-date=2019-09-06\|archive-url=https://web.archive.org/web/20190906084436/https://saemobilus.sae.org/content/2018-01-0035\|url-status=live\|url-access=subscription}}</ref><ref>{{Cite journal\|last1=Gerdes\|first1=J. Christian\|last2=Kegelman\|first2=John C.\|last3=Kapania\|first3=Nitin R.\|last4=Brown\|first4=Matthew\|last5=Spielberg\|first5=Nathan A.\|date=2019-03-27\|title=Neural network vehicle models for high-performance automated driving\|journal=Science Robotics\|language=en\|volume=4\|issue=28\|article-number=eaaw1975\|doi=10.1126/scirobotics.aaw1975\|pmid=33137751\|s2cid=89616974\|issn=2470-9476\|doi-access=free}}</ref><ref>{{Cite web\|url=https://www.theengineer.co.uk/ai-autonomous-cars/\|title=How AI is paving the way for fully autonomous cars\|last=Pickering\|first=Chris\|date=2017-08-15\|website=The Engineer\|language=en-UK\|access-date=2019-09-06\|archive-date=2019-09-06\|archive-url=https://web.archive.org/web/20190906084433/https://www.theengineer.co.uk/ai-autonomous-cars/\|url-status=live}}</ref><ref>{{Cite journal\|last1=Ray\|first1=Baishakhi\|last2=Jana\|first2=Suman\|last3=Pei\|first3=Kexin\|last4=Tian\|first4=Yuchi\|date=2017-08-28\|title=DeepTest: Automated Testing of Deep-Neural-Network-driven Autonomous Cars\|language=en\|arxiv=1708.08559\|bibcode=2017arXiv170808559T}}</ref><ref>{{Cite journal\|last1=Sinha\|first1=P. K.\|last2=Hadjiiski\|first2=L. M.\|last3=Mutib\|first3=K.\|date=1993-04-01\|title=Neural Networks in Autonomous Vehicle Control\|journal=IFAC Proceedings Volumes\|series=1st IFAC International Workshop on Intelligent Autonomous Vehicles, Hampshire, UK, 18–21 April\|volume=26\|issue=1\|pages=335–340\|doi=10.1016/S1474-6670(17)49322-0\|issn=1474-6670}}</ref>

	In psychology, [[pattern recognition (psychology)\|pattern recognition]] is used to make sense of and identify objects, and is closely related to perception. This explains how the sensory inputs humans receive are made meaningful. Pattern recognition can be thought of in two different ways. The first concerns template matching and the second concerns feature detection. A template is a pattern used to produce items of the same proportions. The template-matching hypothesis suggests that incoming stimuli are compared with templates in the long-term memory. If there is a match, the stimulus is identified. Feature detection models, such as the Pandemonium system for classifying letters (Selfridge, 1959), suggest that the stimuli are broken down into their component parts for identification. One observation is a capital E having three horizontal lines and one vertical line.<ref>{{cite web \|url=http://www.s-cool.co.uk/a-level/psychology/attention/revise-it/pattern-recognition \|title=A-level Psychology Attention Revision - Pattern recognition \| S-cool, the revision website \|publisher=S-cool.co.uk \|access-date=2012-09-17 \|archive-date=2013-06-22 \|archive-url=https://web.archive.org/web/20130622023719/http://www.s-cool.co.uk/a-level/psychology/attention/revise-it/pattern-recognition \|url-status=live }}</ref>		In psychology, [[pattern recognition (psychology)\|pattern recognition]] is used to make sense of and identify objects, and is closely related to perception. This explains how the sensory inputs humans receive are made meaningful. Pattern recognition can be thought of in two different ways. The first concerns template matching and the second concerns feature detection. A template is a pattern used to produce items of the same proportions. The template-matching hypothesis suggests that incoming stimuli are compared with templates in the long-term memory. If there is a match, the stimulus is identified. Feature detection models, such as the Pandemonium system for classifying letters (Selfridge, 1959), suggest that the stimuli are broken down into their component parts for identification. One observation is a capital E having three horizontal lines and one vertical line.<ref>{{cite web \|url=http://www.s-cool.co.uk/a-level/psychology/attention/revise-it/pattern-recognition \|title=A-level Psychology Attention Revision - Pattern recognition \| S-cool, the revision website \|publisher=S-cool.co.uk \|access-date=2012-09-17 \|archive-date=2013-06-22 \|archive-url=https://web.archive.org/web/20130622023719/http://www.s-cool.co.uk/a-level/psychology/attention/revise-it/pattern-recognition \|url-status=live }}</ref>
Line 186:		Line 186:
	*{{cite book\|last1=Hornegger\|first1=Joachim\|last2=Paulus\|first2=Dietrich W. R.\|title=Applied Pattern Recognition: A Practical Introduction to Image and Speech Processing in C++\|edition=2nd\|year=1999\|publisher=Morgan Kaufmann Publishers\|location=San Francisco\|isbn=978-3-528-15558-2}}		*{{cite book\|last1=Hornegger\|first1=Joachim\|last2=Paulus\|first2=Dietrich W. R.\|title=Applied Pattern Recognition: A Practical Introduction to Image and Speech Processing in C++\|edition=2nd\|year=1999\|publisher=Morgan Kaufmann Publishers\|location=San Francisco\|isbn=978-3-528-15558-2}}
	*{{cite book\|last=Schuermann\|first=Juergen\|title=Pattern Classification: A Unified View of Statistical and Neural Approaches\|year=1996\|publisher=Wiley\|location=New York\|isbn=978-0-471-13534-0}}		*{{cite book\|last=Schuermann\|first=Juergen\|title=Pattern Classification: A Unified View of Statistical and Neural Approaches\|year=1996\|publisher=Wiley\|location=New York\|isbn=978-0-471-13534-0}}
	*{{cite book\|editor=Godfried T. Toussaint\|title=Computational Morphology\|year=1988\|publisher=North-Holland Publishing Company\|location=Amsterdam\|url=https://books.google.com/books?id=ObOjBQAAQBAJ\|isbn=~~9781483296722~~}}		*{{cite book\|editor=Godfried T. Toussaint\|title=Computational Morphology\|year=1988\|publisher=North-Holland Publishing Company\|location=Amsterdam\|url=https://books.google.com/books?id=ObOjBQAAQBAJ\|isbn=978-1-4832-9672-2}}
	*{{cite book\|last1=Kulikowski\|first1=Casimir A.\|last2=Weiss\|first2=Sholom M.\|title=Computer Systems That Learn: Classification and Prediction Methods from Statistics, Neural Nets, Machine Learning, and Expert Systems\|year=1991\|publisher=Morgan Kaufmann Publishers\|location=San Francisco\|isbn=978-1-55860-065-2}}		*{{cite book\|last1=Kulikowski\|first1=Casimir A.\|last2=Weiss\|first2=Sholom M.\|title=Computer Systems That Learn: Classification and Prediction Methods from Statistics, Neural Nets, Machine Learning, and Expert Systems\|year=1991\|publisher=Morgan Kaufmann Publishers\|location=San Francisco\|isbn=978-1-55860-065-2}}
	*{{cite book\|last1=Duda\|first1=Richard O.\|last2=Hart\|first2=Peter E.\|last3=Stork\|first3=David G.\|title=Pattern Classification\|edition=2nd\|year=2000\|publisher=Wiley-Interscience\|isbn=978-~~0471056690~~\|url=https://books.google.com/books?id=Br33IRC3PkQC}}		*{{cite book\|last1=Duda\|first1=Richard O.\|last2=Hart\|first2=Peter E.\|last3=Stork\|first3=David G.\|title=Pattern Classification\|edition=2nd\|year=2000\|publisher=Wiley-Interscience\|isbn=978-0-471-05669-0\|url=https://books.google.com/books?id=Br33IRC3PkQC}}
	*{{cite journal\|last1=Jain\|first1=Anil.K.\|last2=Duin\|first2=Robert.P.W.\|last3=Mao\|first3=Jianchang\|title=Statistical pattern recognition: a review\|year=2000\|journal=IEEE Transactions on Pattern Analysis and Machine Intelligence \| volume=22 \| pages=4–37 \| doi = 10.1109/34.824819 \| issue=1\|citeseerx=10.1.1.123.8151\|s2cid=192934 }}		*{{cite journal\|last1=Jain\|first1=Anil.K.\|last2=Duin\|first2=Robert.P.W.\|last3=Mao\|first3=Jianchang\|title=Statistical pattern recognition: a review\|year=2000\|journal=IEEE Transactions on Pattern Analysis and Machine Intelligence \| volume=22 \| pages=4–37 \| doi = 10.1109/34.824819 \| issue=1\|bibcode=2000ITPAM..22....4J \|citeseerx=10.1.1.123.8151\|s2cid=192934 }}
	*[https://web.archive.org/web/20140911114525/http://egmont-petersen.nl/classifiers.htm An introductory tutorial to classifiers (introducing the basic terms, with numeric example)]		*[https://web.archive.org/web/20140911114525/http://egmont-petersen.nl/classifiers.htm An introductory tutorial to classifiers (introducing the basic terms, with numeric example)]
	* {{cite book \| last=Kovalevsky \| first=V. A. \| title=Image Pattern Recognition \| publisher=Springer New York \| publication-place=New York, NY \| date=1980 \| isbn=978-1-4612-6033-2 \| oclc=852790446}}		* {{cite book \| last=Kovalevsky \| first=V. A. \| title=Image Pattern Recognition \| publisher=Springer New York \| publication-place=New York, NY \| date=1980 \| isbn=978-1-4612-6033-2 \| oclc=852790446}}