# Machine perception > Mediated Wiki article. Canonical URL: https://mediated.wiki/source/Machine_perception > Markdown URL: https://mediated.wiki/source/Machine_perception.md > Source: https://en.wikipedia.org/wiki/Machine_perception > Source revision: 1346165176 > License: Creative Commons Attribution-ShareAlike 4.0 International (https://creativecommons.org/licenses/by-sa/4.0/) {{Short description|Computer ability}} '''Machine perception''' is the capability of a computer system to interpret [data](/source/data) in a manner that is similar to the way [human](/source/human)s use their [sense](/source/sense)s to relate to the world around them.{{Cite web|url=http://www.ccs.fau.edu/~hahn/mpcr/|title=Machine Perception & Cognitive Robotics Laboratory|website=www.ccs.fau.edu|access-date=2016-06-18}} The basic method that the [computer](/source/computer)s take in and respond to their [environment](/source/Environment_(systems)) is through the attached [hardware](/source/Electronic_hardware). Until recently [input](/source/Input_(computer_science)) was limited to a keyboard, or a mouse, but advances in technology, both in hardware and [software](/source/software), have allowed computers to take in [sensory](/source/Sensory_nervous_system) input in a way similar to humans. Machine [perception](/source/perception) allows the computer to use this sensory input, as well as conventional [computational](/source/Computational_science) means of gathering [information](/source/information), to gather information with greater accuracy and to present it in a way that is more comfortable for the [user](/source/User_(computing)). These include [computer vision](/source/computer_vision), [machine hearing](/source/machine_hearing), machine touch, and [machine smelling](/source/machine_smelling), as artificial [scents](/source/Sense_of_smell) are, at a [chemical compound](/source/chemical_compound), [molecular](/source/Molecule), [atom](/source/atom)ic level, indiscernible and [identical.](/source/Identical_particles){{cite web |last=Cotton |first=Simon |date=2009-03-01 |title=If it smells - it's chemistry |url=https://edu.rsc.org/feature/if-it-smells-its-chemistry/2020168.article |access-date=2022-05-03 |website=RSC Education }}{{Cite web |title=Artificial networks learn to smell like the brain |url=https://news.mit.edu/2021/artificial-networks-learn-smell-like-the-brain-1018 |access-date=2022-05-03 |website=MIT News {{!}} Massachusetts Institute of Technology |date=18 October 2021 |language=en}} The end goal of machine perception is to give machines the ability to [see](/source/Visual_perception), [feel](/source/Feeling) and [perceive](/source/perceive) the world as humans do and therefore for them to be able to [explain](/source/Explainable_artificial_intelligence) in a human way why they are making their decisions, to warn us when it is failing and more importantly, the reason why it is failing.{{cite web|url=https://www.ece.vt.edu/research/area/perception|title=Machine Perception Research - ECE - Virginia Tech|website=www.ECE.VT.edu|access-date=January 10, 2018|archive-date=March 7, 2021|archive-url=https://web.archive.org/web/20210307031656/https://ece.vt.edu/research/area/perception}} This [purpose](/source/Goal) is very similar to the proposed purposes for [artificial intelligence](/source/artificial_intelligence) generally, except that machine perception would only grant machines limited [sentience](/source/sentience), rather than bestow upon machines full [consciousness](/source/consciousness), [self-awareness](/source/self-awareness), and [intentionality](/source/intentionality). ==Machine vision== {{main|machine vision}} [Computer vision](/source/Computer_vision) is a field that includes methods for acquiring, processing, analyzing, and understanding images and high-dimensional data from the real world to produce numerical or symbolic information, e.g., in the forms of decisions. Computer vision has many applications already in use today such as [facial recognition](/source/Facial_recognition_system), geographical modeling, and even aesthetic judgment. However, machines still struggle to interpret visual impute accurately if it is blurry or if the [viewpoint](/source/Recognition-by-components_theory) at which stimuli are viewed varies often. Computers also struggle to determine the proper nature of some stimulus if overlapped by or seamlessly touching another stimulus. This refers to the [Principle of Good Continuation](/source/Ambiguous_image). Machines also struggle to perceive and record stimulus functioning according to the Apparent Movement principle which is a field of research in [Gestalt psychology](/source/Gestalt_psychology). ==Machine hearing== Machine hearing, also known as machine listening or [computer audition](/source/computer_audition) is the ability of a computer or machine to take in and process sound data such as speech or music.{{Cite book |last=Tanguiane ([Tangian](/source/Andranik_Tangian)) |first=Andranick |date=1993 |title= Artificial Perception and Music Recognition |publisher=Springer|location=Berlin-Heidelberg}}{{Cite journal |last=Tanguiane (Tangian)|first=Andranick |year=1994 |title= Principle of correlativity of perception and its applications to music recognition |journal= Music Perception|volume=11|issue=4|pages=465–502 |doi=10.2307/40285634 |jstor=40285634 }} This area has a wide range of application including music recording and compression, speech synthesis and [speech recognition](/source/speech_recognition). Moreover, this technology allows the machine to replicate the human brain's ability to selectively focus on a specific sound against many other competing sounds and background noise. This ability is called "[auditory scene analysis](/source/auditory_scene_analysis)". The technology enables the machine to segment several streams occurring at the same time.{{Cite journal |last=Tangian |first=Andranik |year=2001 |title= How do we think: modeling interactions of memory and thinking |journal= Cognitive Processing |volume=2 |pages=117–151 |url=https://publikationen.bibliothek.kit.edu/1000133287 |doi=10.5445/IR/1000133287|s2cid=237995668 }}{{cite web|title=Machine Perception & Cognitive Robotics Laboratory|url=http://www.ccs.fau.edu/~hahn/mpcr/|website=ccs.FAU.edu|access-date=January 10, 2018}} Many commonly used devices such as a smartphones, voice translators and cars make use of some form of machine hearing. Present technology still has challenges in [speech segmentation](/source/speech_segmentation). This means it is occasionally unable to correctly split words within sentences especially when spoken in an atypical accent. ==Machine touch{{anchor|Machine touch}}== [[File:SynTouch BioTac.jpg|thumb|left|A [tactile sensor](/source/tactile_sensor)]] Machine touch is an area of machine perception where tactile information is processed by a machine or computer. Applications include [tactile perception](/source/tactile_sensor) of surface properties and [dexterity](/source/dexterity) whereby tactile information can enable intelligent reflexes and interaction with the environment.{{cite journal|title=Learning efficient haptic shape exploration with a rigid tactile sensor array, S. Fleer, A. Moringen, R. Klatzky, H. Ritter |year=2020 |doi=10.1371/journal.pone.0226880 |pmid=31896135 |doi-access=free |last1=Fleer |first1=S. |last2=Moringen |first2=A. |last3=Klatzky |first3=R. L. |last4=Ritter |first4=H. |journal=PLOS ONE |volume=15 |issue=1 |article-number=e0226880 |pmc=6940144 }} Though this could possibly be done through measuring when and where friction occurs and also the nature and intensity of the friction, machines however still do not have any way of measuring few ordinary physical human experiences including physical pain. For example, scientists have yet to invent a mechanical substitute for the [Nociceptor](/source/Nociceptor)s in the body and brain that are responsible for noticing and measuring physical human discomfort and suffering. Researchers are exploring ways to combine tactile sensors with machine learning algorithms to approximate human-like touch perception, enabling robots to handle delicate objects, detect texture differences, or respond adaptively to environmental changes. Emerging applications include robotic surgery , prosthetics with sensory feedback, and haptic interfaces in virtual reality, which aim to provide more immersive and precise interaction between humans and machines. ==Machine olfaction== Scientists are developing computers known as [machine olfaction](/source/machine_olfaction) which can recognize and measure [smells](/source/Sense_of_smell) as well. Airborne [chemicals](/source/Chemical_substance) are sensed and classified with a device sometimes known as an [electronic nose](/source/electronic_nose).{{Cite web |title=Using artificial intelligence to smell the roses: Study applies machine learning to olfaction with possible vast applications in flavors and fragrances |url=https://www.sciencedaily.com/releases/2020/07/200728182544.htm |access-date=2022-05-03 |website=ScienceDaily |language=en}}{{Cite web |last=Marr |first=Bernard |title=Artificial Intelligence Is Developing A Sense Of Smell: What Could A Digital Nose Mean In Practice? |url=https://www.forbes.com/sites/bernardmarr/2021/05/10/artificial-intelligence-is-developing-a-sense-of-smell-what-could-a-digital-nose-mean-in-practice/ |access-date=2022-05-03 |website=Forbes |language=en}} == Machine taste == {{excerpt|Electronic tongue}} == Future == Other than those listed above, some of the future hurdles that the science of machine perception still has to overcome include, but are not limited to: - [Embodied cognition](/source/Embodied_cognition) - The theory that cognition is a full body experience, and therefore can only exist, and therefore be measure and analyzed, in fullness if all required human abilities and processes are working together through a mutually aware and supportive systems network. - The [Moravec's paradox](/source/Moravec's_paradox) (see the link) - The [Principle of similarity](/source/Principle_of_similarity) - The ability young children develop to determine what family a newly introduced stimulus falls under even when the said stimulus is different from the members with which the child usually associates said family with. (An example could be a child figuring that a chihuahua is a dog and house pet rather than vermin.) - The [Unconscious inference](/source/Unconscious_inference): The natural human behavior of determining if a new stimulus is dangerous or not, what it is, and then how to relate to it without ever requiring any new conscious effort. - The innate human ability to follow the [likelihood principle](/source/likelihood_principle) in order to learn from circumstances and others over time. - The [recognition-by-components theory](/source/recognition-by-components_theory) - being able to mentally analyze and break even complicated mechanisms into manageable parts with which to interact with. For example: A person seeing both the cup and the handle parts that make up a mug full of hot cocoa, in order to use the handle to hold the mug so as to avoid being burned. - The [free energy principle](/source/Unconscious_inference) - determining long before hand how much energy one can safely delegate to being aware of things outside one's self without the loss of the needed energy one requires for sustaining their life and function satisfactorily. This allows one to become both optimally aware of the world around them self without depleting their energy so much that they experience damaging stress, decision fatigue, and/or exhaustion. ==See also== * [Robotic sensing](/source/Robotic_sensing) * [Sensor](/source/Sensor)s * [SLAM](/source/Simultaneous_localization_and_mapping) *[History of artificial intelligence](/source/History_of_artificial_intelligence) ==References== {{reflist| {{cite journal| author=Turk, Matthew | journal=Chinese Journal of Computers | volume= 12 | date= 2000 | title=Perceptive Media: Machine Perception and Human Computer Interaction|url=http://cs.ucsb.edu/~mturk/Papers/PerceptiveMedia.pdf}} pages 1235-1244 {{cite book |doi=10.1109/CVPR.2011.5995467|chapter-url=https://dspace.sunyconnect.suny.edu/bitstream/handle/1951/55408/Dhar_grad.sunysb_0771M_10339.pdf?sequence=1|chapter = High level describable attributes for predicting aesthetics and interestingness|title = CVPR 2011|pages = 1657–1664|year = 2011|last1 = Dhar|first1 = Sagnik|last2 = Ordonez|first2 = Vicente|last3 = Berg|first3 = Tamara L.| hdl=1951/55408 |isbn = 978-1-4577-0394-2| s2cid=14609200 }} {{Cite journal |doi = 10.1109/MSP.2010.937498|title = Machine Hearing: An Emerging Field [Exploratory DSP|journal = IEEE Signal Processing Magazine|volume = 27|issue = 5|pages = 131–139|year = 2010|last1 = Lyon|first1 = Richard|bibcode = 2010ISPM...27..131L| s2cid=13143070 }} {{cite web| author=Malcolm Tatum| url=http://www.wisegeek.com/what-is-machine-perception.htm| date= October 3, 2012| title=What is Machine Perception}} {{cite arXiv| author=Alexander Serov| date= January 29, 2013| title=Subjective Reality and Strong Artificial Intelligence| eprint=1301.6359| class=cs.AI}} }} {{DEFAULTSORT:Machine Perception}} Category:Artificial intelligence Category:Artificial intelligence engineering --- Adapted from the Wikipedia article [Machine perception](https://en.wikipedia.org/wiki/Machine_perception) by Wikipedia contributors ([contributor history](https://en.wikipedia.org/wiki/Machine_perception?action=history)). Available under [Creative Commons Attribution-ShareAlike 4.0 International](https://creativecommons.org/licenses/by-sa/4.0/). Changes may have been made.