Editing Computer vision (section)

==System methods==
The organization of a computer vision system is highly application-dependent. Some systems are stand-alone applications that solve a specific measurement or detection problem, while others constitute a sub-system of a larger design which, for example, also contains sub-systems for control of mechanical actuators, planning, information databases, man-machine interfaces, etc. The specific implementation of a computer vision system also depends on whether its functionality is pre-specified or if some part of it can be learned or modified during operation. Many functions are unique to the application. There are, however, typical functions that are found in many computer vision systems.

* '''Image acquisition''' – A digital image is produced by one or several [[image sensor]]s, which, besides various types of light-sensitive cameras, include [[Rangefinder camera|range sensors]], tomography devices, radar, ultra-sonic cameras, etc. Depending on the type of sensor, the resulting image data is an ordinary 2D image, a 3D volume, or an image sequence. The pixel values typically correspond to light intensity in one or several spectral bands (gray images or colour images) but can also be related to various physical measures, such as depth, absorption or reflectance of sonic or electromagnetic waves, or [[magnetic resonance imaging]].<ref name="Davies-2005"/>
* '''Pre-processing''' – Before a computer vision method can be applied to image data in order to extract some specific piece of information, it is usually necessary to process the data in order to ensure that it satisfies certain assumptions implied by the method. Examples are:
** Re-sampling to ensure that the image coordinate system is correct.
** Noise reduction to ensure that sensor noise does not introduce false information.
** Contrast enhancement to ensure that relevant information can be detected.
** [[Scale space]] representation to enhance image structures at locally appropriate scales.
* '''[[Feature detection (computer vision)|Feature extraction]]''' – Image features at various levels of complexity are extracted from the image data.<ref name="Davies-2005"/> Typical examples of such features are:
** Lines, [[edge detection|edges]] and [[ridge detection|ridges]].
** Localized [[interest point detection|interest points]] such as [[corner detection|corners]], [[blob detection|blobs]] or points.
:More complex features may be related to texture, shape, or motion.
* '''[[Object detection|Detection]]/[[Image segmentation|segmentation]]''' – At some point in the processing, a decision is made about which image points or regions of the image are relevant for further processing.<ref name="Davies-2005"/> Examples are:
** Selection of a specific set of interest points.
** Segmentation of one or multiple image regions that contain a specific object of interest.
** Segmentation of image into nested scene architecture comprising foreground, object groups, single objects or [[Salience (neuroscience)|salient]] object<ref>{{cite arXiv |author=A. Maity |title=Improvised Salient Object Detection and Manipulation |year=2015|eprint=1511.02999|class=cs.CV}}</ref> parts (also referred to as spatial-taxon scene hierarchy),<ref>Barghout, Lauren. "[http://www.lirmm.fr/~lafourcade/pub/IPMU2014/papers/0443/04430163.pdf Visual Taxometric Approach to Image Segmentation Using Fuzzy-Spatial Taxon Cut Yields Contextually Relevant Regions] {{Webarchive|url=https://web.archive.org/web/20181114100658/http://www.lirmm.fr/~lafourcade/pub/IPMU2014/papers/0443/04430163.pdf |date=2018-11-14 }}." Information Processing and Management of Uncertainty in Knowledge-Based Systems. Springer International Publishing, 2014.</ref> while the [[Salience (neuroscience)|visual salience]] is often implemented as [[Visual spatial attention|spatial]] and [[Visual temporal attention|temporal attention]]. 
** Segmentation or [[Object co-segmentation|co-segmentation]] of one or multiple videos into a series of per-frame foreground masks while maintaining its temporal semantic continuity.<ref name="Liu Wang Hua Zhang 2018 pp. 5840–5853">{{cite journal | last1=Liu | first1=Ziyi | last2=Wang | first2=Le | last3=Hua | first3=Gang | last4=Zhang | first4=Qilin | last5=Niu | first5=Zhenxing | last6=Wu | first6=Ying | last7=Zheng | first7=Nanning | title=Joint Video Object Discovery and Segmentation by Coupled Dynamic Markov Networks | journal=IEEE Transactions on Image Processing | volume=27 | issue=12 | year=2018 | issn=1057-7149 | doi=10.1109/tip.2018.2859622 | pmid=30059300 | pages=5840–5853 | bibcode=2018ITIP...27.5840L | s2cid=51867241 | url=https://qilin-zhang.github.io/_pages/pdfs/Joint_Video_Object_Discovery_and_Segmentation_by_Coupled_Dynamic_Markov_Networks.pdf | access-date=2018-09-14 | archive-url=https://web.archive.org/web/20180907032435/https://qilin-zhang.github.io/_pages/pdfs/Joint_Video_Object_Discovery_and_Segmentation_by_Coupled_Dynamic_Markov_Networks.pdf | archive-date=2018-09-07 | url-status=dead }}</ref><ref name="Wang Duan Zhang Niu p=1657">{{cite journal | last1=Wang | first1=Le | last2=Duan | first2=Xuhuan | last3=Zhang | first3=Qilin | last4=Niu | first4=Zhenxing | last5=Hua | first5=Gang | last6=Zheng | first6=Nanning | title=Segment-Tube: Spatio-Temporal Action Localization in Untrimmed Videos with Per-Frame Segmentation | journal=Sensors | volume=18 | issue=5 | date=2018-05-22 | issn=1424-8220 | doi=10.3390/s18051657 | pmid=29789447 | pmc=5982167 | page=1657 | bibcode=2018Senso..18.1657W | url=https://qilin-zhang.github.io/_pages/pdfs/Segment-Tube_Spatio-Temporal_Action_Localization_in_Untrimmed_Videos_with_Per-Frame_Segmentation.pdf |archive-url=https://web.archive.org/web/20180907110146/https://qilin-zhang.github.io/_pages/pdfs/Segment-Tube_Spatio-Temporal_Action_Localization_in_Untrimmed_Videos_with_Per-Frame_Segmentation.pdf |archive-date=2018-09-07 |url-status=live | doi-access=free }}</ref>  
* '''High-level processing''' – At this step, the input is typically a small set of data, for example, a set of points or an image region, which is assumed to contain a specific object.<ref name="Davies-2005"/> The remaining processing deals with, for example:
** Verification that the data satisfies model-based and application-specific assumptions.
** Estimation of application-specific parameters, such as object pose or object size.
** [[Image recognition]] – classifying a detected object into different categories.
** [[Image registration]] – comparing and combining two different views of the same object.
* '''Decision making''' Making the final decision required for the application,<ref name="Davies-2005"/> for example:
** Pass/fail on automatic inspection applications.
** Match/no-match in recognition applications.
** Flag for further human review in medical, military, security and recognition applications.

===Image-understanding systems===
Image-understanding systems (IUS) include three levels of abstraction as follows: low level includes image primitives such as edges, texture elements, or regions; intermediate level includes boundaries, surfaces and volumes; and high level includes objects, scenes, or events. Many of these requirements are entirely topics for further research.

The representational requirements in the designing of IUS for these levels are: representation of prototypical concepts, concept organization, spatial knowledge, temporal knowledge, scaling, and description by comparison and differentiation.

While inference refers to the process of deriving new, not explicitly represented facts from currently known facts, control refers to the process that selects which of the many inference, search, and matching techniques should be applied at a particular stage of processing. Inference and control requirements for IUS are: search and hypothesis activation, matching and hypothesis testing, generation and use of expectations, change and focus of attention, certainty and strength of belief, inference and goal satisfaction.<ref>{{Cite book|title = Encyclopedia of Artificial Intelligence, Volume 1|last = Shapiro|first = Stuart C.|publisher = John Wiley & Sons, Inc.|year = 1992|isbn = 978-0-471-50306-4|location = New York|pages = 643–646}}</ref>