DETERMINING CLEAN OR DIRTY CAPTURED IMAGES
Methods are provided for determining whether an image captured by a capturing device is clean or dirty. These methods include: receiving the image captured by the image capturing device; splitting the received image into a plurality of image portions according to predefined splitting criteria; perfo...
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Patent |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | |
| container_title | |
| container_volume | |
| creator | HERCHENBACH, Daniel MHANA, Anas CARRENO, Sebastian LEHMANN, Robin |
| description | Methods are provided for determining whether an image captured by a capturing device is clean or dirty. These methods include: receiving the image captured by the image capturing device; splitting the received image into a plurality of image portions according to predefined splitting criteria; performing, for each of at least some of the image portions, a Laplacian filter of the image portion to produce a feature vector including Laplacian filter features of the image portion; providing the feature vectors to a first machine learning module that has been trained to produce a clean/dirty indicator depending on corresponding feature vector, the clean/dirty indicator including a probabilistic value of cleanness or dirtiness of corresponding image portion; and determining whether the image is clean or dirty depending on the clean/dirty indicators produced by the first machine learning module. Systems and computer programs suitable for performing such methods are also provided. |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US2019164271A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US2019164271A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US2019164271A13</originalsourceid><addsrcrecordid>eNrjZNBycQ1xDfL19PP0c1dw9nF19FPwD1Jw8QwKiVRwdgwICQ1ydVHw9HV0dw3mYWBNS8wpTuWF0twMym6uIc4euqkF-fGpxQWJyal5qSXxocFGBoaWhmYmRuaGjobGxKkCANicJXs</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>DETERMINING CLEAN OR DIRTY CAPTURED IMAGES</title><source>esp@cenet</source><creator>HERCHENBACH, Daniel ; MHANA, Anas ; CARRENO, Sebastian ; LEHMANN, Robin</creator><creatorcontrib>HERCHENBACH, Daniel ; MHANA, Anas ; CARRENO, Sebastian ; LEHMANN, Robin</creatorcontrib><description>Methods are provided for determining whether an image captured by a capturing device is clean or dirty. These methods include: receiving the image captured by the image capturing device; splitting the received image into a plurality of image portions according to predefined splitting criteria; performing, for each of at least some of the image portions, a Laplacian filter of the image portion to produce a feature vector including Laplacian filter features of the image portion; providing the feature vectors to a first machine learning module that has been trained to produce a clean/dirty indicator depending on corresponding feature vector, the clean/dirty indicator including a probabilistic value of cleanness or dirtiness of corresponding image portion; and determining whether the image is clean or dirty depending on the clean/dirty indicators produced by the first machine learning module. Systems and computer programs suitable for performing such methods are also provided.</description><language>eng</language><subject>CALCULATING ; COMPUTING ; COUNTING ; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ; PHYSICS</subject><creationdate>2019</creationdate><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20190530&DB=EPODOC&CC=US&NR=2019164271A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76290</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20190530&DB=EPODOC&CC=US&NR=2019164271A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>HERCHENBACH, Daniel</creatorcontrib><creatorcontrib>MHANA, Anas</creatorcontrib><creatorcontrib>CARRENO, Sebastian</creatorcontrib><creatorcontrib>LEHMANN, Robin</creatorcontrib><title>DETERMINING CLEAN OR DIRTY CAPTURED IMAGES</title><description>Methods are provided for determining whether an image captured by a capturing device is clean or dirty. These methods include: receiving the image captured by the image capturing device; splitting the received image into a plurality of image portions according to predefined splitting criteria; performing, for each of at least some of the image portions, a Laplacian filter of the image portion to produce a feature vector including Laplacian filter features of the image portion; providing the feature vectors to a first machine learning module that has been trained to produce a clean/dirty indicator depending on corresponding feature vector, the clean/dirty indicator including a probabilistic value of cleanness or dirtiness of corresponding image portion; and determining whether the image is clean or dirty depending on the clean/dirty indicators produced by the first machine learning module. Systems and computer programs suitable for performing such methods are also provided.</description><subject>CALCULATING</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2019</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZNBycQ1xDfL19PP0c1dw9nF19FPwD1Jw8QwKiVRwdgwICQ1ydVHw9HV0dw3mYWBNS8wpTuWF0twMym6uIc4euqkF-fGpxQWJyal5qSXxocFGBoaWhmYmRuaGjobGxKkCANicJXs</recordid><startdate>20190530</startdate><enddate>20190530</enddate><creator>HERCHENBACH, Daniel</creator><creator>MHANA, Anas</creator><creator>CARRENO, Sebastian</creator><creator>LEHMANN, Robin</creator><scope>EVB</scope></search><sort><creationdate>20190530</creationdate><title>DETERMINING CLEAN OR DIRTY CAPTURED IMAGES</title><author>HERCHENBACH, Daniel ; MHANA, Anas ; CARRENO, Sebastian ; LEHMANN, Robin</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US2019164271A13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2019</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>HERCHENBACH, Daniel</creatorcontrib><creatorcontrib>MHANA, Anas</creatorcontrib><creatorcontrib>CARRENO, Sebastian</creatorcontrib><creatorcontrib>LEHMANN, Robin</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>HERCHENBACH, Daniel</au><au>MHANA, Anas</au><au>CARRENO, Sebastian</au><au>LEHMANN, Robin</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>DETERMINING CLEAN OR DIRTY CAPTURED IMAGES</title><date>2019-05-30</date><risdate>2019</risdate><abstract>Methods are provided for determining whether an image captured by a capturing device is clean or dirty. These methods include: receiving the image captured by the image capturing device; splitting the received image into a plurality of image portions according to predefined splitting criteria; performing, for each of at least some of the image portions, a Laplacian filter of the image portion to produce a feature vector including Laplacian filter features of the image portion; providing the feature vectors to a first machine learning module that has been trained to produce a clean/dirty indicator depending on corresponding feature vector, the clean/dirty indicator including a probabilistic value of cleanness or dirtiness of corresponding image portion; and determining whether the image is clean or dirty depending on the clean/dirty indicators produced by the first machine learning module. Systems and computer programs suitable for performing such methods are also provided.</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_epo_espacenet_US2019164271A1 |
| source | esp@cenet |
| subjects | CALCULATING COMPUTING COUNTING IMAGE DATA PROCESSING OR GENERATION, IN GENERAL PHYSICS |
| title | DETERMINING CLEAN OR DIRTY CAPTURED IMAGES |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-02T19%3A11%3A44IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-epo_EVB&rft_val_fmt=info:ofi/fmt:kev:mtx:patent&rft.genre=patent&rft.au=HERCHENBACH,%20Daniel&rft.date=2019-05-30&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS2019164271A1%3C/epo_EVB%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |