Active segmention of scanned images based on deep reinforcement learning for OCR applications
A system for partitioning a two-dimensional (2D) array and recognizing elements of the 2D array selects a location in an array comprising pixel data of the 2D array; and selects a direction in which to traverse the array from the selected location to segment the elements of the 2D array. The system...
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 | Qi, Xuewei Hiemenga, David J Clifford, David H Mengistu, Yehenew G Bulan, Orhan |
| description | A system for partitioning a two-dimensional (2D) array and recognizing elements of the 2D array selects a location in an array comprising pixel data of the 2D array; and selects a direction in which to traverse the array from the selected location to segment the elements of the 2D array. The system uses a model and a reward/penalty function to guide the traversal through the array. The system changes direction when the data encountered while traversing the array in the selected direction represents one of the elements of the 2D array and continues in the selected direction when the data represents a joint between two elements of the 2D array. The system recognizes one or more of the elements of the 2D array segmented by traversing the array. |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US10685261B2</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US10685261B2</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US10685261B23</originalsourceid><addsrcrecordid>eNqNjM0KwjAQhHvxIOo7rA8g2IqlVy2KN8Gfo5Q1nZRAuwnd4PObgg_gaZj5ZmaevQ4mug9I0Q2Q6LyQt6SGRdCSG7iD0ps1mYRaINAIJ9aPBtOAevAoTjpKEV3rG3EIvTM8Xekym1nuFaufLrL1-fSoLxsE30ADGwhi87zn27LaF2V-LHb_dL7WMDwb</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Active segmention of scanned images based on deep reinforcement learning for OCR applications</title><source>esp@cenet</source><creator>Qi, Xuewei ; Hiemenga, David J ; Clifford, David H ; Mengistu, Yehenew G ; Bulan, Orhan</creator><creatorcontrib>Qi, Xuewei ; Hiemenga, David J ; Clifford, David H ; Mengistu, Yehenew G ; Bulan, Orhan</creatorcontrib><description>A system for partitioning a two-dimensional (2D) array and recognizing elements of the 2D array selects a location in an array comprising pixel data of the 2D array; and selects a direction in which to traverse the array from the selected location to segment the elements of the 2D array. The system uses a model and a reward/penalty function to guide the traversal through the array. The system changes direction when the data encountered while traversing the array in the selected direction represents one of the elements of the 2D array and continues in the selected direction when the data represents a joint between two elements of the 2D array. The system recognizes one or more of the elements of the 2D array segmented by traversing the array.</description><language>eng</language><subject>CALCULATING ; COMPUTING ; COUNTING ; ELECTRIC COMMUNICATION TECHNIQUE ; ELECTRICITY ; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ; PHYSICS ; PICTORIAL COMMUNICATION, e.g. TELEVISION</subject><creationdate>2020</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=20200616&DB=EPODOC&CC=US&NR=10685261B2$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20200616&DB=EPODOC&CC=US&NR=10685261B2$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>Qi, Xuewei</creatorcontrib><creatorcontrib>Hiemenga, David J</creatorcontrib><creatorcontrib>Clifford, David H</creatorcontrib><creatorcontrib>Mengistu, Yehenew G</creatorcontrib><creatorcontrib>Bulan, Orhan</creatorcontrib><title>Active segmention of scanned images based on deep reinforcement learning for OCR applications</title><description>A system for partitioning a two-dimensional (2D) array and recognizing elements of the 2D array selects a location in an array comprising pixel data of the 2D array; and selects a direction in which to traverse the array from the selected location to segment the elements of the 2D array. The system uses a model and a reward/penalty function to guide the traversal through the array. The system changes direction when the data encountered while traversing the array in the selected direction represents one of the elements of the 2D array and continues in the selected direction when the data represents a joint between two elements of the 2D array. The system recognizes one or more of the elements of the 2D array segmented by traversing the array.</description><subject>CALCULATING</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>ELECTRIC COMMUNICATION TECHNIQUE</subject><subject>ELECTRICITY</subject><subject>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</subject><subject>PHYSICS</subject><subject>PICTORIAL COMMUNICATION, e.g. TELEVISION</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2020</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNjM0KwjAQhHvxIOo7rA8g2IqlVy2KN8Gfo5Q1nZRAuwnd4PObgg_gaZj5ZmaevQ4mug9I0Q2Q6LyQt6SGRdCSG7iD0ps1mYRaINAIJ9aPBtOAevAoTjpKEV3rG3EIvTM8Xekym1nuFaufLrL1-fSoLxsE30ADGwhi87zn27LaF2V-LHb_dL7WMDwb</recordid><startdate>20200616</startdate><enddate>20200616</enddate><creator>Qi, Xuewei</creator><creator>Hiemenga, David J</creator><creator>Clifford, David H</creator><creator>Mengistu, Yehenew G</creator><creator>Bulan, Orhan</creator><scope>EVB</scope></search><sort><creationdate>20200616</creationdate><title>Active segmention of scanned images based on deep reinforcement learning for OCR applications</title><author>Qi, Xuewei ; Hiemenga, David J ; Clifford, David H ; Mengistu, Yehenew G ; Bulan, Orhan</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US10685261B23</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2020</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC COMMUNICATION TECHNIQUE</topic><topic>ELECTRICITY</topic><topic>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</topic><topic>PHYSICS</topic><topic>PICTORIAL COMMUNICATION, e.g. TELEVISION</topic><toplevel>online_resources</toplevel><creatorcontrib>Qi, Xuewei</creatorcontrib><creatorcontrib>Hiemenga, David J</creatorcontrib><creatorcontrib>Clifford, David H</creatorcontrib><creatorcontrib>Mengistu, Yehenew G</creatorcontrib><creatorcontrib>Bulan, Orhan</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Qi, Xuewei</au><au>Hiemenga, David J</au><au>Clifford, David H</au><au>Mengistu, Yehenew G</au><au>Bulan, Orhan</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Active segmention of scanned images based on deep reinforcement learning for OCR applications</title><date>2020-06-16</date><risdate>2020</risdate><abstract>A system for partitioning a two-dimensional (2D) array and recognizing elements of the 2D array selects a location in an array comprising pixel data of the 2D array; and selects a direction in which to traverse the array from the selected location to segment the elements of the 2D array. The system uses a model and a reward/penalty function to guide the traversal through the array. The system changes direction when the data encountered while traversing the array in the selected direction represents one of the elements of the 2D array and continues in the selected direction when the data represents a joint between two elements of the 2D array. The system recognizes one or more of the elements of the 2D array segmented by traversing the array.</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_epo_espacenet_US10685261B2 |
| source | esp@cenet |
| subjects | CALCULATING COMPUTING COUNTING ELECTRIC COMMUNICATION TECHNIQUE ELECTRICITY IMAGE DATA PROCESSING OR GENERATION, IN GENERAL PHYSICS PICTORIAL COMMUNICATION, e.g. TELEVISION |
| title | Active segmention of scanned images based on deep reinforcement learning for OCR applications |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-20T18%3A59%3A41IST&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=Qi,%20Xuewei&rft.date=2020-06-16&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS10685261B2%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 |