Denoising Letter Images from Scanned Invoices Using Stacked Autoencoders
Invoice document digitization is crucial for efficient management in industries. The scanned invoice image is often noisy due to various reasons. This affects the OCR (optical character recognition) detection accuracy. In this paper, letter data obtained from images of invoices are denoised using a...
Uloženo v:
| Vydáno v: | Computers, materials & continua Ročník 71; číslo 1; s. 1371 - 1386 |
|---|---|
| Hlavní autoři: | , , , , , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Henderson
Tech Science Press
2022
|
| Témata: | |
| ISSN: | 1546-2226, 1546-2218, 1546-2226 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Invoice document digitization is crucial for efficient management in industries. The scanned invoice image is often noisy due to various reasons. This affects the OCR (optical character recognition) detection accuracy. In this paper, letter data obtained from images of invoices are denoised using a modified autoencoder based deep learning method. A stacked denoising autoencoder (SDAE) is implemented with two hidden layers each in encoder network and decoder network. In order to capture the most salient features of training samples, a undercomplete autoencoder is designed with non-linear encoder and decoder function. This autoencoder is regularized for denoising application using a combined loss function which considers both mean square error and binary cross entropy. A dataset consisting of 59,119 letter images, which contains both English alphabets (upper and lower case) and numbers (0 to 9) is prepared from many scanned invoices images and windows true type (.ttf) files, are used for training the neural network. Performance is analyzed in terms of Signal to Noise Ratio (SNR), Peak Signal to Noise Ratio (PSNR), Structural Similarity Index (SSIM) and Universal Image Quality Index (UQI) and compared with other filtering techniques like Nonlocal Means filter, Anisotropic diffusion filter, Gaussian filters and Mean filters. Denoising performance of proposed SDAE is compared with existing SDAE with single loss function in terms of SNR and PSNR values. Results show the superior performance of proposed SDAE method. |
|---|---|
| AbstractList | Invoice document digitization is crucial for efficient management in industries. The scanned invoice image is often noisy due to various reasons. This affects the OCR (optical character recognition) detection accuracy. In this paper, letter data obtained from images of invoices are denoised using a modified autoencoder based deep learning method. A stacked denoising autoencoder (SDAE) is implemented with two hidden layers each in encoder network and decoder network. In order to capture the most salient features of training samples, a undercomplete autoencoder is designed with non-linear encoder and decoder function. This autoencoder is regularized for denoising application using a combined loss function which considers both mean square error and binary cross entropy. A dataset consisting of 59,119 letter images, which contains both English alphabets (upper and lower case) and numbers (0 to 9) is prepared from many scanned invoices images and windows true type (.ttf) files, are used for training the neural network. Performance is analyzed in terms of Signal to Noise Ratio (SNR), Peak Signal to Noise Ratio (PSNR), Structural Similarity Index (SSIM) and Universal Image Quality Index (UQI) and compared with other filtering techniques like Nonlocal Means filter, Anisotropic diffusion filter, Gaussian filters and Mean filters. Denoising performance of proposed SDAE is compared with existing SDAE with single loss function in terms of SNR and PSNR values. Results show the superior performance of proposed SDAE method. |
| Author | Hanif, Muhammad Sehar, Tayyaba Kim, DoHyeun Jamil, Faisal Lee, YunJung Ibrahim, Muhammad Ahmad, Shabir |
| Author_xml | – sequence: 1 givenname: Muhammad surname: Ibrahim fullname: Ibrahim, Muhammad – sequence: 2 givenname: Muhammad surname: Hanif fullname: Hanif, Muhammad – sequence: 3 givenname: Shabir surname: Ahmad fullname: Ahmad, Shabir – sequence: 4 givenname: Faisal surname: Jamil fullname: Jamil, Faisal – sequence: 5 givenname: Tayyaba surname: Sehar fullname: Sehar, Tayyaba – sequence: 6 givenname: YunJung surname: Lee fullname: Lee, YunJung – sequence: 7 givenname: DoHyeun surname: Kim fullname: Kim, DoHyeun |
| BookMark | eNpNkD1rwzAQhkVJoUnavaOhs1N9WbbGkH4kEOiQZhaydApOaymV7EL_fZ24Q4fjPV4e7uCZoYkPHhC6J3jBqMD80bRmQTGli2F4UV2hKSm4yCmlYvJvv0GzlI4YM8EknqL1E_jQpMYfsi10HcRs0-oDpMzF0GY7o70Hm238d2jM0O4v5K7T5mOol30XwJtgIaZbdO30Z4K7v5yj_cvz-2qdb99eN6vlNjdUiC631gFnIHntSopLQYg1mmpeCW0NwbZ2hlYCitIxXhDrSEVlrR2A1KR0jrM5ehjvnmL46iF16hj66IeX6qxBSomxHCg8UiaGlCI4dYpNq-OPIlhdfKnBlzr7UqMv9gsCGmBr |
| Cites_doi | 10.1007/s10796-014-9527-0 10.1089/big.2020.0284 10.1109/97.995823 10.1109/TIP.2018.2811546 10.1109/TIP.2007.901238 10.1109/MSP.2011.2179329 10.1109/TASSP.1986.1164857 10.1007/s11276-021-02554-w 10.1109/82.749102 10.1080/08839514.2014.954344 10.1137/040605412 10.1016/j.neunet.2020.07.025 10.1109/TCS.1987.1086066 10.1016/j.imavis.2008.06.006 10.1109/TPAMI.2016.2596743 10.2166/wst.2020.369 10.1016/S0262-8856(99)00020-7 10.1137/040616024 10.1109/83.869182 10.1109/TIP.2014.2316423 10.1109/83.503916 10.1186/s42492-019-0016-7 10.1109/TIP.2006.881969 10.1109/JSAIT.2020.2991563 10.1109/TIP.2003.819861 10.1016/j.patcog.2013.05.014 10.1109/ACCESS.2020.3011705 |
| ContentType | Journal Article |
| Copyright | 2022. This work is licensed under https://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
| Copyright_xml | – notice: 2022. This work is licensed under https://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
| DBID | AAYXX CITATION 7SC 7SR 8BQ 8FD ABUWG AFKRA AZQEC BENPR CCPQU COVID DWQXO JG9 JQ2 L7M L~C L~D PHGZM PHGZT PIMPY PKEHL PQEST PQQKQ PQUKI PRINS |
| DOI | 10.32604/cmc.2022.022458 |
| DatabaseName | CrossRef Computer and Information Systems Abstracts Engineered Materials Abstracts METADEX Technology Research Database ProQuest Central (Alumni) ProQuest Central UK/Ireland ProQuest Central Essentials ProQuest Central Database Suite (ProQuest) ProQuest One Coronavirus Research Database ProQuest Central Korea Materials Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional ProQuest Central Premium ProQuest One Academic (New) ProQuest Publicly Available Content Database ProQuest One Academic Middle East (New) ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Academic (retired) ProQuest One Academic UKI Edition ProQuest Central China |
| DatabaseTitle | CrossRef Publicly Available Content Database Materials Research Database Technology Research Database Computer and Information Systems Abstracts – Academic ProQuest One Academic Middle East (New) ProQuest Central Essentials ProQuest One Academic Eastern Edition ProQuest Computer Science Collection Computer and Information Systems Abstracts Coronavirus Research Database ProQuest Central (Alumni Edition) ProQuest One Community College ProQuest Central China METADEX Computer and Information Systems Abstracts Professional ProQuest Central Engineered Materials Abstracts ProQuest One Academic UKI Edition ProQuest Central Korea ProQuest Central (New) ProQuest One Academic Advanced Technologies Database with Aerospace ProQuest One Academic (New) |
| DatabaseTitleList | Publicly Available Content Database |
| Database_xml | – sequence: 1 dbid: PIMPY name: ProQuest Publicly Available Content Database url: http://search.proquest.com/publiccontent sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISSN | 1546-2226 |
| EndPage | 1386 |
| ExternalDocumentID | 10_32604_cmc_2022_022458 |
| GroupedDBID | AAFWJ AAYXX ACIWK ADMLS AFFHD AFKRA ALMA_UNASSIGNED_HOLDINGS BENPR CCPQU CITATION EBS EJD J9A OK1 P2P PHGZM PHGZT PIMPY RTS TUS 7SC 7SR 8BQ 8FD ABUWG AZQEC COVID DWQXO JG9 JQ2 L7M L~C L~D PKEHL PQEST PQQKQ PQUKI PRINS |
| ID | FETCH-LOGICAL-c266t-ddfe43e94bf7207611dca2a486adc10dbfc286e57f3451df1829bafee9a17ff43 |
| IEDL.DBID | BENPR |
| ISICitedReferencesCount | 5 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000717553300034&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1546-2226 1546-2218 |
| IngestDate | Sun Jun 29 16:33:04 EDT 2025 Sat Nov 29 03:13:20 EST 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 1 |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c266t-ddfe43e94bf7207611dca2a486adc10dbfc286e57f3451df1829bafee9a17ff43 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| OpenAccessLink | https://www.proquest.com/docview/2604999009?pq-origsite=%requestingapplication% |
| PQID | 2604999009 |
| PQPubID | 2048737 |
| PageCount | 16 |
| ParticipantIDs | proquest_journals_2604999009 crossref_primary_10_32604_cmc_2022_022458 |
| PublicationCentury | 2000 |
| PublicationDate | 2022-00-00 20220101 |
| PublicationDateYYYYMMDD | 2022-01-01 |
| PublicationDate_xml | – year: 2022 text: 2022-00-00 |
| PublicationDecade | 2020 |
| PublicationPlace | Henderson |
| PublicationPlace_xml | – name: Henderson |
| PublicationTitle | Computers, materials & continua |
| PublicationYear | 2022 |
| Publisher | Tech Science Press |
| Publisher_xml | – name: Tech Science Press |
| References | Jain (ref5) 2016; 18 Liang (ref39) 2015 Bernstein (ref13) 1987; 34 Sit (ref32) 2020; 82 Fan (ref2) 2019; 2 Fan (ref6) 2001 Gu (ref24) 2014 Wang (ref12) 1999; 46 Elad (ref21) 2006; 15 Zuo (ref27) 2014; 23 Dabov (ref20) 2007; 16 Hong (ref15) 2000; 18 Wang (ref43) 2002; 9 Osher (ref22) 2005; 4 Khayyat (ref29) 2020; 8 Xu (ref36) 2015 Buades (ref16) 2005; 4 Shoren (ref30) 2021; 8 Vincent (ref41) 2010; 11 Barni (ref10) 2000; 9 Li (ref18) 2009; 27 Elgendy (ref33) 2021; 9 Krizhevsky (ref34) 2012; 25 Buades (ref19) 2005; 2 Al-Khaffaf (ref9) 2008 Goodfellow (ref40) 2016; 1 Tian (ref35) 2020; 131 Farahanirad (ref8) 2011 Hari (ref14) 2013; 46 Saba (ref17) 2014; 28 Mairal (ref25) 2009 Pitas (ref7) 1986; 34 Milanfar (ref3) 2012; 30 Abreu (ref11) 1996; 5 Elgendy (ref31) 2021; 27 Jain (ref37) 2008; 21 Wang (ref42) 2004; 13 Ongie (ref28) 2020; 1 Xu (ref1) 2018; 27 Schmidt (ref23) 2014 Chen (ref26) 2016; 39 Motwani (ref4) 2004 Vincent (ref38) 2008 |
| References_xml | – volume: 18 start-page: 159 year: 2016 ident: ref5 article-title: A survey of edge-preserving image denoising methods publication-title: Information Systems Frontiers doi: 10.1007/s10796-014-9527-0 – volume: 9 start-page: 265 year: 2021 ident: ref33 article-title: Advanced deep learning for resource allocation and security aware data offloading in industrial mobile edge computing publication-title: Journal of Big Data doi: 10.1089/big.2020.0284 – start-page: 1184 year: 2015 ident: ref36 article-title: Denoising convolutional neural network – volume: 9 start-page: 81 year: 2002 ident: ref43 article-title: A universal image quality index publication-title: IEEE Signal Processing Letters doi: 10.1109/97.995823 – volume: 11 start-page: 3371 year: 2010 ident: ref41 article-title: Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion publication-title: Journal of Machine Learning Research – volume: 27 start-page: 2996 year: 2018 ident: ref1 article-title: External prior guided internal prior learning for real-world noisy image denoising publication-title: IEEE Transactions on Image Processing doi: 10.1109/TIP.2018.2811546 – volume: 16 start-page: 2080 year: 2007 ident: ref20 article-title: Image denoising by sparse 3-d transform-domain collaborative filtering publication-title: IEEE Transactions on Image Processing doi: 10.1109/TIP.2007.901238 – volume: 30 start-page: 106 year: 2012 ident: ref3 article-title: A tour of modern image filtering: New insights and methods, both practical and theoretical publication-title: IEEE Signal Processing Magazine doi: 10.1109/MSP.2011.2179329 – volume: 34 start-page: 573 year: 1986 ident: ref7 article-title: Nonlinear mean filters in image processing publication-title: IEEE Transactions on Acoustics, Speech, and Signal Processing doi: 10.1109/TASSP.1986.1164857 – volume: 2 start-page: 60 year: 2005 ident: ref19 article-title: A non-local algorithm for image denoising – volume: 27 start-page: 2023 year: 2021 ident: ref31 article-title: Joint computation offloading and task caching for multi-user and multi-task MEC systems: Reinforcement learning-based algorithms publication-title: Wireless Networks doi: 10.1007/s11276-021-02554-w – start-page: 34 year: 2001 ident: ref6 article-title: Binarizing document image using coplanar prefilter – volume: 46 start-page: 78 year: 1999 ident: ref12 article-title: Progressive switching median filter for the removal of impulse noise from highly corrupted images publication-title: IEEE Transactions on Circuits and Systems II: Analog and Digital Signal Processin doi: 10.1109/82.749102 – volume: 1 start-page: 496 year: 2016 ident: ref40 article-title: Autoencoders publication-title: Deep Learning – volume: 28 start-page: 879 year: 2014 ident: ref17 article-title: Evaluation of current documents image denoising techniques: A comparative study publication-title: Applied Artificial Intelligence doi: 10.1080/08839514.2014.954344 – volume: 4 start-page: 460 year: 2005 ident: ref22 article-title: An iterative regularization method for total variation-based image restoration publication-title: Multiscale Modeling & Simulation doi: 10.1137/040605412 – volume: 131 start-page: 251 year: 2020 ident: ref35 article-title: Deep learning on image denoising: An overview publication-title: Neural Networks doi: 10.1016/j.neunet.2020.07.025 – volume: 34 start-page: 1275 year: 1987 ident: ref13 article-title: Adaptive nonlinear filters for simultaneous removal of different kinds of noise in images publication-title: IEEE Transactions on Circuits and Systems doi: 10.1109/TCS.1987.1086066 – start-page: 697 year: 2015 ident: ref39 article-title: Stacked denoising autoencoder and dropout together to prevent overfitting in deep neural network – volume: 27 start-page: 623 year: 2009 ident: ref18 article-title: Support vector regression based image denoising publication-title: Image and Vision Computing doi: 10.1016/j.imavis.2008.06.006 – volume: 39 start-page: 1256 year: 2016 ident: ref26 article-title: Trainable nonlinear reaction diffusion: A flexible framework for fast and effective image restoration publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence doi: 10.1109/TPAMI.2016.2596743 – volume: 82 start-page: 2635 year: 2020 ident: ref32 article-title: A comprehensive review of deep learning applications in hydrology and water resources publication-title: Water Science Technology doi: 10.2166/wst.2020.369 – volume: 18 start-page: 573 year: 2000 ident: ref15 article-title: An edge-preserving sub-band coding model based on non-adaptive and adaptive regularization publication-title: Image and Vision Computing doi: 10.1016/S0262-8856(99)00020-7 – volume: 4 start-page: 490 year: 2005 ident: ref16 article-title: A review of image denoising algorithms, with a new one publication-title: Multiscale Modeling & Simulation doi: 10.1137/040616024 – start-page: 1096 year: 2008 ident: ref38 article-title: Extracting and composing robust features with denoising autoencoders – start-page: 2862 year: 2014 ident: ref24 article-title: Weighted nuclear norm minimization with application to image denoising – volume: 21 start-page: 769 year: 2008 ident: ref37 article-title: Natural image denoising with convolutional networks publication-title: Advances in Neural Information Processing System – volume: 9 start-page: 1704 year: 2000 ident: ref10 article-title: A quasi-euclidean norm to speed up vector median filtering publication-title: IEEE Transactions on Image Processing doi: 10.1109/83.869182 – volume: 23 start-page: 2459 year: 2014 ident: ref27 article-title: Gradient histogram estimation and preservation for texture enhanced image denoising publication-title: IEEE Transactions on Image Processing doi: 10.1109/TIP.2014.2316423 – volume: 5 start-page: 1012 year: 1996 ident: ref11 article-title: A new efficient approach for the removal of impulse noise from highly corrupted images publication-title: IEEE Transactions on Image Processing doi: 10.1109/83.503916 – volume: 25 start-page: 1097 year: 2012 ident: ref34 article-title: Imagenet classification with deep convolutional neural networks publication-title: Advances in Neural Information Processing Systems – start-page: 2272 year: 2009 ident: ref25 article-title: Non-local sparse models for image restoration – volume: 8 start-page: 1 year: 2021 ident: ref30 article-title: Deep learning applications for COVID-19 publication-title: Journal of Big Data – volume: 2 start-page: 1 year: 2019 ident: ref2 article-title: Brief review of image denoising techniques publication-title: Visual Computing for Industry, Biomedicine, and Art doi: 10.1186/s42492-019-0016-7 – volume: 15 start-page: 3736 year: 2006 ident: ref21 article-title: Image denoising via sparse and redundant representations over learned dictionaries publication-title: IEEE Transactions on Image Processing doi: 10.1109/TIP.2006.881969 – volume: 1 start-page: 39 year: 2020 ident: ref28 article-title: Deep learning techniques for inverse problems in imaging publication-title: IEEE Journal on Selected Areas in Information Theory doi: 10.1109/JSAIT.2020.2991563 – volume: 13 start-page: 600 year: 2004 ident: ref42 article-title: Image quality assessment: From error visibility to structural similarity publication-title: IEEE Transactions on Image Processing doi: 10.1109/TIP.2003.819861 – start-page: 475 year: 2011 ident: ref8 article-title: A hybrid edge detection algorithm for salt-and-pepper noise – volume: 46 start-page: 3198 year: 2013 ident: ref14 article-title: Unsharp masking using quadratic filter for the enhancement of fingerprints in noisy background publication-title: Pattern Recognition doi: 10.1016/j.patcog.2013.05.014 – volume: 8 start-page: 137052 year: 2020 ident: ref29 article-title: Advanced deep learning-based computational offloading for multilevel vehicular edge-cloud computing networks publication-title: IEEE Access doi: 10.1109/ACCESS.2020.3011705 – start-page: 27 year: 2004 ident: ref4 article-title: Survey of image denoising techniques – start-page: 1 year: 2008 ident: ref9 article-title: Removing salt-and-pepper noise from binary images of engineering drawings – start-page: 2774 year: 2014 ident: ref23 article-title: Shrinkage fields for effective image restoration |
| SSID | ssj0036390 |
| Score | 2.2604685 |
| Snippet | Invoice document digitization is crucial for efficient management in industries. The scanned invoice image is often noisy due to various reasons. This affects... |
| SourceID | proquest crossref |
| SourceType | Aggregation Database Index Database |
| StartPage | 1371 |
| SubjectTerms | Coders Image quality Machine learning Neural networks Noise reduction Object recognition Optical character recognition Signal to noise ratio Training |
| Title | Denoising Letter Images from Scanned Invoices Using Stacked Autoencoders |
| URI | https://www.proquest.com/docview/2604999009 |
| Volume | 71 |
| WOSCitedRecordID | wos000717553300034&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVPQU databaseName: ProQuest Central customDbUrl: eissn: 1546-2226 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0036390 issn: 1546-2226 databaseCode: BENPR dateStart: 20040101 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Publicly Available Content Database customDbUrl: eissn: 1546-2226 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0036390 issn: 1546-2226 databaseCode: PIMPY dateStart: 20040101 isFulltext: true titleUrlDefault: http://search.proquest.com/publiccontent providerName: ProQuest |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV07T8MwELagZWChPEWhIA8sDKF14uYxoQKt2oEqQiCVKXL8kBialCbt7-cucQQsLEwZElmR7-67z2f7PkJuBFBYzQD9fKWEw2XKnTASviNcoU3kM18NRSU2Eczn4WIRxbbgVthjlQ0mVkCtcok18j7wbiTnQAnuV58Oqkbh7qqV0NglbexUBn7efhjP45cGiz3Iv9WVyCH3HReyWb1R6eFgfbnEFoaue4dpDCXffyam37hcJZtJ57-_eUgOLM2ko9ovjsiOzo5Jp5FwoDaiT8j0SWf5B9YLaH2xh86WgDAFxWsn8JlAGKazbJsjoNDqgAEFggqxr-hoU-bYBxPPQp-St8n49XHqWHEFR0JOLh2ljOaejnhqAheLGUxJMBAPfaEkG6jUSDf09TAwHh8yZWAdEqXCaB0JFhjDvTPSyvJMnxPqaVhmSqY8bOYu3YFIAyZdmfoSyIc0gy65bWY2WdU9NBJYe1RWSMAKCVohqa3QJb1mXhMbTUXyPakXf7--JPs4Vl0i6ZFWud7oK7Int-VHsb62zgHPePYcv38B0tPFRA |
| linkProvider | ProQuest |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V25TsNAEB1BQIKGGxHOLaCgMMTrjR0XCCEgihWIUoAElVnvIaWIDTlA_BTfyIwPAQ0dBbWt1dpv9N6bPWYADiVaWOMi-_laS0eoRDitUPqO5NLY0Hd93ZR5s4mg12s9PIT9Gfio7sLQscqKE3Oi1pmiNfJT9N1kztESnD-_ONQ1inZXqxYaRVh0zfsbpmzjs-gK8T3ivH19d9lxyq4CjkIxmjhaWyM8E4rEBpyyeFcrnJlo-VIrt6ETq3jLN83AeqLpaosGPEykNSaUbmCt8HDcWZgTFOw1mOtHt_3Hivs91Pv8CmZT-A5H9Sw2Rj2a_KkaUslEzk9INqnF_Hch_KkDubi1l__bb1mBpdJGs4si7ldhxqRrsFy1qGAlY61D58qk2YDWQ1hxcYlFQ2TQMaNrNfiaJJlhUfqaEWGy_AAFQwOO3KbZxXSSUZ1POuu9Afd_8j2bUEuz1GwB8wym0crVHhWrV7whk8BVXCW-QnOlbKMOxxWS8XNRIyTG3CpHPUbUY0I9LlCvw26FY1yyxTj-AnH798cHsNC5u72Jb6JedwcWadxiOWgXapPR1OzBvHqdDMaj_TIwGTz9NeifHyUj3w |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Denoising+Letter+Images+from+Scanned+Invoices+Using+Stacked+Autoencoders&rft.jtitle=Computers%2C+materials+%26+continua&rft.au=Ibrahim%2C+Muhammad&rft.au=Hanif%2C+Muhammad&rft.au=Ahmad%2C+Shabir&rft.au=Jamil%2C+Faisal&rft.date=2022&rft.issn=1546-2226&rft.volume=71&rft.issue=1&rft.spage=1371&rft.epage=1386&rft_id=info:doi/10.32604%2Fcmc.2022.022458&rft.externalDBID=n%2Fa&rft.externalDocID=10_32604_cmc_2022_022458 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1546-2226&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1546-2226&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1546-2226&client=summon |