[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-1-en-105":3,"doc-seo-335997-105":53,"doc-detail-335997-en":127},{"code":4,"msg":5,"data":6},0,"success",[7,14,19,24,29,34,39,44,49],{"id":8,"doc_module":9,"doc_module_name":10,"category_name":11,"show_sort_weight":12,"slug":13},11,1,"Template","Presentations",90,"presentations",{"id":15,"doc_module":9,"doc_module_name":10,"category_name":16,"show_sort_weight":17,"slug":18},12,"Resumes",80,"resumes",{"id":20,"doc_module":9,"doc_module_name":10,"category_name":21,"show_sort_weight":22,"slug":23},14,"Invoices",70,"invoices",{"id":25,"doc_module":9,"doc_module_name":10,"category_name":26,"show_sort_weight":27,"slug":28},15,"Posters",60,"posters",{"id":30,"doc_module":9,"doc_module_name":10,"category_name":31,"show_sort_weight":32,"slug":33},16,"Social Media",50,"social-media",{"id":35,"doc_module":9,"doc_module_name":10,"category_name":36,"show_sort_weight":37,"slug":38},17,"Forms",40,"forms",{"id":40,"doc_module":9,"doc_module_name":10,"category_name":41,"show_sort_weight":42,"slug":43},18,"Letters",30,"letters",{"id":45,"doc_module":9,"doc_module_name":10,"category_name":46,"show_sort_weight":47,"slug":48},21,"Paper Templates",5,"papers-templates",{"id":50,"doc_module":9,"doc_module_name":10,"category_name":51,"show_sort_weight":4,"slug":52},158,"General","general-158",{"code":4,"msg":54,"data":55},"ok",{"site_id":56,"language":57,"slug":58,"title":59,"keywords":60,"description":61,"schema_data":62,"social_meta":120,"head_meta":122,"extra_data":124,"updated_unix":126},105,"en","a-study-on-automated-invoice-recognition-and-text-correction-paper","A study on automated invoice recognition and text correction - Paper","","Automated parcel and package acceptance systems are increasingly required due to growth in domestic delivery and e-commerce, yet full automation is hindered by low kiosk usage among middle-aged and elderly users and by limitations of paper-based receipts. The study proposes a system that automatically corrects and digitizes handwritten invoices and package information. It uses an image segmentation model for noise-resistant invoice image extraction and a visual document understanding model with an LLM-based correction algorithm to correct misrecognized address information. Additional strategies for handwriting recognition are presented to improve accuracy and enable error and typo detection and correction.",{"@graph":63,"@context":119},[64,80,102],{"@type":65,"itemListElement":66},"BreadcrumbList",[67,71,74,77],{"item":68,"name":69,"@type":70,"position":9},"https://docshare.wps.com","Home","ListItem",{"item":72,"name":10,"@type":70,"position":73},"https://docshare.wps.com/template/",2,{"item":75,"name":21,"@type":70,"position":76},"https://docshare.wps.com/template/invoices/",3,{"item":78,"name":59,"@type":70,"position":79},"https://docshare.wps.com/template/a-study-on-automated-invoice-recognition-and-text-correction-paper/335997/",4,{"url":78,"name":59,"@type":81,"image":82,"author":87,"headline":59,"publisher":90,"fileFormat":93,"inLanguage":57,"description":61,"dateModified":94,"datePublished":95,"encodingFormat":93,"isAccessibleForFree":96,"interactionStatistic":97},"DigitalDocument",{"url":83,"@type":84,"width":85,"height":86},"https://docshare.wps.com/thumbnails/a-study-on-automated-invoice-recognition-and-text-correction-paper/335997.png","ImageObject",442,249,{"name":88,"@type":89},"Evangeline","Person",{"url":68,"name":91,"@type":92},"DocShare","Organization","application/pdf","2026-10-16","2026-09-21",true,{"@type":98,"interactionType":99,"userInteractionCount":101},"InteractionCounter",{"@type":100},"ViewAction",8,{"@type":103,"mainEntity":104},"FAQPage",[105,111,115],{"name":106,"@type":107,"acceptedAnswer":108},"What problem does the study address in current parcel and package acceptance systems?","Question",{"text":109,"@type":110},"It targets the difficulty of fully automating offline parcel acceptance because many users are not comfortable with digital devices and existing paper-based receipt workflows are insufficient for modern needs.","Answer",{"name":112,"@type":107,"acceptedAnswer":113},"How does the proposed system handle handwritten invoice inputs?",{"text":114,"@type":110},"It extracts invoice images using an image segmentation model that is robust to optical and physical noise, then applies a visual document understanding model with an LLM-based correction algorithm to correct address information and output a corrected address.",{"name":116,"@type":107,"acceptedAnswer":117},"Which technologies are used to digitize information from invoice images?",{"text":118,"@type":110},"The system relies on image segmentation for detecting the parcel/bill regions and OCR for recognizing characters on the bill, with deep learning-based segmentation enabling improved boundary separation under noise.","https://schema.org",{"og:url":78,"og:type":121,"og:title":59,"og:site_name":91,"og:description":61},"article",{"robots":123,"canonical":78},"index,follow",{"doc_id":125,"site_id":56},335997,1791281453,{"code":4,"msg":5,"data":128},{"doc_id":125,"user_id":129,"nickname":88,"user_avatar":130,"doc_module":9,"category_id":20,"category_name":21,"doc_title":59,"doc_description":61,"doc_content":131,"file_id":132,"file_url":133,"file_type":134,"file_size":135,"view_count":101,"is_deleted":4,"is_public":9,"is_downloadable":9,"audit_status":9,"page_count":101,"language":136,"language_code":57,"site_id":56,"html_lang":57,"table_of_contents":137,"faqs":138,"seo_title":139,"seo_description":61,"update_tm":140,"read_time":76},13056703019662,"https://ap-avatar.wpscdn.com/avatar/be000253a8e92610077?_k=1778726343310543188","Journal of Advanced Marine Engineering and Technology, Vol. 48, No. 6, pp. 516~523, 2024 J. Advanced Marine Engineering and Technology (JAMET) [https://doi.org/10.5916/jamet.2024.48.6.516](https://doi.org/10.5916/jamet.2024.48.6.516)  \nISSN 2234-7925 (Print)  \nISSN 2765-4796 (Online)  \nOriginal Paper  \nA study on automated invoice recognition and text correction  \nJin-Se Lee 1 ㆍ Kyu-Wan Han2 ㆍ Hong-Il Seo3 ㆍ Dong-Hoan Seo†  \n(Received December 1, 2024； Revised December 11, 2024；Accepted December 27, 2024)  \n\n| Abstract: Recently, with the growth of the domestic parcel delivery and e-commerce markets, there has been an increasing demand for automated parcel and package acceptance systems. The post office and convenience stores are using kiosks to replace them, but the usage rate of middle-aged and elderly people, who are the main users who are not familiar with digital devices, is low, making it difficult to call it a reasonable automation method. In addition, the existing paper-based receipt system is insufficient to meet modern requirements. Therefore, this paper proposes a system that automatically corrects and digitizes handwritten invoices and package information. The proposed system extracts invoice images that are resistant to optical and physical noise through an image segmentation model, and uses a visual document understanding model to correct address information that has been incorrectly recognized through an LLM-based correction algorithm to output the address. In particular, the system presents strategies for improving and commercializing the overall system by extracting areas ofthe invoice that were previously inferred using image processing algorithms alone, and by pre-and post-processing display models for handwriting recognition. This improves the performance of systems that process handwritten invoices and enables the detection and correction of errors and typos.\u003Cbr>Keywords: Handwritten, Invoice recognition system, Segmentation, Visual document understanding, Large language model |  |\n| --- | --- |\n| 1. Introduction | process while aligning with the existing parcel delivery system is |\n| The recent exponential growth of the domestic parcel delivery | essential. Consequently, to automate the postal and parcel deliv- |\n| and e-commerce markets has resulted in a surge in demand for | ery system, a technology capable of recognizing and digitizing |\n| unmanned and automated parcel and package acceptance sys- | existing handwritten parcel bills from images captured by a cam- |\n| tems, which are essential for maintaining the quality of service in | era is required. |\n| the logistics system. The majority of online services within the | Two distinct technologies are employed to facilitate the digit- |\n| domain of logistics systems are automated in a manner that ena- | ization of the information present on the bill. The first of these is |\n| bles users to convey the information they require via chatbots that | image segmentation, which is responsible for detecting both the |\n| utilize Large Language Models (LLM) . In the context of offline | load and the bill within the image. The second is optical character |\n| services, post offices and grocery stores are supplanting the func- | recognition (OCR), which is tasked with recognizing the charac- |\n| tions of printing invoices, calculating delivery charges, and pro- | ters present on the bill. Image segmentation is a method of delin- |\n| cessing payments, which were previously performed by humans, | eating the boundary of the object of interest from the background |\n| with the use of kiosks. Nevertheless, full automation remains | and surrounding noise. Image segmentation is employed to dif- |\n| challenging due to the low usage rate of middle-aged and elderly | ferentiate between parcels and invoices, thereby enhancing the |\n| individuals who are less familiar with digital devices. To address | precision of text recognition in invoices. With the advent of deep |\n| this is","cbCair5VDKJwdghB","https://ap.wps.com/l/cbCair5VDKJwdghB","pdf",679911,"English","# Abstract\n# 1. Introduction\n## Automated parcel and package acceptance demand\n## Kiosk-based invoice and payment processing\n## Handwritten bill digitization approach\n# 2. Methods Overview\n## Image segmentation for invoice and parcel separation\n## OCR for character recognition\n## Deep learning and model limitations\n# Corresponding Author and Author Affiliations\n## Submission and publication metadata\n# Open Access and Copyright","[{\"question\":\"What problem does the study address in current parcel and package acceptance systems?\",\"answer\":\"It targets the difficulty of fully automating offline parcel acceptance because many users are not comfortable with digital devices and existing paper-based receipt workflows are insufficient for modern needs.\"},{\"question\":\"How does the proposed system handle handwritten invoice inputs?\",\"answer\":\"It extracts invoice images using an image segmentation model that is robust to optical and physical noise, then applies a visual document understanding model with an LLM-based correction algorithm to correct address information and output a corrected address.\"},{\"question\":\"Which technologies are used to digitize information from invoice images?\",\"answer\":\"The system relies on image segmentation for detecting the parcel/bill regions and OCR for recognizing characters on the bill, with deep learning-based segmentation enabling improved boundary separation under noise.\"}]","A study on automated invoice recognition and text correction - Paper | PDF",1790013094]