Filters








55,370 Hits in 6.3 sec

Automatic document classification and indexing in high-volume applications

E. Appiani, F. Cesarini, A.M. Colla, M. Diligenti, M. Gori, S. Marinai, G. Soda
2001 International Journal on Document Analysis and Recognition  
In this paper a system for analysis and automatic indexing of imaged documents for high-volume applications is described.  ...  Experimental results are encouraging overall; in particular, document classification results fulfill the requirements of high-volume applications .  ...  We would like to acknowledge Sandra Bruzzo, Pietro Pedrazzi, Christian Pisani, and Rosa Martino (Elsag) for their valuable support in implementing and testing STRETCH; Enrico Francesconi (Dip.  ... 
doi:10.1007/pl00010904 fatcat:hl3iqkn3dbdqzbfkdaqdbzk4oe

Bringing Order to Digital Libraries: From Keyphrase Extraction to Index Term Assignment

Nicolai Erbs, Iryna Gurevych, Marc Rittberger
2013 D-Lib Magazine  
Table 7: Manually and automatically assigned index terms for an example document.  ...  Common terms like stopwords ( and, but ) have a high frequency in all documents and thus have a lower tfidf value. Terms with a medium to high tfidf value are taken as keyphrases.  ... 
doi:10.1045/september2013-erbs fatcat:hm2lmbajmzfxhdnebu64del3he

A Review on Classification and Comparison of Automatic Logo Based Document Image Retrieval Methods and other Applications

Raveendra K, P V N Reddy, P V V Kishore
2017 International Journal of Applied Engineering Research  
processing applications like Authenticity of documents, Security for information, Traffic Surveillance (Intelligent Transportation System), Pattern recognition, Marketing, Medical Imaging, Satellite imaging  ...  In this paper we provided an effective categorization of vast number of methods, techniques, transforms, algorithms, approaches and schemes available for the purpose of logo detection in various image  ...  Using these automatic logo based document image retrieval methods the data management will become easy specifically in the indexing of website contents and their maintenance.  ... 
doi:10.37622/ijaer/12.24.2017.15458-15463 fatcat:snucumgf7zbp7pxirc7dwezcya

Page 65 of The Information Management Journal Vol. 34, Issue 2 [page]

2000 The Information Management Journal  
and back office applications.  ...  Both methods have advantages and disad- vantages. A full-text search without any limiting parameters potentially delivers high volumes of irrelevant material.  ... 

Cognitive Approach in Document Indexing

Savo TOMOVIĆ, Kosta PAVLOVIĆ
2018 Eastern European Journal of Regional Studies  
Datum Solutions Cognitive Capture implements the automatic processing of administrative documents that need to be treated in a close to real time manner.  ...  The software can handle complex documents, in which the contents of different regions and fields can be highly heterogeneous with respect to layout, printing quality and the utilization of fonts and typing  ...  By the automatic processing we consider document classification and indexing.  ... 
doaj:88af51e70b7740518ec328e031b516fe fatcat:irimw43xvvgnfchiy3t66smbma

A Supervised Requirement-oriented Patent Classification Scheme Based on the Combination of Metadata and Citation Information

Fujin Zhu, Xuefeng Wang, Donghua Zhu, Yuqin Liu
2015 International Journal of Computational Intelligence Systems  
as the document representation for the new method since it can obtain relatively high classification accuracy with a dramatically simplified document preprocessing process.  ...  These static classifications are too complex and general to meet the in-depth patent classification requirements of a specific technology area or organization.  ...  In order to obtain high quality patent information to support science and technology management, such a great volume of patent documents need to be classified into some predefined taxonomies.  ... 
doi:10.1080/18756891.2015.1023588 fatcat:gj7ofy6yxvadnejhqlpgnpqfwi

Analysis of Text Classification Algorithms: A Review

Nida Zafar Khan, Prof. S. R. Yadav
2019 International Journal of Trend in Scientific Research and Development  
The primary requirement of text retrieval systems is text classification, which retrieve texts in response to a user query, and text understanding systems, which transform text in some way such as answering  ...  Classification of data has become an important research area. The process of classifying documents into predefined categories based on their content is Text classification.  ...  Text classification or Document categorization has several applications such as call center routing, automatic metadata extraction, word sense disambiguation, e-mail forwarding and spam detection, organizing  ... 
doi:10.31142/ijtsrd21448 fatcat:wxkkysjrwbh6ppca5fh265pmva

From Focused Crawling to Expert Information [chapter]

Sergej Sizov, Jens Graupmann, Martin Theobald
2003 Proceedings 2003 VLDB Conference  
In either case it attempts to explore the data behind portals by automatically generating queries to the portals and indexing the returned result pages.  ...  Two kinds of archetypes are considered: good authorities as determined by employing Kleinberg's link analysis algorithm, and documents that have been automatically classified with high confidence, where  ... 
doi:10.1016/b978-012722442-8/50116-6 dblp:conf/vldb/SizovGT03 fatcat:5etbiau55rf35isio6bcqilkm4

Quantitative and Qualitative Analysis of Time-Series Classification using Deep Learning

Saba Ale Ebrahim, Javad Poshtan, Seyedh Mahboobeh Jamali, Nader Ale Ebrahim
2020 IEEE Access  
Time-series classification is utilized in a variety of applications leading to the development of many data mining techniques for time-series analysis.  ...  The research field has been broken down into three main categories as different frameworks of deep neural networks, different applications in remote sensing and also in signal processing for time-series  ...  FIGURE 4 shows the network structure of 50 high frequency author's keywords and keywords index.  ... 
doi:10.1109/access.2020.2993538 fatcat:kztcdypcd5delp2svervrgnq2m

Quantitative and Qualitative Analysis of Time-Series Classification using Deep Learning

Saba Ale Ebrahim, Javad Poshtan, Seyedh Mahboobeh Jamali, Nader Ale Ebrahim
2020 figshare.com  
Time-series classification is utilized in a variety of applications leading to the development of many data mining techniques for time-series analysis.  ...  The research field has been broken down into three main categories as different frameworks of deep neural networks, different applications in remote sensing and also in signal processing for time-series  ...  FIGURE 4 shows the network structure of 50 high frequency author's keywords and keywords index.  ... 
doi:10.6084/m9.figshare.13337249.v1 fatcat:ptcvzi72bzdlxhvzofpn5pi3bu

A Review on Knowledge Discovery using Text Classification Techniques in Text Mining

Chauhan ShrihariR, Amish Desai
2015 International Journal of Computer Applications  
From reviews I propose method with the use best classification method to improve the performance of result and improve indexing. And show the comparison of different classification techniques.  ...  With rapid growing of information increasing trends in people to extract knowledge from large text document.  ...  A typical text categorization process consist of preprocessing, indexing, dimensions reductions and classification.  ... 
doi:10.5120/19542-0784 fatcat:xwgei3efuvbtzktmu45sdt73hy

Knowledge File System -- A Principled Approach to Personal Information Management

Kuiyu Chang, I. Wayan Tresna Perdana, Bramandia Ramadhana, Kailash Sethuraman, Truc Viet Le, Neha Chachra
2010 2010 IEEE International Conference on Data Mining Workshops  
Its primary functionality is to automatically organize files in a transparent and seamless manner so as to facilitate easy retrieval.  ...  Lastly, an embedded database is used to log all file access to support file-usage classification. virtual file system; search engine; personal information management; indexing; classification I.  ...  ACKNOWLEDGEMENTS This research was funded in part by NTU Startup Grant CE-SUG 11/03 and Singapore Ministry of Education's Academic Research Fund Tier 1 RG 30/09.  ... 
doi:10.1109/icdmw.2010.119 dblp:conf/icdm/ChangPRSLC10 fatcat:2o4vljiyrnds7bjjblh3jw5yvm

Page 35 of Library & Information Science Abstracts Vol. , Issue 2 [page]

1992 Library & Information Science Abstracts  
Discusses researches conducted in the People’s Republic of China on automatic indexing of documents written in Chinese language since 1980.  ...  Reviews the classification policies and practices in Finland. Several classification and indexing methods are used for information storage and retrieval, the most common being UDC.  ... 

Market Intelligence Portal: An entity-based system for managing market intelligence

Z. Su, J. Jiang, T. Liu, G T. Xie, Y. Pan
2004 IBM Systems Journal  
Because of the huge volume of this information and the high rate of its growth, there is a great demand from enterprises for automated MI management systems.  ...  In contrast with traditional knowledge portal methods, our work is based on entity-level computing technologies rather than document-level technologies.  ...  in documents, and our patented flat classification scheme to support high-efficiency personalized categorization.  ... 
doi:10.1147/sj.433.0534 fatcat:i2s52n6ffbch5f5qol326gktu4

Enterprise Search: Tough Stuff

Rajat Mukherjee, Jianchang Mao
2004 Queue  
Documents in multiple languages can reside in the same index, and techniques for automatic language detection can be used for language-based content routing and partitioning.  ...  XML is ubiquitous in content and applications.  ... 
doi:10.1145/988392.988406 fatcat:nn6ifjqepvep3ngpy4ig2cqyai
« Previous Showing results 1 — 15 out of 55,370 results