Complex Document Classification and Integration with Indexing

Bhagat, Riya; Thosani, Parth; Shah, Nisarg; Shankarmani, Radha

doi:10.1109/icesc51422.2021.9532737

Cited by 2 publications

(2 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Complex documents contain a mix of text, images, labels, tables, and various elements, which present a formidable challenge in document classification. These documents can include memos, newspapers, letters, and more, and effectively categorizing them is critical for the rapid digitization of diverse content [4]. The difficulty arises from the fact that these scanned images look very similar as they share standard page colors, text characteristics, and paper textures.…”

Section: Introductionmentioning

confidence: 99%

VisFormers—Combining Vision and Transformers for Enhanced Complex Document Classification

Dutta,

Adhikary,

Dwivedi

2024

MAKE

View full text Add to dashboard Cite

Complex documents have text, figures, tables, and other elements. The classification of scanned copies of different categories of complex documents like memos, newspapers, letters, and more is essential for rapid digitization. However, this task is very challenging as most scanned complex documents look similar. This is because all documents have similar colors of the page and letters, similar textures for all papers, and very few contrasting features. Several attempts have been made in the state of the art to classify complex documents; however, only a few of these works have addressed the classification of complex documents with similar features, and among these, the performances could be more satisfactory. To overcome this, this paper presents a method to use an optical character reader to extract the texts. It proposes a multi-headed model to combine vision-based transfer learning and natural-language-based Transformers within the same network for simultaneous training for different inputs and optimizers in specific parts of the network. A subset of the Ryers Vision Lab Complex Document Information Processing dataset containing 16 different document classes was used to evaluate the performances. The proposed multi-headed VisFormers network classified the documents with up to 94.2% accuracy, while a regular natural-language-processing-based Transformer network achieved 83%, and vision-based VGG19 transfer learning could achieve only up to 90% accuracy. The model deployment can help sort the scanned copies of various documents into different categories.

show abstract

Section: Introductionmentioning

confidence: 99%

VisFormers—Combining Vision and Transformers for Enhanced Complex Document Classification

Dutta,

Adhikary,

Dwivedi

2024

MAKE

View full text Add to dashboard Cite

show abstract

“…Several research [10]- [15] have been conducted about content-based image document search using OCR technology but they are only limited to searching base content for scanned documents without focusing on classified documents for a more specific search. Meanwhile, the increasing number and diversity of documents are making the classification process important to direct, summarize, and organize the documents easily, with efficient and cost-effective solutions [16]. Document classification is defined as the automatic grouping of documents into certain criteria based on similar content such as the subject, topic, language, field, and several others [17].…”

Section: Introductionmentioning

confidence: 99%

Advanced content-based retrieval for digital correspondence documents with ontology classification

et al. 2022

View full text Add to dashboard Cite

The growth of digital correspondence documents with various types, different naming rules, and no sufficient search system complicates the search process with certain content, especially if there are unclassified documents, the search becomes inaccurate and takes a long time. This research proposed archiving method with automatic hierarchical classification and the content-based search method which displays ontology classification information as the solution to the content-based search problems. The method consists of preprocessing (creation of automatic hierarchical classification model using a combination of convolutional neural network (CNN) and regular expression method), archiving (document archiving with automatic classification), and retrieval (content-based search by displaying ontology relationships from the document classification). The archiving of 100 documents using the automatic hierarchical classification was found to be 79% accurate as indicated by the 99% accuracy for CNN and 80% for Regex. Moreover, the search results for classified content-based documents through the display of ontology relationships were discovered to be 100% accurate. This research succeeded in improving the quality of search results for digital correspondence documents as indicated by its higher specificity, accuracy, and speed compared to conventional methods based on file names, annotations, and unclassified content.

show abstract

Complex Document Classification and Integration with Indexing

Cited by 2 publications

References 11 publications

VisFormers—Combining Vision and Transformers for Enhanced Complex Document Classification

VisFormers—Combining Vision and Transformers for Enhanced Complex Document Classification

Advanced content-based retrieval for digital correspondence documents with ontology classification

Contact Info

Product

Resources

About