Automated recognition and extraction of tabular fields for the indexing of census records

Clawson, Robert; Bauer, Kevin; Chidester, Glen; Pohontsch, Milan; Kennard, Douglas J.; Ryu, Jongha; Barrett, William A.

doi:10.1117/12.2004788

Cited by 8 publications

(8 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Document segmentation into logical snippets, such as text lines or table cells, is often used as a preprocessing step for text recognition systems [26]. For forms, which are defined by a rigid structure of fields, accurate segmentation can be acheived via alignment with a form template which encodes the relative spacing of the segmentation cuts for that form's particular structure or type [7,29]. Such form templates can even be created automatically by simultaneous registration of many forms of the same type [19].…”

Section: Introductionmentioning

confidence: 99%

CONFIRM – Clustering of noisy form images using robust matching

Tensmeyer

Martinez

2019

Pattern Recognition

View full text Add to dashboard Cite

Identifying the type of a scanned form greatly facilitates processing, including automated field segmentation and field recognition. Contrary to the majority of existing techniques, we focus on unsupervised type identification, where the set of form types are not known apriori, and on noisy collections that contain very similar document types. This work presents a novel algorithm: CONFIRM (Clustering Of Noisy Form Images using Robust Matching), which simultaneously discovers the types in a collection of forms and assigns each form to a type. CONFIRM matches type-set text and rule lines between forms to create domain specific features, which we show outperform Bag of Visual Word (BoVW) features employed by the current state-of-the-art. To scale to large document collections, we use a bootstrap approach to clustering, where only a small subset of the data is clustered directly, while the rest of the data is assigned to clusters in linear time. We show that CONFIRM reduces average cluster impurity by 44% compared to the state-of-the art on 5 collections of historical forms that contain significant noise. We also show competitive performance on the relatively clean NIST tax form collection.

show abstract

Section: Introductionmentioning

confidence: 99%

CONFIRM – Clustering of noisy form images using robust matching

Tensmeyer

Martinez

2019

Pattern Recognition

View full text Add to dashboard Cite

show abstract

“…Anything that can be done to reduce the size of n will reduce the compute time. Second, we have shown in previous work 10 that handwriting recognition accuracy drops significantly when comparing between different handwriting styles and out-ofvocabulary words. The main ramification of the decision to break the collection into groups is that learning in one group does not transfer to the next group.…”

Section: Precomputing Morphing Costsmentioning

confidence: 99%

“…10 Also, the Fourier-Mellin transform has been shown to be effective in determining the transform parameters to rectify a document image with strong delineated structure. 11 Consensus based techniques can help in discovering cell boundaries.…”

Section: Document Preprocessingmentioning

confidence: 99%

See 1 more Smart Citation

Intelligent indexing: a semi-automated, trainable system for field labeling

Clawson

Barrett

2015

SPIE Proceedings

Self Cite

View full text Add to dashboard Cite

We present Intelligent Indexing: a general, scalable, collaborative approach to indexing and transcription of non-machinereadable documents that exploits visual consensus and group labeling while harnessing human recognition and domain expertise. In our system, indexers work directly on the page, and with minimal context switching can navigate the page, enter labels, and interact with the recognition engine. Interaction with the recognition engine occurs through preview windows that allow the indexer to quickly verify and correct recommendations. This interaction is far superior to conventional, tedious, inefficient post-correction and editing. Intelligent Indexing is a trainable system that improves over time and can provide benefit even without prior knowledge. A user study was performed to compare Intelligent Indexing to a basic, manual indexing system. Volunteers report that using Intelligent Indexing is less mentally fatiguing and more enjoyable than the manual indexing system. Their results also show that it reduces significantly (30.2%) the time required to index census records, while maintaining comparable accuracy. (a video demonstration is available at

show abstract

“…Making use of the pre-printed table substrate, they use Hough transform to detect the horizontal and vertical rulings that constitute the tabular structure. Clawson et al present a projection-profile based method to detect and extract handwritten tabular fields from historical census forms [5]. We notice that these existing techniques are evaluated on datasets where rulings are usually salient and well displaced, meaning no other lines will distract table analysis.…”

Section: Introductionmentioning

confidence: 99%