Empirical performance evaluation of graphics recognition systems

Phillips, Ihsin T.; Chhabra, Atul K.

doi:10.1109/34.790427

Cited by 144 publications

(79 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…(7)) following the steps of Ref. [24] and correspond to the number of one-to-one, g_one-to-many, g_many-to-one, d_one-to-many, and d_many-to-one, respectively. A global performance metric for text line detection can be defined if we combine the values of detection rate and recognition accuracy.…”

Section: Performance Evaluation Methodologymentioning

confidence: 99%

Text line detection in handwritten documents

Louloudis

Gatos

Pratikakis

et al. 2008

Pattern Recognition

110

View full text Add to dashboard Cite

Section: Performance Evaluation Methodologymentioning

confidence: 99%

Text line detection in handwritten documents

Louloudis

Gatos

Pratikakis

et al. 2008

Pattern Recognition

110

View full text Add to dashboard Cite

“…A successful system must both determine the type of each entity present and recover a sufficiently accurate spatial description, ensuring that each reported entity is correctly located, both in absolute coordinates and in relation to neighbouring entities. These two issues of classification and spatial coherence are, for example, both explicitly addressed by current [8] performance evaluation schemes. Initial examination of the KADS/CommonKADS model library suggests that, given these goals, models describing classification and configuration tasks are the most relevant.…”

Section: Models Of Expertise: Classification Vs Configurationmentioning

confidence: 99%

Interpreting Line Drawing Images: A Knowledge Level Perspective

Pridmore

Darwish

Elliman

2002

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Image understanding systems rely heavily on a priori knowledge of their application domain, often exploiting techniques developed in the wider field of knowledge-based systems (KBSs). Despite attempts, typified by the KADS/CommonKADS projects, to develop structured knowledge engineering approaches to KBS development, those working in image understanding continue to employ unstructured 1 st generation KBS methods. We analyse some existing image understanding systems, concerned with the interpretation of images of line drawings, from a knowledge engineering perspective. Attention focuses on the relationship between the structure of the systems considered and the KADS/CommonKADS models of expertise, sometimes called generic task models. Mappings are identified between each system and an appropriate task model, identifying common inference structures and use of knowledge. This is the first step in the acquisition of models of the expertise underpinning drawing interpretation. Such models would bring significant benefits to the design, maintenance and understanding of line drawing interpretation systems.

show abstract

“…Images of the paper ballot grabbed using ultraviolet light of neuronal nets like it is shown for instance in [7]. Structural methods have been also proposed like in [8] [9]. Finally, several authors proposed methods that combine different techniques [10].…”

Section: Optical Character Recognition Algorithmmentioning

confidence: 99%

An Electronic Secure Voting System Based on Automatic Paper Ballot Reading

Goirizelaia

Espinosa

Martín

et al. 2004

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract.A secret and secure ballot is the core of every democracy. We all feel proud of being able to decide the future of our countries by making appropriate use of our right to vote in an election. However, how can we improve the efficiency of the voting process? Democratic governments should have mechanisms which ensure the integrity, security and privacy of its citizens at the polls during an election process. This paper describes a new electronic secure voting system, based on automatic paper ballot reading, which can be utilized to offer efficient help to officials and party representatives during elections. It presents how the system is organized, it also describes our OCR system and how it is implemented to read paper ballots, and it ends showing some experimental results.

show abstract

Empirical performance evaluation of graphics recognition systems

Cited by 144 publications

References 13 publications

Text line detection in handwritten documents

Text line detection in handwritten documents

Interpreting Line Drawing Images: A Knowledge Level Perspective

An Electronic Secure Voting System Based on Automatic Paper Ballot Reading

Contact Info

Product

Resources

About