Evaluating Retraining Rules for Semi-Supervised Learning in Neural Network Based Cursive Word Recognition

Frinken, Volkmar; Bunke, Horst

doi:10.1109/icdar.2009.18

Cited by 24 publications

(8 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, the result shown that also when the cardinality of the new selected training set is negligible if compared to that of the initial training set, the feedback strategy is able to produce improvements. Future work will inspect deeply the possibility of evaluate the approaches on the task of semi-supervised learning as well as in unsupervised learning [24,25,26].…”

Section: Discussionmentioning

confidence: 99%

Learning Iterative Strategies in Multi-Expert Systems Using SVMs for Digit Recognition

Barbuzzi

Impedovo

Mangini

et al. 2013

Image Analysis and Processing – ICIAP 2013

View full text Add to dashboard Cite

Abstract. This paper presents three different learning iterative strategies, in a multi-expert system. In first strategy entire new dataset is used. In second strategy each single classifier selects new samples starting from those on which it performs a misclassification. Finally, the collective behavior of classifiers is studied to select the most profitable samples for knowledge base updating. The experimental results provide a comparison of three approaches under different operating conditions and feedback process. A classifier SVM and four different combination techniques were used by considering the CEDAR (handwritten digit) database. It is shown how results depend by the iterations on the feedback process, as well as by the specific combination decision schema and by data distribution.

show abstract

Section: Discussionmentioning

confidence: 99%

Learning Iterative Strategies in Multi-Expert Systems Using SVMs for Digit Recognition

Barbuzzi

Impedovo

Mangini

et al. 2013

Image Analysis and Processing – ICIAP 2013

View full text Add to dashboard Cite

show abstract

“…There are many applications in which user effort is limited or expensive. For instance, some applications need to build competent systems from scarce annotated data [9,11,21] in order to be used as soon as possible. Alternatively, in other applications complete annotation of documents is not required to convey the meaning, or to be used as source for other application, such as information retrieval [12].…”

Section: Computer Assisted Transcription Of Text Imagesmentioning

confidence: 99%

“…However, as there are unsupervised words, the system needs to select which words may be correct. So, we resort again to confidence measures to successfully adapt from high confidence unsupervised words by means of semisupervised learning [9].…”

Section: Semi-supervised Learningmentioning

confidence: 99%

Interactive handwriting recognition with limited user effort

Serrano

Giménez

Civera

et al. 2013

IJDAR

View full text Add to dashboard Cite

Transcription of handwritten text in (old) documents is an important, time-consuming task for digital libraries. Although post-editing automatic recognition of handwritten text is feasible, it is not clearly better than simply ignoring it and transcribing the document from scratch. A more effective approach is to follow an interactive approach in which both, the system is guided by the user, and the user is assisted by the system to complete the transcription task as efficiently as possible. Nevertheless, in some applications, the user effort available to transcribe documents is limited and fully supervision of the system output is not realistic. To circumvent these problems, we propose a novel interactive approach which efficiently employs user effort to transcribe a document by improving three different aspects. Firstly, the system employs a limited amount of effort to solely supervise recognised words that are likely to be incorrect. Thus, user effort is efficiently focused on the supervision of words for which the system is not confident enough. Secondly, it refines the initial transcription provided to the user by recomputing it constrained to user supervisions. In this way, incorrect words in unsupervised parts can be automatically amended without user supervision. Finally, it improves the underlying system models by retraining the system from partially supervised transcriptions. In order to prove these statements, empirical results are presented on two real databases showing that the proposed approach can notably reduce user effort in the transcription of handwritten text in (old) documents.

show abstract

“…This system is highly specialized after the adaptation and not suitable for general handwriting recognition, though. The task of unconstrained writer independent single word recognition was addressed in [6,7]. In this paper, we extend this approach by not restricting the focus on single, manually segmented words, but considering entire text lines.…”

Section: Introductionmentioning

confidence: 99%

Self-training for Handwritten Text Line Recognition

Frinken

Bunke

2010

Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications

Self Cite

View full text Add to dashboard Cite

Abstract. Off-line handwriting recognition deals with the task of automatically recognizing handwritten text from images, for example from scanned sheets of paper. Due to the tremendous variations of writing styles encountered between different individuals, this is a very challenging task. Traditionally, a recognition system is trained by using a large corpus of handwritten text that has to be transcribed manually. This, however, is a laborious and costly process. Recent developments have proposed semisupervised learning, which reduces the need for manually transcribed text by adding large amounts of handwritten text without transcription to the training set. The current paper is the first one, to the knowledge of the authors, where semi-supervised learning for unconstrained handwritten text line recognition is proposed. We demonstrate the applicability of selftraining, a form of semi-supervised learning, to neural network based handwriting recognition. Through a set of experiments we show that text without transcription can successfully be used to significantly increase the performance of a handwriting recognition system.

show abstract

Evaluating Retraining Rules for Semi-Supervised Learning in Neural Network Based Cursive Word Recognition

Abstract: Abstract

Cited by 24 publications

References 12 publications

Learning Iterative Strategies in Multi-Expert Systems Using SVMs for Digit Recognition

Learning Iterative Strategies in Multi-Expert Systems Using SVMs for Digit Recognition

Interactive handwriting recognition with limited user effort

Self-training for Handwritten Text Line Recognition

Contact Info

Product

Resources

About