Detection and Classification of Interesting Parts in Scanned Documents by Means of AdaBoost Classification and Low-Level Features Verification

Markiewicz, Andrzej; Forczmański, Paweł

doi:10.1007/978-3-319-23117-4_46

Cited by 2 publications

(2 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…That is why in the experiments we employed a substage of dimensionality reduction/feature selection, namely: principal component analysis (PCA) [50], linear discriminant analysis (LDA) [51], information gain (IG) [52] and least [53]. It is an improvement over a recent work [54].…”

Section: Dimensionality Reductionmentioning

confidence: 99%

Two-stage approach to extracting visual objects from paper documents

Forczmański

Markiewicz

2016

Machine Vision and Applications

Self Cite

View full text Add to dashboard Cite

In the paper we present an approach to the automatic detection and identification of important elements in paper documents. This includes stamps, logos, printed text blocks, signatures and tables. Presented approach consists of two stages. The first one includes object detection by means of AdaBoost cascade of weak classifiers and Haarlike features. Resulting image blocks are, at the second stage, subjected to verification based on selected features calculated from recently proposed low-level descriptors combined with certain classifiers representing current machinelearning approaches. The training phase, for both stages, uses bootstrapping, i.e., integrative process, aiming at increasing the accuracy. Experiments performed on large set of digitized paper documents showed that adopted strategy is useful and efficient.

show abstract

Section: Dimensionality Reductionmentioning

confidence: 99%

Two-stage approach to extracting visual objects from paper documents

Forczmański

Markiewicz

2016

Machine Vision and Applications

Self Cite

View full text Add to dashboard Cite

show abstract

“…The combination of multiple base classifiers has been an important issue in machine learning for about twenty years [8], [35]. The ensembles of classifiers (EoC) or multiple classifiers systems (MCSs) [5], [21], [11], [26], [34] are popular in supervised classification algorithms where single classifiers are often unstable (small changes in input data may result in creation of very different decision boundaries) or are often more accurate than any of the base classifiers.…”

Section: Introductionmentioning

confidence: 99%

Combination of Linear Classifiers Using Score Function – Analysis of Possible Combination Strategies

Trajdos

Burduk

2019

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

In this work, we addressed the issue of combining linear classifiers using their score functions. The value of the scoring function depends on the distance from the decision boundary. Two score functions have been tested and four different combination strategies were investigated. During the experimental study, the proposed approach was applied to the heterogeneous ensemble and it was compared to two reference methods -majority voting and model averaging respectively. The comparison was made in terms of seven different quality criteria. The result shows that combination strategies based on simple average, and trimmed average are the best combination strategies of the geometrical combination.

show abstract

Detection and Classification of Interesting Parts in Scanned Documents by Means of AdaBoost Classification and Low-Level Features Verification

Cited by 2 publications

References 28 publications

Two-stage approach to extracting visual objects from paper documents

Two-stage approach to extracting visual objects from paper documents

Combination of Linear Classifiers Using Score Function – Analysis of Possible Combination Strategies

Contact Info

Product

Resources

About