Artificial neural networks for document analysis and recognition

Marinai, Simone; Gori, Marco; Soda, Giovanni

doi:10.1109/tpami.2005.4

Cited by 161 publications

(81 citation statements)

References 87 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…However, we have some problems concerning on the accuracy of the compensation of the position of the pen head. As future works, we would like to discuss the analysis of the structure of note based on the relations among character regions [7] and the recognition for hand-written characters [8]. University.…”

Section: Discussionmentioning

confidence: 99%

Digitization of Hand-Written Notes Using a Wearable Camera

Watanabe¹,

Ozeki²,

Kohama³

2015

IJIET

View full text Add to dashboard Cite

Abstract-In taking hand-written note, the taking process plays important roles for recalling related information in addition of notations (words and figures) in the note. In this paper, we focus on the process through taking hand-written note. First, introduce an image processing method for the deduction of the position of pen head by using a wearable type camera. Next, we propose a method for the transformation of the physical position of the pen head into the logical position based on behaviors by students. Here, the logical position denotes the line and character numbers in the hand-written note. Moreover, we detect the face movement by using the block-matching method.Index Terms-Image processing, hand-written note, noting process, wearable camera.

show abstract

Section: Discussionmentioning

confidence: 99%

Digitization of Hand-Written Notes Using a Wearable Camera

Watanabe¹,

Ozeki²,

Kohama³

2015

IJIET

View full text Add to dashboard Cite

show abstract

“…Statistical features such as: region size, its position, number of lines and words are mainly used as an input of neural network, [36]. A deep survey of neural network application in segment analysis and recognition can be found in [25].…”

Section: Segment Recognitionmentioning

confidence: 99%

Image-based logical document structure recognition

Kamola

Spytkowski

Paradowski

et al. 2014

Pattern Anal Applic

View full text Add to dashboard Cite

The paper presents a complete solution for recognition of textual and graphic structures in various types of documents acquired from the Internet. In the proposed approach, the document structure recognition problem is divided into sub-problems. The first one is localizing logical structure elements within the document. The second one is recognizing segmented logical structure elements. The input to the method is an image of document page, the output is the XML file containing all graphic and textual elements included in the document, preserving the reading order of document blocks. This file contains information about the identity and position of all logical elements in the document image. The paper describes all details of the proposed method and shows the results of the experiments validating its effectiveness. The results of the proposed method for paragraph structure recognition are comparable to the referenced methods which offer segmentation only.

show abstract

“…This method is more reliable than the projection methods, but the computation cost is also more expensive. Classifier-based methods [30,31] select segmentation points using classifiers trained by correct segmentation samples. The drawback of classifier-based method is that classifiers require enough training samples to obtain better segmentation results.…”

Section: Character Segmentationmentioning

confidence: 99%