Document Image Skew Detection: Survey and Annotated Bibliography

Hull, Jonathan J.

doi:10.1142/9789812797704_0003

Cited by 88 publications

(52 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…However, most of conventional methods focused on machine-printed [8,22] and/or clean (noise-free) documents [2, 9, 14-17, 28, 31-34], so they cannot be directly applied to historical documents. In historical document processing, binarization is a challenging task due to degradations (e.g., bleed-through and faint characters) and structure noises.…”

Section: Textline Detection In Historical Documentsmentioning

confidence: 99%

Textline detection in degraded historical document images

Ahn

Ryu

Koo

et al. 2017

J Image Video Proc.

View full text Add to dashboard Cite

This paper presents a textline detection method for degraded historical documents. Our method follows a conventional two-step procedure that the binarization is first performed and then the textlines are extracted from the binary image. In order to address the challenges in historical documents such as document degradation, structure noise, and skews, we develop new methods for the binarization and textline extraction. First, we improve the performance of binarization by detecting the non-text regions and processing only text regions. We also improve the textline detection method by extracting main textblock and compensating the skew angle and writing style. Experimental results show that the proposed method yields the state-of-the-art performance for several datasets.

show abstract

Section: Textline Detection In Historical Documentsmentioning

confidence: 99%

Textline detection in degraded historical document images

Ahn

Ryu

Koo

et al. 2017

J Image Video Proc.

View full text Add to dashboard Cite

show abstract

“…The skew, i.e. the inclination of the document, is removed by a hierarchical rotation of the complete document image such that the horizontal projection profile is step-wise maximised [21]. Note that the skew angle is estimated on complete document images first and then corrected on single word images.…”

Section: Image Preprocessingmentioning

confidence: 99%

Graph-Based Keyword Spotting in Historical Handwritten Documents

Stauffer

Fischer

Riesen

2016

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. The amount of handwritten documents that is digitally available is rapidly increasing. However, we observe a certain lack of accessibility to these documents especially with respect to searching and browsing. This paper aims at closing this gap by means of a novel method for keyword spotting in ancient handwritten documents. The proposed system relies on a keypoint-based graph representation for individual words. Keypoints are characteristic points in a word image that are represented by nodes, while edges are employed to represent strokes between two keypoints. The basic task of keyword spotting is then conducted by a recent approximation algorithm for graph edit distance. The novel framework for graph-based keyword spotting is tested on the George Washington dataset on which a state-of-the-art reference system is clearly outperformed.

show abstract

“…The Most Forward with fixed Radius (MFR) algorithm is widely used for next hop selection in geographic forwarding schemes [11]. In MFR, the current relay node always selects the neighbor closest to the destination as the next relay.…”

Section: Problem Definitionmentioning

confidence: 99%

Sink Trail Protocol Extention with Dead End Free Topology Used in WSN

2015

IJSR

View full text Add to dashboard Cite

Wireless sensor network (WSN) uses a sensor node to observer and stored environmental physical condition and organised the data at central location. There are to much divercity in the movement of mobile sinks due to continueous changes in the terrestrial, without using GPS devices or predefined landmark. SinkTrail sends data packets by making a logical coordinate system using routing and forwardings, so that it can be used in wrost application scenario. A local maximum problem that is dead end while routing or forwarding data packetsis the primary drawback of sinktrail .In order to overcome from this primary drawback we extend sinkTrail with a Dead End Free Topology (DEFT) in our proposed system. Such system can have the capability and efficiency to deal with the dead end occurred in the sink trail protocol. This type of system also provide facility for do not occurred dead end situation and also find shortest routing path using dead end free topology.

show abstract

Document Image Skew Detection: Survey and Annotated Bibliography

Cited by 88 publications

References 21 publications

Textline detection in degraded historical document images

Textline detection in degraded historical document images

Graph-Based Keyword Spotting in Historical Handwritten Documents

Sink Trail Protocol Extention with Dead End Free Topology Used in WSN

Contact Info

Product

Resources

About