Techniques for static handwriting trajectory recovery

Nguyen, Vu; Blumenstein, Michael

doi:10.1145/1815330.1815390

Cited by 39 publications

(24 citation statements)

References 76 publications

(86 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A recovery scheme of drawing order of handwritten letters after generating several paths and the best path is selected [23]. A survey to recover pen trajectories multiple approaches to recover drawing order as skeleton, contours, ambiguous zones detections and ambiguous zones analysis are discussed [17]. A study based on matching cost function that is the summation of positional distortions cost and directional difference cost between the template stroke and its matching path.…”

Section: Introductionmentioning

confidence: 99%

A combined static and dynamic feature extraction technique to recognize handwritten digits

Sharma

2015

Vietnam J Comput Sci

View full text Add to dashboard Cite

The recent advances in the feature extraction techniques in recognition of handwritten digits attract researchers to work in this area. The present study includes recognition of handwritten digits using hybrid feature extraction technique including static and dynamic properties of handwritten digit images. In this paper, static properties include number of non-zero (white) pixels in square, horizontal, vertical and diagonal styles as sub regions of a binary image. The dynamic properties include features from recovery of drawing order of original image. The extraction of dynamic features include two stages: first stage recover the drawing order of an image and second stage compute the chain code directions from recovered drawing order. The algorithm for recovery of drawing order uses properties of writing behavior. The support vector machine has been used as recognition method for the proposed feature extraction scheme. We have achieved an overall error rate of 0.73 % for mnist data set including 60,000 training images and 10,000 test images. Our feature extraction technique results in feature vector length of an image equals to 356. The achieved results strengthen our proposed technique usability as error rate achieved is at par with literature (<1 %) and the length of feature vector per image is small in comparison to input feature vector length of 784 which has been commonly used in previous work. The developed system is stable and useful in real life applications.

show abstract

Section: Introductionmentioning

confidence: 99%

A combined static and dynamic feature extraction technique to recognize handwritten digits

Sharma

2015

Vietnam J Comput Sci

View full text Add to dashboard Cite

show abstract

“…Nguyen and Blumenstein 20) summarized recently developed techniques for temporal order recovery from static handwriting. Inspired by motor control theory, Plamondon and Privitera 21) recovered the temporal features from stroke geometries such as curvature.…”

Section: Automated Veriˆcation Methodsmentioning

confidence: 99%

Offline writer verification based on forensic expertise: Analyzing multiple characters by combining the shape and advanced pen pressure information

Okawa

Yoshida

2017

Jpn. J. Forensic. Sci. Tech.

View full text Add to dashboard Cite

OOEine writer veriˆcation is an important security measure and is related to human traits. However, even with modern techniques, maximizing the amount of information from the limited number of available samples remains a challenging task. We propose a new oOEine writer veriˆcation system inspired by the expertise of forensic document examiners. The system combines the shape and pen pressure information in multiple characters captured by a multiband image scanner. From the visible images, the shape information is extracted as a weighted direction code histogram, and the local pen pressure information (which is based on ink intensity) is extracted as local directional pattern features with adaptive zoning. From the infrared images, the global pen pressure information (which is based on the writing indentations) is extracted asˆrst-and second-order texture statistics. In an experimental comparison study at less than 0.1 error rate, the proposed system reduced the number of required Japanese Kanji characters from six (in the conventional system) to three. After combining these techniques, the error rate per character (averaged from 54 volunteers) was reduced from 4.8 in the conventional method to 1.3.

show abstract

“…This makes thinning results of offline handwriting character become far different from human handwriting. In the comprehensive survey [5], the general idea of trajectory recovery problem always includes the ambiguous zone detection step which deal with distortion around the junction points of the original character. In order to solve this problem, most of the approaches [6]- [8], start at correct junction point from skeleton character.…”

Section: Introductionmentioning

confidence: 99%