Journal ArticleDOI
Collection of on-line handwritten Japanese character pattern databases and their analyses
Masaki Nakagawa,Kaoru Matsumoto +1 more
Reads0
Chats0
TLDR
The design of on-line handwritten Japanese character pattern databases, software tools for pattern collection and verification, and analyses of collected patterns reveal greater variations in stroke count for characters having many strokes, with people generally using fewer strokes.Abstract:
We describe the design of on-line handwritten Japanese character pattern databases, software tools for pattern collection and verification, and analyses of collected patterns. Two databases containing over 3 million patterns were compiled: one with 120 people contributing 12,000 patterns each and another with 163 participants contributing 10,000 patterns each. Patterns were collected mostly in their sentential contexts and verified by machine and human inspection. Their analyses reveal greater variations in stroke count for characters having many strokes, with people generally using fewer strokes; they additionally reveal that stroke order variations are generally caused by common habits and added strokes.read more
Citations
More filters
Journal ArticleDOI
Iconic and multi-stroke gesture recognition
TL;DR: A large number of features known from the literature are explored for the recognition of multi-stroke gestures, and it is shown that using these new stroke-based features, significant improvements in classification accuracy can be obtained.
Proceedings ArticleDOI
Ground truth creation for handwriting recognition in historical documents
TL;DR: With a small set of algorithmic tools and few manual interactions, it is shown how laypersons can efficiently create a ground truth for handwriting recognition.
Journal ArticleDOI
A robust model for on-line handwritten japanese text recognition
TL;DR: A robust context integration model for on-line handwritten Japanese text recognition based on string class probability approximation that can flexibly combine the scores of various contexts and is insensitive to the variability in path length is described.
Journal ArticleDOI
A Model of On-line Handwritten Japanese Text Recognition Free from Line Direction and Writing Format Constraints
TL;DR: A model and its effect for on-line handwritten Japanese text recognition free from line-direction constraint and writing format constraint such as character writing boxes or ruled lines is presented.
Journal ArticleDOI
Personal digital bodyguards for e-security, e-learning and e-health: A prospective survey
TL;DR: A prospective survey of various projects dealing with five e-fields of investigation, focussing on state of the art results and providing directions in research and development, under the theoretical umbrella of the Kinematic Theory of human movements and its Lognormality Principle.
References
More filters
Journal ArticleDOI
A database for handwritten text recognition research
TL;DR: An image database for handwritten text recognition research is described that contains digital images of approximately 5000 city names, 5000 state names, 10000 ZIP Codes, and 50000 alphanumeric characters to overcome the limitations of earlier databases.
Journal ArticleDOI
The state of the art in online handwriting recognition
TL;DR: The state of the art of online handwriting recognition during a period of renewed activity in the field is described, based on an extensive review of the literature, including journal articles, conference proceedings, and patents.
Proceedings ArticleDOI
UNIPEN project of on-line data exchange and recognizer benchmarks
TL;DR: The status of the UNIPEN project of data exchange and recognizer benchmarks started two years ago is reported, to propose and implement solutions to the growing need of handwriting samples for online handwriting recognizers used by pen-based computers.
Proceedings ArticleDOI
The IRESTE On/Off (IRONOFF) dual handwriting database
TL;DR: This work has developed a dual on/off database, named IRONOFF, that contains a large number of isolated characters, digits, and cursive words written by French writers and has been designed so that, given an online point, it can be mapped at the correct location in the corresponding scanned image, and conversely, each offline pixel can be temporally indexed.
Journal ArticleDOI
Handwritten character classification using nearest neighbor in large databases
TL;DR: It is shown that systems built on a simple statistical technique and a large training database can be automatically optimized to produce classification accuracies of 99% in the domain of handwritten digits.