Proceedings Eighth International Workshop on Frontiers in Handwriting Recognition
Cơ quản chủ quản: N/A
Các bài báo tiêu biểu
Vind(x): using the user through cooperative annotation
- Trang 221-226
In this paper, the image retrieval system Vind(x) is described. The architecture
of the system and first user-experiences are reported. Using Vind(x), users on
the Internet may cooperatively annotate objects in paintings by use of the pen
or mouse. The collected data can be searched through query-by-drawing
techniques, but can also serve as an (ever-growing) training and benchmark set
for the deve...
#Information retrieval #Image retrieval #Internet #Pattern recognition #Humans #Painting #Image databases #Cultural differences #Cognitive science #Mice
Nhận diện chữ Hiragana viết tay sử dụng máy vector hỗ trợ Dịch bởi AI
- Trang 55-60
Bài báo mô tả một phương pháp nhằm cải thiện tỷ lệ nhận diện tích lũy của việc
nhận diện mẫu sử dụng đồ thị không tuần hoàn định hướng quyết định (DDAG) dựa
trên máy vector hỗ trợ (SVM). Mặc dù DDAG ban đầu có hiệu suất cao và tốc độ
thực thi nhanh, nhưng nó không xem xét tỷ lệ nhận diện tích lũy. Chúng tôi xây
dựng một DDAG có thể kết hợp tỷ lệ nhận diện tích lũy. Kết quả thí nghiệm của
chúng tôi...
#Support vector machines #Support vector machine classification #Character recognition #Pattern recognition #Character generation #Kernel #Voting #Quadratic programming #Lagrangian functions #Conferences
Dynamic observations and dynamic state termination for off-line handwritten word recognition using HMM
- Trang 314-319
HMM has been successfully used to model 1D data, e.g. voice signals. Their use
to model 2D patterns was not as successful due to a major difficulty, in
describing the 2D data using 1D observation sequences. In this paper, we discuss
the importance of this issue and present an improved method to extract 1D
observations from the dynamics of off-line handwritten words. The method is
based on pen traj...
#Handwriting recognition #Hidden Markov models #Data mining #Speech recognition #Signal mapping #Laboratories #Electronic mail #Signal analysis #Focusing #Conferences
The effect of large training set sizes on online Japanese Kanji and English cursive recognizers
- Trang 36-40
Much research in handwriting recognition has focused on how to improve
recognizers with constrained training set sizes. This paper presents the results
of training a nearest-neighbor based online Japanese Kanji recognizer and a
neural-network based online cursive English recognizer on a wide range of
training set sizes, including sizes not generally available. The experiments
demonstrate that incr...
#Handwriting recognition #Character recognition #Prototypes #Training data #Writing #Neural networks #Ink #Sparse matrices #Frequency #Delay effects
Handwritten text recognition through writer adaptation
- Trang 363-368
Handwritten text recognition is a problem rarely studied out of specific
applications for which lexical knowledge can constrain the vocabulary to a
limited one. In the case of handwritten text recognition, additional information
can be exploited to characterize the specificity of the writing. This knowledge
can help the recognition system to find coherent solutions from both the lexical
and the mo...
#Text recognition #Handwriting recognition #Writing #Hidden Markov models #Character recognition #Vocabulary #Shape #Image analysis #Pattern recognition #Semisupervised learning
Minimum classification error training for online handwritten word recognition
- Trang 61-66
We describe an application of the minimum classification error (MCE) training
criterion to online unconstrained-style word recognition. The described system
uses allograph-HMMs to handle writer variability. The result, on vocabularies of
5k to 10k, shows that MCE training achieves around 17% word error rate reduction
when compared to the baseline maximum likelihood system.
#Handwriting recognition #Hidden Markov models #Error analysis #Writing #Vocabulary #Personal digital assistants #Handheld computers #Shape #Signal processing #Speech recognition
An overview and comparison of voting methods for pattern recognition
- Trang 195-200
In pattern recognition, there is a growing use of multiple classifier
combinations with the goal to increase recognition performance. In many cases,
plurality voting is a part of the combination process. In this article, we
discuss and test several well known voting methods from politics and economics
on classifier combination in order to see if an alternative to the simple
plurality vote exists. ...
#Voting #Pattern recognition #Helium #Testing #Nominations and elections #Enterprise resource planning #Artificial intelligence #Conferences #Handwriting recognition #Humans
Automating performance optimization for script word recognition systems
- Trang 139-144
In this paper we present a system for automating parameter optimization of
pattern recognition systems and demonstrate its capabilities on script word
recognition systems. This system, called Optima (optimization manager) has been
specially developed to fit the requirements of optimization in the pattern
recognition field, where computation- and engineering-costs for system
evaluation are very hig...
#Optimization #System performance #Pattern recognition #Industrial training #Handwriting recognition #Automatic control #Control systems #Engineering management #Cost function #Writing
Nghiên cứu về việc sử dụng CDHMM cho nhận dạng chữ Hán viết tay với từ vựng lớn Dịch bởi AI
- Trang 334-338
Chúng tôi (2002) đã nghiên cứu cách sử dụng mô hình Markov ẩn liên tục với hỗn
hợp Gaussian (CDHMM) để mô hình hóa và nhận diện chữ Hán viết tay. Chúng tôi đã
xác định và phát triển một tập hợp các kỹ thuật có thể được sử dụng để xây dựng
một hệ thống nhận diện ngoài dây dựa trên CDHMM thực tiễn cho một từ vựng lớn
của các ký tự chữ Hán viết tay. Chúng tôi đã báo cáo ở nơi khác về các kỹ thuật
chí...
#Vocabulary #Handwriting recognition #Hidden Markov models #Character recognition #Automatic speech recognition #Power system modeling #Information science #Computer science #Information systems #Context modeling
An online signature verification system using hidden Markov model in polar space
- Trang 329-333
In this paper, we propose a method of online signature verification system using
HMM models in a polar coordinate system. In the previous works, the signature
verification was performed in terms of a standard X-Y coordinate system. This
coordinate system always needs the normalization of signature stroke size and
angle variance. To reduce normalization error and computing time, we propose the
pola...
#Handwriting recognition #Hidden Markov models #Writing #Pattern recognition #Space technology #Testing #Speech recognition #Databases #Sampling methods #Software