Topic
Handwriting recognition
About: Handwriting recognition is a research topic. Over the lifetime, 5154 publications have been published within this topic receiving 148736 citations. The topic is also known as: symbol recognition & reading handwritten characters.
Papers published on a yearly basis
Papers
More filters
••
08 Feb 2015TL;DR: An improved HMM formulation for offline handwriting recognition (HWR) using modified quadratic discriminant function (MQDF) within HMM framework and encouraging results on offline handwritten character and word recognition in English using MQDF HMMs are got.
Abstract: We propose an improved HMM formulation for offline handwriting recognition (HWR). The main contribution of this
work is using modified quadratic discriminant function (MQDF) [1] within HMM framework. In an MQDF-HMM the
state observation likelihood is calculated by a weighted combination of MQDF likelihoods of individual Gaussians of
GMM (Gaussian Mixture Model). The quadratic discriminant function (QDF) of a multivariate Gaussian can be rewritten
by avoiding the inverse of covariance matrix by using the Eigen values and Eigen vectors of it. The MQDF is
derived from QDF by substituting few of badly estimated lower-most Eigen values by an appropriate constant. The
estimation errors of non-dominant Eigen vectors and Eigen values of covariance matrix for which the training data is
insufficient can be controlled by this approach. MQDF has been successfully shown to improve the character recognition
performance [1]. The usage of MQDF in HMM improves the computation, storage and modeling power of HMM when
there is limited training data. We have got encouraging results on offline handwritten character (NIST database) and
word recognition in English using MQDF HMMs.
••
12 Jul 2009TL;DR: A novel approach to recognize similar handwritten numerals based on empirical mode decomposition (EMD) by using the local maximum modulus of wavelet transform to get width-invariant and grey-level invariant characterization of contours in an image.
Abstract: This paper presents a novel approach to recognize similar handwritten numerals based on empirical mode decomposition (EMD). We firstly use the local maximum modulus of wavelet transform (MMWT) to get the width-invariant and grey-level invariant characterization of contours in an image. Then we apply EMD analysis to decompose the synthetic shift normalization of curvature into their components, which could produce more compact features. Finally, three different classifiers, i.e. support vector machine (SVM), hidden Markov model (HMM), and artificial neural network (ANN), are used to discriminate similar handwritten numerals for testing the effectiveness of the extracted features. Experimental results show that the proposed approach obtains higher recognition rates compared with the traditional algorithm for extracting features.
•
22 Feb 2019
TL;DR: In this article, a bank electronic signature recognition system based on touch display technology, which comprises a financial terminal, a financial transaction module, a device structure arranged in the financial terminal and used for realizing the financial transaction function, and a handwriting input control module is used for converting the handwriting of the user into the data acceptable to the system.
Abstract: The invention provides a bank electronic signature recognition system based on touch display technology, which comprises a financial terminal, a financial transaction module, a device structure arranged in the financial terminal and used for realizing the financial transaction function, and a bank electronic signature recognition system based on touch display technology. The handwriting input structure is used for displaying the signature or handwriting inputted by the user by using the capacitive touch component and the electromagnetic touch component, and includes a handwriting input controlmodule for converting the handwriting of the user into the data acceptable to the system, and the handwriting input control module is used for converting the handwriting of the user into the data acceptable to the system. The handwriting recognition financial terminal authority management module is a module structure for receiving the handwriting recognition result generated by the financial system to determine the authority of the user to enter the financial transaction module, and is used for providing a technology that enables the user to realize the identity confirmation operation in thefinancial transaction through the touch control technology handwriting input.
•
11 Feb 2021TL;DR: In this paper, an electronic device for processing a handwriting input and including a touch screen, a processor operatively connected with the touch screen and a memory associated with the processor, where the memory stores instructions, which when executed, cause the processor to control the electronic device to perform handwriting recognition for a first handwriting input of a user displayed on the touch-screen.
Abstract: Disclosed is an electronic device for processing a handwriting input and including a touch screen, a processor operatively connected with the touch screen, and a memory operatively connected with the processor, wherein the memory stores instructions, which when executed, cause the processor to control the electronic device to perform handwriting recognition for a first handwriting input of a user displayed on the touch screen, to convert the first handwriting input into a text, identify at least one of an attribute or characteristic of the first handwriting input, apply at least one of the identified attribute or characteristic to the converted text, and in response to a request for conversion of the first handwriting input, replace the first handwriting input into a text (herein after, a first rich text) to which the identified at least one of the attribute or characteristic has been applied.
01 Jan 2011
TL;DR: Considering digital ink traces as plane curves provides a useful framework for handwriting recognition, and a single, coherent view leads to highly ecient methods with a high recognition rate.
Abstract: Considering digital ink traces as plane curves provides a useful framework for handwriting recognition. Characters may be represented as parametric curves approximated by certain truncated orthogonal series, mapping symbols to the lowdimensional vector space of series coecients. Many useful properties are obtained in this representation, allowing fast recognition based on small training sets. The beauty of this framework is that a single, coherent view leads to highly ecient methods with a high recognition rate. Furthermore, these truncated orthogonal series are subject to all the geometric techniques of symbolic-numeric polynomial algorithms.