Using HMMs to boost accuracy in optical character recognition
نویسنده
چکیده
One of the current trends in the eld of optical character recognition (OCR) is the combination of multiple classi ers to produce more robust recognition. In this paper, a kNN classi er, a multi-layer perceptron, and a support vector machine with a radial basis function kernel are tested on a pre-segmented word-based OCR task with and without Viterbi errorcorrection. I discuss the effects of error-correction on the classi cation accuracy of each method.
منابع مشابه
Modeling of Pen-Coordinate Information in SCPR-based HMM for On-line Recognition of Handwritten Japanese Characters
This paper describes stochastic modeling of pencoordinate information in HMMs with structured character pattern representation (SCPR) for on-line recognition of handwritten Japanese characters. SCPR allows HMMs for Kanji character patterns to share common subpatterns. Although SCPR-based HMMs have been successfully applied to Kanji character recognition, the pen-coordinate feature has not been ...
متن کاملA Hybrid NN/HMM Modeling Technique for Online Arabic Handwriting Recognition
In this work we propose a hybrid NN/HMM model for online Arabic handwriting recognition. The proposed system is based on Hidden Markov Models (HMMs) and Multi Layer Perceptron Neural Networks (MLPNNs). The input signal is segmented to continuous strokes called segments based on the Beta-Elliptical strategy by inspecting the extremum points of the curvilinear velocity profile. A neural network t...
متن کاملOptical Character Recognition using Hidden Markov Models
OCR has many useful applications and has attracted a great deal of research over the past years. It has been used in vehicle license plate recognition, information retrieval, document digitization, and in text-to-speech applications. In this work, Hidden Markov Models are used to perform OCR. HMM classifiers have been extensively used in continuous speech recognition (CSR) for many years. The s...
متن کاملOptical Character Recognition using Hidden Markov Models
OCR has many useful applications and has attracted a great deal of research over the past years. It has been used in vehicle license plate recognition, information retrieval, document digitization, and in text-to-speech applications. In this work, Hidden Markov Models are used to perform OCR. HMM classifiers have been extensively used in continuous speech recognition (CSR) for many years. The s...
متن کاملA Robust Method for Recognizing Accents in Vietnamese Handwriting Characters
Handwriting character recognition is one of the most common research topics. Many approaches have applied to English characters and achieve high accuracy. However, the complexities in the language of each country are not same. Vietnamese handwriting character recognition is facing many problems, most of them come from the accent. This paper focuses on accent recognition, especially when there i...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2006