Continuous HMM applied to quantization of on-line Korean character spaces

Jung, Keechul; Yoon, S.M.; Kim, H. J.

doi:10.1016/s0167-8655(99)00160-9

Cited by 13 publications

(4 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Codebook generated using k means clustering algorithm with 128 clusters, this number is the dominated in many researches [8,9].…”

Section: Vector Quantizationmentioning

confidence: 99%

Holistic Approach for Arabic Word Recognition

Wahbi¹,

Musa²

2016

IJCATR

View full text Add to dashboard Cite

Abstract. Optical Character Recognition (OCR) is one of the important branches. One segmenting words into character is one of the most challenging steps on OCR. As the results of advances in machine speeds and memory sizes as well as the availability of large training dataset, researchers currently study Holistic Approach "recognition of a word without segmentation". This paper describes a method to recognize off-line handwritten Arabic names. The classification approach is based on Hidden Markov models.. For each Arabic word many HMM models with different number of states have been trained. The experiments result are encouraging, it also show that best number of state for each word need careful selection and considerations.

show abstract

“…Codebook generated using k means clustering algorithm with 128 clusters, this number is the dominated in many researches [8,9].…”

Section: Vector Quantizationmentioning

confidence: 99%

Holistic Approach for Arabic Word Recognition

Wahbi¹,

Musa²

2016

IJCATR

View full text Add to dashboard Cite

show abstract

“…Since the user action distribution during the training period is known and the states are hidden, we can use a generative model (Jung et al, 2000) to decode the state sequence given the observed actions and thereby obtain optimal estimates of the emission probabilities b u . Note, using a straight-forward Hidden Markov Model in this case to determine the emission probabilities of actions is not suitable because the state transition probabilities are affected by the user context.…”

Section: Estimating User Actionsmentioning

confidence: 99%

Analyzing the Dynamics of Communication in Online Social Networks

Sundaram

Choudhury

2010

Handbook of Social Network Technologies and Applications

View full text Add to dashboard Cite

The outcomes of this research are manifold. I present the contributions in three parts, corresponding to the three key organizing ideas. First, it is observed that user context is key to characterizing communication between a pair of individuals. However interestingly, the probability of future communication seems to be i more sensitive to the context compared to the delay, which appears to be rather habitual. Further, it is observed that diffusion of social actions in a network can be indicative of future information cascades; that might be attributed to social influence or homophily depending on the nature of the social action. Second, it is also observed that different modes of social engagement lead to evolution of groups that have considerable predictive capability in characterizing external-world temporal occurrences, such as stock market dynamics as well as collective political sentiments. Sihem Amer-Yahia and Dr. Doree Duncan Seligmann during these three internships.The research I accomplished during these internships, enabled with the wonderful computing infrastructure and the rich availability of data, will remain very central to my academic accomplishment during the graduate school years. Additionally, encouraging discussions, fruitful guidance and generous help from Winter, Jake, Cong, Ronny, Ajita and Michael also helped me gather enthusiasm, have fun and remain on top of exciting research problems.

show abstract

“…Online handwritten character recognition of any scripting language is a difficult task due to the problems of different handwriting styles of different individuals, complex structure of a language and different touch-based handwriting capturing devices used by the individuals. A good amount of research work has been carried out on online handwriting recognition in the recent past for different scripts such as Chinese, Japanese, Korean and Arabic [1][2][3][4]. On the other hand, works on isolated character recognition for many Indic languages like Bangla, Hindi, Tamil and Telugu have been reported by many researchers in the past few years [5][6][7][8].…”

Section: Introductionmentioning

confidence: 99%

Recognition of online unconstrained handwritten Gurmukhi characters based on Finite State Automata

2018

View full text Add to dashboard Cite

This paper presents a language-based efficient post-processing algorithm for the recognition of online unconstrained handwritten Gurmukhi characters. A total of 93 stroke classes have been identified to recognize the Gurmukhi character set in this work. Support Vector Machine (SVM) classifier has been employed for stroke classification. The main objective of this paper is to improve the character level recognition accuracy using an efficient Finite State Automata (FSA)-based formation of Gurmukhi characters algorithm. A database of 21,945 online handwritten Gurmukhi words is primarily collected in this experiment. After analysing the collected database, we have observed that a character can be written using one or more strokes. Therefore, a total of 65,946 strokes have been annotated using the 93 identified stroke classes. Among these strokes, 15,069 stroke samples are considered for training the classifier. The proposed system achieved promising recognition accuracy of 97.3% for Gurmukhi characters, when tested with a new database of 8,200 characters, written by 20 different writers.

show abstract

Continuous HMM applied to quantization of on-line Korean character spaces

Cited by 13 publications

References 7 publications

Holistic Approach for Arabic Word Recognition

Holistic Approach for Arabic Word Recognition

Analyzing the Dynamics of Communication in Online Social Networks

Recognition of online unconstrained handwritten Gurmukhi characters based on Finite State Automata

Contact Info

Product

Resources

About