7 Hits in 5.1 sec

Automatic Recognition of Offline Handwritten Urdu Digits In Unconstrained Environment Using Daubechies Wavelet Transforms

Imtiyaz Ahmed Ansari
2013 IOSR Journal of Engineering  
A lot of work has been done in recognition of characters and numerals of various languages like Devanagari, English, Chinese, and Arabic etc.  ...  The back propagation neural network has been used for classification. An average recognition accuracy of 92.07% has been achieved.  ...  Mohamed Abaynarh et al. had [8] presented unconstrained handwritten Amazighe character recognition based upon orthogonal moments and neural networks classifier.  ... 
doi:10.9790/3021-03925056 fatcat:m2e36sgxwnbrhmb3rsto72o26i

Comparative Analysis of Wavelet Transforms in the Recognition of Ancient Grantha Script

Jyothi R. L., Abdul Rahiman M.
2017 Journal of clean energy technologies  
Discrete meyer wavelet produces the highest recognition efficiency compared to other wavelet families. In this work, the Feed Forward Neural network is used for classification purpose.  ...  For the recognition of ancient Grantha script, a comparative analysis of various transforms like haar, biorthogonal, coiflet, daubechies, discrete meyer and symlet wavelet families are carried out.  ...  with a character image and multilayer neural network is trained with this multiresolution feature vector.  ... 
doi:10.7763/ijcte.2017.v9.1144 fatcat:vjhom7ph25do7fty7667x2ezvi

Pattern recognition with SVM and dual-tree complex wavelets

G.Y. Chen, W.F. Xie
2007 Image and Vision Computing  
We achieve the highest rates when we use the dual-tree complex wavelet features with the Gaussian radial basis function kernel and the wavelet kernel for recognizing similar handwritten numerals, and when  ...  The approximate shiftinvariant property of the dual-tree complex wavelet and its good directional selectivity in 2D make it a very appealing choice for pattern recognition.  ...  Acknowledgements The authors thank the anonymous reviewers whose constructive suggestions and corrections have improved the quality of the paper. This work was supported by a post-  ... 
doi:10.1016/j.imavis.2006.07.009 fatcat:su4inkup3jdjtcqp2zkv3mxdnu

An overview of character recognition focused on off-line handwriting

N. Arica, F.T. Yarman-Vural
2001 IEEE Transactions on Systems Man and Cybernetics Part C (Applications and Reviews)  
Then, the available CR techniques with their superiorities and weaknesses are reviewed. Finally, the current status of CR is discussed and directions for future research are suggested.  ...  This material serves as a guide and update for the readers, working in the Character Recognition area. First, an overview of CR systems and their evolution over time is presented.  ...  Kuzeyhan Ozdemir, who initiated the CR studies and contributed a lot to the progress of this paper, during his MS studies. Thanks are also to Mr.  ... 
doi:10.1109/5326.941845 fatcat:jb3bjig3p5abtmgjz3bowuhdfu

Experiments in the Contextual Recognition of Cursive Script

R.W. Ehrich, K.J. Koehler
1975 IEEE transactions on computers  
Eden: A System for automatic recognition of handwritten words, Proc.  ...  Buchstabenerkennung (intelligent character recognition), Mustererkennung (pattern recognition) und graphonomische Forschungen.  ...  Tang: Multiresolution recognition of unconstrained handwritten numerals with wavelet transform and multilayer cluster neural network.  ... 
doi:10.1109/t-c.1975.224184 fatcat:rpnqadygyjc2zge3bvd7fwifcy

On the performance of wavelets for handwritten numerals recognition

S.E.N. Correia, J.M. de Carvalho, R. Sabourin
Object recognition supported by user interaction for service robots  
This paper validates a recognition system using bidimensional wavelet transforms as feature extractor and investigates the relevance of each subband image in the recognition process.  ...  Numerals from the NIST database were used for evaluation of the systems tested.  ...  The classifier was a multilayer cluster neural network [10] trained with the backpropagation momentum algorithm.  ... 
doi:10.1109/icpr.2002.1047811 dblp:conf/icpr/CorreiaCS02 fatcat:p2ewumkwczaxtesxuio46dnvua

Extracting Textual Information from Images and Videos for Automatic Content-Based Annotation and Retrieval

Julinda Gllavata, Freisleben, Bernd (Prof.Dr.), Mathematik Und Informatik
In this context, the extraction of scene and artificial text from images and videos is an important research problem, with the aim of achieving automatic content-based retrieval and summarization of the  ...  The output of this step is a binary image where black text characters appear on a white background. - Character recognition performs optical character recognition (OCR) on the binarized image and converts  ...  Acknowledgements First of all, I would like to express my gratitude to my advisor Prof. Dr. Bernd Freisleben for his invaluable support, guidance and encouragement throughout this research project.  ... 
doi:10.17192/z2007.0107 fatcat:ukn24ynnanbmvbv3ouym6mnpca