Old Handwritten Musical Symbol Classification by a Dynamic Time Warping Based Method
نویسندگان
چکیده
A growing interest in the document analysis field is the recognition of old handwritten documents, towards the conversion into a readable format. The difficulties when working with old documents are increased, and other techniques are required for recognizing handwritten graphical symbols that are drawn in such these documents. In this paper we present a Dynamic Time Warping based method that outperforms the classical descriptors, being also invariant to scale, rotation, and elastic deformations typical found in handwriting musical notation.
منابع مشابه
A Template-based Recognition System for On-line Handwritten Characters
New developments on our real-time recognition engine for isolated handwritten characters are presented. This engine is based on approximate Dynamic Time Warping comparisons with prototypes selected by fast, less accurate classification procedures. The error rate it currently obtains on the standard Pendigits task, 0.60%, is significantly lower than both the error rate of other recently publishe...
متن کاملRecognition Of Multivariate Temporal Musical Gestures Using N-Dimensional Dynamic Time Warping
This paper presents a novel algorithm that has been specifically designed for the recognition of multivariate temporal musical gestures. The algorithm is based on Dynamic Time Warping and has been extended to classify any N dimensional signal, automatically compute a classification threshold to reject any data that is not a valid gesture and be quickly trained with a low number of training exam...
متن کاملUsing Dynamic Time Warping for Persian Handwriting Recognition
This paper discusses the use of fast and customized Dynamic Time Warping method for offline Persian handwriting recognition that could be easily extended to Arabic language. Many systems in this field are based on either Neural Network or Hidden Markov Model that suffer from low recognition rate, sensitivity to noises or wide range of parameters that reduce system performance. The complete syst...
متن کاملExperiments with a Self-supervised Adaptive Classification Strategy in On-line Recognition of Isolated Handwritten Latin Characters
Results on a comparison of recognition techniques for on-line recognition of handwritten Latin alphabets are presented. The emphasis is on an adaptive classii-cation strategy introduced in this paper. The classiication strategy is based on compressing or distilling a large database of handwritten characters to a small set of character prototypes. The distillation is performed as a clustering pr...
متن کاملReal Scene Graphics Symbol Recognition
A common problem encountered in recognizing symbols in real-scene images is the perspective deformation. A character recognition method resistant to perspective deformation has been proposed in [4]. Particularly, a symbol is represented by a sequence of cross ratio spectra, in which 3D perspective deformation is modeled as a 1D uneven stretching. Dynamic Time Warping algorithm is employed to co...
متن کامل