An Efficient Feature Vector for Segmentation-Free Recognition of Online Cursive Handwriting Based on a Hybrid Deep Neural Network.
Partha Sarathi MukherjeeUjjwal BhattacharyaSwapan Kumar ParuiPublished in: DAS (2018)
Keyphrases
- cursive handwriting
- feature vectors
- neural network
- feature extraction
- online learning
- color and texture information
- pattern recognition
- segmentation algorithm
- multiscale
- numeral strings
- image parsing
- handwritten words
- object recognition
- segmentation method
- level set
- symbol recognition
- automatic recognition
- medical images
- information extraction
- euclidean distance
- image features
- hybrid intelligent
- image segmentation
- background subtraction
- document analysis
- handwriting recognition
- recognition rate
- support vector machine
- correct recognition
- feature space
- feature vectors are extracted
- back propagation
- recognition process
- recognition algorithm
- multilayer perceptron
- binary images
- energy function
- feature set
- artificial neural networks
- similarity measure
- feature selection
- information retrieval