An ensemble of neural networks for nonlinear segmentation of overlapped cursive script

Abstract

Precise character segmentation is the only solution towards higher Optical Character Recognition (OCR) accuracy. In cursive script, overlapped characters are serious issue in the process of character segmentations as characters are deprived from their discriminative parts using conventional linear segmentation strategy. Hence, non-linear segmentation is an utmost need to avoid loss of characters parts and to enhance character/script recognition accuracy. This paper presents an improved approach for non-linear segmentation of the overlapped characters in handwritten roman script. The proposed technique is composed of a sequence of heuristic rules based on geometrical features of characters to locate possible non-linear character boundaries in a cursive script word. However, to enhance efficiency, heuristic approach is integrated with trained ensemble neural network validation strategy for verification of character boundaries. Accordingly, correct boundaries are retained and incorrect are removed based on ensemble neural networks vote. Finally, based on verified valid segmentation points, characters are segmented non-linearly. For fair comparison CEDAR benchmark database is experimented. The experimental results are much better than conventional linear character segmentation techniques reported in the state of art. Ensemble neural network play vital role to enhance character segmentation accuracy as compared to individual neural networks.

Image Annotation With YCbCr Color Features Based on Multiple Deep CNN- GLP

“…By assigning distinct weights to individual features, CNNs effectively streamline the overall complexity of the network. Due to their distinctive attributes, CNNs have garnered significant acclaim in the domain of pattern recognition [20].…”

“…Based on the terminology described above, the following procedure can be described Figure 6 shows a multi-scale Gaussian-Laplacian pyramid derived from intermediate results of different pyramid levels. The sampling value for the pyramid in our test was 3 [20]. Figure 6 schematically presents the Gaussian-Laplacian image decomposition scheme.…”

An Efficient Skewed Line Segmentation Technique for Cursive Script OCR

“…In [22], the author presents a set of rules that are derived heuristically to search character boundaries of the cursive script that is validated by using an ensemble of neural confidence. Rehman [23] introduced a new concept of corezone for segmenting such difficult slanted handwritten words.…”

Marker Identification of Disc Workpiece Based on HOG-SVM Classifier

“…For the nonlinear segmentation of Roman handwritten characters, the suspected character boundary of cursive script was searched by heuristic derivation, and the effective boundary was screened out by an integrated neural network. e topdown handwritten text line segmentation method was used to realize the character segmentation of nonspaced handwritten documents through a detailed enlargment [17,18]. To deal with the segmentation of embossed characters in low-quality images with the uneven brightness, the iterative closed-loop feedback segmentation method based on segmentation effect evaluation function was viable [19].…”