A fuzzy approach for word level script identification of text in low resolution display board images using wavelet features

Script identification is an appealing research interest in the field of document image analysis during the last few decades. The accurate recognition of the script is paramount to many post-processing steps such as automated document sorting, machine translation and searching of text written in a particular script in multilingual environment. For automatic processing of such documents through Optical Character Recognition (OCR) software, it is necessary to identify different script words of the documents before feeding them to the OCR of individual scripts. In this paper, a robust word-level handwritten script identification technique has been proposed using texture based features to identify the words written in any of the seven popular scripts namely, Bangla, Devanagari, Gurumukhi, Malayalam, Oriya, Telugu, and Roman. The texture based features comprise of a combination of Histograms of Oriented Gradients (HOG) and Moment invariants. The technique has been tested on 7000 handwritten text words in which each script contributes 1000 words. Based on the identification accuracies and statistical significance testing of seven well-known classifiers, Multi-Layer Perceptron (MLP) has been chosen as the final classifier which is then tested comprehensively using different folds and with different epoch sizes. The overall accuracy of the system is found to be 94.7% using 5-fold cross validation scheme, which is quite impressive considering the complexities and shape variations of the said scripts. This is an extended version of the paper described in (Singh et al., 2014).

Download Full-text

Wavelet Features for Texture Classification and Their Use in Script Identification

Advances in Pattern Recognition ◽

10.1142/9789812772381_0071 ◽

2006 ◽

Author(s):

P. S. Hiremath ◽

S. Shivashankar

Keyword(s):

Texture Classification ◽

Script Identification ◽

Wavelet Features

Download Full-text

A Robust Segmentation Technique for Line, Word and Character Extraction from Kannada Text in Low Resolution Display Board Images

International Journal of Image and Graphics ◽

10.1142/s021946781450003x ◽

2014 ◽

Vol 14 (01n02) ◽

pp. 1450003 ◽

Cited By ~ 2

Author(s):

S. A. Angadi ◽

M. M. Kodabagi

Keyword(s):

Extraction Process ◽

Word Segmentation ◽

Text Line ◽

Low Resolution ◽

Data Set ◽

Display Board ◽

Robust Segmentation ◽

Character Extraction ◽

Segmentation Accuracy ◽

Line Segmentation

Reliable extraction/segmentation of text lines, words and characters is one of the very important steps for development of automated systems for understanding the text in low resolution display board images. In this paper, a new approach for segmentation of text lines, words and characters from Kannada text in low resolution display board images is presented. The proposed method uses projection profile features and on pixel distribution statistics for segmentation of text lines. The method also detects text lines containing consonant modifiers and merges them with corresponding text lines, and efficiently separates overlapped text lines as well. The character extraction process computes character boundaries using vertical profile features for extracting character images from every text line. Further, the word segmentation process uses k-means clustering to group inter character gaps into character and word cluster spaces, which are used to compute thresholds for extracting words. The method also takes care of variations in character and word gaps. The proposed methodology is evaluated on a data set of 1008 low resolution images of display boards containing Kannada text captured from 2 mega pixel cameras on mobile phones at various sizes 240 × 320, 480 × 640 and 960 × 1280. The method achieves text line segmentation accuracy of 97.17%, word segmentation accuracy of 97.54% and character extraction accuracy of 99.09%. The proposed method is tolerant to font variability, spacing variations between characters and words, absence of free segmentation path due to consonant and vowel modifiers, noise and other degradations. The experimentation with images containing overlapped text lines has given promising results.

Download Full-text