Skew Detection of Devanagari Script Using Pixels

reorientededed Detection of Devanagari deal Using Pixels reorienteded Detection of Devanagari Script Using Pixels of Axes-Parallel Rectangle and Linear retroflectionTrupti A. JundaleRavindra S. HegadiAbstractskew contracting and study of hand indite selective information is one of the difficult tasks in pattern recognition atomic number 18a. Here we illustrate the rule for reoriented spotting and castigation of Devanagari written script. The proposed approach exits for single reorient. The enter images for this investigate be collected from various writers and contain single/ coherent skew interchanges/ parameter of productss. The proposed approach uses tangential pixels of axes parallel rectangle and elongated fixing method acting to calculate the skew of sacred scripture/ groove. Finally whirling trans beation is use for chastisement of skew of word/ confines which is figure by bi reportar regression. This technique achieves 89% accuracy to correct s kew of word and achieves 93% accuracy to correct skew of form for handwritten Devanagari script.Index legal injuryPreprocessing, Axes-parallel rectangle, Linear Regression, skew espial, Skew subject areaI. IntroductionThe frequency of digital schoolbook file extends to develop at a brisk rate in spite of the usage of paper based inventorys. As a consequence, the regaining of paper muniments to its electronic version and its consequent image processing and reason have been converted into a vital application area in computer slew and pattern recognition researches. With recent emergence and far-flung application of multimedia technologies, there is an increasing demand to create a paperless environment, hence, memorandum image processing in general and Optical computer address Recognition (OCR) in particular is playing an important role in transformation of the traditional paper based environment to truly paperless electronic environment3.Devanagari is one of the import antly employ and espouses writing system in the world. The theme/ authorized language of India (Hindi) and Nepal (Nepali) uses Devanagari Script. Many other languages like Marathi (state language of Maharashtra), Sanskrit, Kashmiri, Bhojpuri, Maithili, Bodo, Dogri etcetera comes under Devanagari Script. As Indias national language uses Devanagari script, lot of official data is in written format before the era of digitization. So in the todays world of digitization, it is needed to keep bear witness of handwritten/printed data in digital form. To pull in this, Optical use Recognition (OCR) system is carried out. The perception and correction of skew is one of the inwrought steps in any character recognition or document processing system. Because of the writing genre of the Devanagari script, it is difficult to detect skew as compared to any other script. The writing style of every person whitethorn vary so there is presence of multiple skew in data. Skew is the angle which d iverges from x-axis. The successful skew maculation and correction turns close process like analysis of character or OCR to be accurate. The document may contain three type of skew single/uniform skew, multiple skew and non-uniform skew. Single/uniform skew is, when all text pull backs in a document have same orientation. Multiple skew is, when some text lines have diametrical orientation than other and non-uniform skew is, when orientation changes within a line. There is lot of research unattached for skew detection of s female genitalsned document image but less work is available for skew detection of text/word.II. Devanagari scriptOne of the main parts of Brahmic family is a Devanagari Script, which is belonging from Indo-Aryan languages. It is written from left to right. contradictory Latin script, concept of upper/lower case is absent in Devanagari script. It consists of 33 consonants and 14 vowels. Generally every word written in most of the Devanagari Script pull up st akes have a header line on group of characters, called as Shirorekha and this is considered as one word 7. Vowels that can be written as separate characters or by exploitation diacritic marks on below, upper, before or after consonants are called modifiers. In Devanagari script, two or three consonants can be written as a single character, which is known as compound character. Fig.1 shows different features of Devanagari script.Fig. 1. Devanagari Script WordThe main characters of word are written in middle zone. Upper zone and lower zone are for modifiers and Shirorekha is careworn at header line. In Fig.1 two characters are combined to form a new shape of single character known as compound character.III. Related WorkIn the literature, algorithmic rules that estimate the angle at which a text/document image is turf outd are surveyed. The openhanded descriptores of technique are identified, which include methods that calculate skew from Hough transform, horizontal prominence p rofile, Fourier transform, nearest-neighbour or principal component analysis. The basic method used by each class of technique is presented and the contributions of individual algorithms within each class are discussed.Hough Transform One of the best feature inception technique used in digital image processing and computer vision is Hough Transform. It is mainly used for detection of regular curves such as lines, ellipses, circles etc. The simplest case of Hough transform is the linear transform for detecting bully lines. The line in the image space is just a single register in the parameter space. 1 uses Hough transform method for detection of document skew. A novel skew correction algorithm is proposed focusing on leap line that optimizes speed and accuracy by using Hough transform to gear up the skew corrected licences plate images in 2.Fourier Transform In this method first 2-D Fourier transform impart be applied to the image plane. Then, coefficients of the originator sp ectrum are calculated and stored in a spectrum. A orderional banner for each angle is then calculated. The angle that maximizes the directional criterion is anticipate to give the skew angle of the image.Projection indite Projection Profile can be a horizontal project profile or vertical bulge profile. The horizontal/vertical projection profile is a histogram of the number of black pixels along horizontal/vertical scan lines. In projection profiles, histogram is created at each possible angle and a embody function is applied to this histogram. The skew angle is the angle at which this equal function is maximized. Mostly horizontal projection profile method is used for scanned document skew detection. 6 exploits the unique property of the writing line of Arabic script and is based on connected component analysis and projection profiles. Skew detection of fabric images scheme based on geomorphologic method and projection profile analysis is proposed in 8.Nearest inhabit In Ne arest Neighbour method histogram of the direction angle is computed. 5 uses a Focused Nearest Neighbour Clustering (FNNC) of interest points and the analysis of paragraphs/lines. bondage with a largest possible number of nearest neighbour pairs are selected and their tilts are computed to give the skew angle of document image.Other than these techniques, one-step skew and orientation detection method using a well-established geometric text-line case is used in 11. The advantage of this method is that it combines accurate skew theme with robust, resolution-independent orientation detection. 12 proposed a Rectangular Active Contour Model (RAC Model) for bailiwick region detection and skew angle calculation by high-minded a rectangular shape constraint on the nil-level set in Chain-Vese Model (C-V Model) according to the rectangular feature of content regions in document images. B. V. Dhandra et.al, 13 uses image distension and region labelling approach for double star document skew detection. Apart from this, fast and robust skew estimation techniques like a bilinear filtering model which is used to detect edges existing in the document, roll (Centre of Gravity) method are used in the literature.IV. Proposed MethodologyThis section illustrates the proposed methodological analysis for skew detection and correction. Section A describes pre-processing step. Section B describes extraction of axes parallel rectangle pixels. Skew detection using linear regression is expound in C. Section D describes skew correction technique and coating section E describes steps of proposed algorithm.A. Pre-processingThe input to the system is a word or a line of single/uniform skew of handwritten Devanagari script which is scanned by optical scanner or captured by digital camera. Acquired input is pre-processed for removing noise. Firstly input image is converted into gray outgo image and then thresholding is applied over for converting given image into binary program im age containing only black and white pixels. In this binarized image, white pixels diddle background and black pixels represent foreground.B. Axes-Parallel RectangleThis stage calculates the area of axes-parallel rectangle. The angle with the to the lowest degree area of the axes-parallel rectangle represents the skew angle. Outer tangential pixels of an input word/line are used to form an axes-parallel rectangle. Figure 2 shows tangential pixels of skewed one are embedded into an axes-parallel rectangle.Fig. 2 (a) Skewed rectangle suitted in an Axes-parallel rectangle (b) Rectangle with zero skew.C. Skew DetectionAfter inviteting required pixels using axes-parallel rectangle, linear regression formula is used to detect skew of word/line. Regression analysis can be used to identify the line or curve which provides the best fit through a set of data points. Linear regression analyzes the relation between two variables, X and Y. The variables X and Y are known and the problem is t o fit best straight line through X and Y. In general, the goal of linear regression is to harness the line that best predicts Y from X. Linear regression does this by finding the line that minimizes the sum of the squares of the vertical distances of the points from line. Linear regression does non test whether the data are linear. It assumes that the data is linear, and finds the tip and tease that make a straight line best fit the given data. The goal of linear regression is to adjust the values of heel over and intercept to find the line that best predicts Y from X.Fig. 3 (a) Plot of data without best-fit line (b) Plot of data with best-fit line.This is the simple linear regression model where 0 and 1 are unknown constants and is the residual error. To fit the regression line in the comparison of the data (x1, y1), (x2, y2),..,(xn, yn) by finding best rival between the line and the data. The best choice of 0+1 will be chosen to minimize,This is called the least square fi t. The equation (2) implies After detailed algebra, getwhere and (4) compare (3) gives slope of the regression line and comparability (4) gives the intercept. The slope of the line is nothing but the skew angle of our word/line. Fig.4 shows the slope and intercept of a best fit line.Fig. 4 Slope and intercept of a best fit lineAfter calculating slope using linear regression, skew is calculated using the formula,This gives the required skew of word.D. Skew CorrectionAfter the skew angle of the word/line has been detected, the word/line must be rotated in order to correct this skew. Various methods used for skew correction are direct method, indirect method and contour-oriented method etc. The direct method uses rotation transformation in which corresponding pixels in the input image will be transformed to new location by using equation (1) (5)Where (x, y) are the co-ordinates of pixels belonging to the word for which skew has to be detected and (x, y) are the co-ordinates of pix els belonging to the word after correction. For a pixel (x, y) in the output image, the indirect method finds corresponding pixel in the input image and assigns a value of (x, y) to (x, y) using Equation (2). (6)We apply direct method for skew correction which simply rotate calculated skew angle to horizontal angle. The detected angle by linear regression is corrected by applying rotation transformation. The word/line is rotated with angle. The word/line is corrected by rotating at substantiating angle if the skew detection angle is negative and corrected by rotating at negative angle if skew detection angle is positive.E. algorithmic ruleStep 1 Accept the input image which may be word or line.Step 2 Convert the given input into binary by using thresholding method.Step 3 Calculate the axes-parallel rectangle of binary image by finding minimum row and minimum tower pixels.Step 4 Apply linear regression, Equation (3), to detect the skew of axes-parallel rectangle, which is the skew of original word/line.Step 5 Using Equation (6), correct the skew angle of word/line.V. Experimental ResultWe tried and true our algorithm for input images of handwritten document for Hindi and Marathi languages. The algorithm is tried on 500 words and ccc lines of Devanagari script. The accuracy rate for skew correction of word is 89% and accuracy rate for uniform skew correction of line is 93%.Mostly the word with single character or small size length does not give accurate result because of the lack of a sufficient number of minima points. Table I shows the ideal results of words with skew detection of positive and negative angle and skew correction of all these.Results of word skewFigure 5 shows skew detection and correction of uniform skew line. We tested our algorithm for document with single/uniform skew and for skewed printed document also. For these kinds of input images, algorithm runs successfully.VI. ConclusionWe have proposed a methodology for skew detection and cor rection of word and line of handwritten Devanagari script. The slope of best line fit using linear regression algorithm is used for skew detection and it is corrected by simply rotating word/line by calculated angle. This method is tested on handwritten data of Hindi and Marathi language. The word dataset is collected from various writers for testing purpose which contains 500 words and 300 lines. The proposed approach can be modified for future work to get higher accuracy and for detection of documents contain multiple or non-uniform skew text.Fig. 5 (a) Skewed line (b) Axes-parallel rectangle of skewed line (c) Skew correction of lineVII. ReferencesDeepak Kumar, Dalwinder Singh, Modified approach of Hough transform for skew detection and correction in documented images, multinational diary of Research in data processor Science, Vol. 2, Issue 3, pp. 37-40, April 2012.Arulmozhi K., Perumal S. A., Priyadarshini C.S.T., Nallaperumal K., Image refinement using skew angle detection a nd correction for Indian licences plates, Computational Intelligence Computing Research (ICCIC), IEEE, pp. 1-4, Dec. 2012.B.V.Dhandra, H.Mallikarjun, Ravindra Hegadi, V.S.Malemath, Word-wise Script Identification from Bilingual Documents Based on Morphological Reconstruction, optical Information Engineering, IEEE, pp 389-395, 2006.Kleber, Florian, Markus Diem, Robert Sablatnig, Robust Skew Estimation of Handwritten and Printed Documents Based on Grayvalue Images, International collection on Pattern Recognition (ICPR), pp. 3020 3025, Aug. 2014.Ahmad Irfan, A technique for Skew Detection of Printed Arabic Documents, Computer Graphics, Imaging and Visualization (CGIV), IEEE, pp. 62-67, Aug. 2013.Trupti A. Jundale, Ravindra S. Hegadi, Skew Detection and Correction of Devanagari Script Using Hough Transform, International Conference on Advanced Computing Technologies and Applications, Procedia of Computer Science, Journal of Elsevier, March2015, in press.Liu, Zhoufeng, Jie Huang, Chu nlei Li, Skew detection of fabric images based on edge detection and projection profile analysis, Foundations of Intelligent Systems, Springer Berlin Heidelberg, Vol. 122, pp 483-488, 2012.H. K. Kwag, S. H. Kim, S. H. Jeony and G. S. Lee, Efficient skew estimation and correction algorithm for document images, Image and vision Computing, Vol. 20, pp. 25-35, Jan. 2002.van Beusekom, Joost, Faisal Shafait, and Thomas M. Breuel, unite orientation and skew detection using geometric text-line modeling, International Journal on Document Analysis and Recognition (IJDAR), Vol. 13, Issue 2, pp 79-92, June 2010.Fan, Huijie, Linlin Zhu, and Yandong Tang, Skew detection in document images based on rectangular active contour, International Journal on Document Analysis and Recognition (IJDAR), Vol. 13.4, pp 261-269, Dec. 2010.B. V. Dhandra, V. S. Malemath, H. Mallikarjun and R. Hegadi, Skew detection in binary image documents based on image dilation and region labelling approach International Confe rence on Pattern Recognition, IEEE, Vol. 2. pp 954-957, 2006.