International Journal of Scientific & Engineering Research, Volume 5, Issue 1, January-2014 89

ISSN 2229-5518

Using Feature Extraction to Recognize

Handwritten Text Image

Khamael A. Khudhair*, Itimad Raheem Ali**

* Al-Nahrain University /College of Science / Computer Department ,Al-jaderyia –Iraq

** AL-Rafidean College / Computer Department Khamail_abbas@yahoo.com weffee@yahoo.com

Abstract— In this paper, a robust technique for identifying and recognizing Handwritten Text images is presented. There are many methods for Handwritten Text, but most of them require segmentation or connected component analysis. The Recognition process utilizes the determinant value that produces the features for the Handwritten Text. Image’s determinants values are computed by dividing image into blocks then designed Threshold (T) to extract feature, afterwards, use chain code to find the centric point and direction of text. The least square criterion is then utilized to determine the similarity between the existed (in Database file) Handwritten Text with a new query Handwritten Text’s images.

Index Terms— Handwritten Text, Feature Extract, Determinant value, chain coding

1 INTRODUCTION

——————————  ——————————

IJSER

ext in handwritten images typically shows strong variabil- ity in appearance due to different writing styles. Appear- ance differs in the size of the words, slant, skew and
stroke thickness. Such variability calls for the development of normalization and pre-processing techniques suitable for recognition of handwritten text. Among the most common preprocessing steps applied in current state-of-the art systems are noise removals, binarization, skew and slant correction, thinning, and baseline normalization [3]. For slant correction, Pastor et al. [17] proposed to use the maximum variance of the pixels in the vertical projection and Vinciarelli etal. [21], ob- served that non-slanted words show long, continuous strokes. Juan et al. [20] showed that normalizing ascenders and des- canters of the text significantly reduce the vertical variability of handwritten images. A linear scaling method applied to whole images has been used in various systems to reduce the overall size variability of images of handwritten text [6, 3, 8]. A drawback of all those approaches is that, they rely on as- sumptions that may or may not be based upon for a given da- tabase. A second drawback is that all those methods are ap- plied to whole images making it difficult to address local changes. Furthermore, the methods for slant correction rely on binarization which, is a non-trivial problem in itself and should be avoided if possible, as Liu et al. [13] found in their benchmark paper. Recently, Espapna-Boquera etal., [7] pro- posed using trained Multi- Layer-Perceptrons for image clean- ing and normalization. While they report competitive results on standard databases, the training and labeling process is time consuming. In contrast to the methods mentioned until now, methods based on image statistics and moments do not suffer from heuristically assumptions and have been exten- sively studied in the area of isolated digit recognition. Casey [4] proposed that all linear pattern variations can be normal-
ized using second-order moments. Liu et al. [14] used Bi- moment normalization based on quadratic curve fitting and introduced a method to put constrain on the aspect ratio when the x and y axis are normalized independently [12]. Miyoshi et al. [16] reported that computing the moments from the con- tour of a pattern, and not from the pattern itself, improves the overall recognition results. They do not appear at the same relative location of the letter due to the different proportions in which characters are written by different writers of the lan- guage. Even the same person may not always write the same letter with the same proportions.

2-RELATED WORK AND CONTRIBUTION

1.1 Related Work

High accuracy character recognition techniques can provide useful information for segmentation-based handwritten word recognition systems. The research describes neural network- based techniques for segmented character recognition that may be applied to the segmentation and recognition compo- nents of an off-line handwritten word recognition system. Two neural architectures along with two different feature ex- traction Techniques were investigated. A novel technique for character feature extraction is discussed and compared with others in the literature. Recognition results above 80% are re- ported usingcharacters automatically segmented from the CEDAR benchmark database, as well as standard CEDAR al- phanumeric [17].
Text Extraction plays a major role in finding vital and valu- able information. Text extraction involves detection, localiza- tion, tracking, binarization, extraction, enhancement and recognition of the text from the given image. These text char- acters are difficult to be detected and recognized due to their

International Journal of Scientific & Engineering Research, Volume 5, Issue 1, January-2014 90

ISSN 2229-5518

deviation of size, font, style, orientation, alignment, contrast, complex colored, textured background. Due to the rapid growth of available multimedia documents and growing re- quirement for information, identification, indexing and re- trieval, many researches have been done on text extraction in images. Several techniques have been developed for extracting the text from an image. The proposed methods were based on morphological operators, wavelet transform, artificial neural network, skeletonization operation, edge detection algorithm, histogram technique etc. All these techniques have their bene- fits and restrictions. This article discusses various schemes proposed earlier for extracting the text from an image. This paper also provides the performance comparison of several existing methods proposed by researchers in extracting the text from an image [20].

2.2 Contribution

In this paper, a new method proposed to recognize a text based on features in this framework, consists of a formal mod- el definition and three stages algorithm for recognition. Pre- processing image then Modified the classical way of Determi- nant value (that is requisite input whole the Handwritten text into determinant computation), so that the created recognition system becomes feasible (fast and accurate) for recognizing a query text from a huge dataset also, propose a suitable similar- ity measure incorporating the quantitative meaningful fea- tures (Det value) with the qualitative features to get a potential recognition decision.
.

3. THE RECOGNITION METHODOLOGY

3.1 Pre-processing

The pre-processing is a series of operations performed on the scanned input image. It essentially enhances the image; rendering it suitable for segmentation. The various tasks per- formed on the image in pre-processing stage are shown in Fig.1, Extract features. Binarization process converts a gray scale image into a binary image using global thresholding technique, dilating the image and filling the holes present in it are the operations performed in the last two stages to produce the pre-processed image suitable for Recognition [16].

————————————————

• Khamael Abbas is currently Lecturer in computer science in AL- nahrainUniversity, Iraq, E-mail: khamail_abbas@yahoo.com

• Itimad Raheem is currently pursuing phd degree program computer sci-

ence inUTM University, Malayazia, E-mail:weffee@yahoo.com
Fig.1 Image pre-processing Stage

3.2 Image Acquisition

In Image acquisition, the recognition system acquires a scanned image as an input image. The image should have a specific format such as JPEG, BMP etc., as shown in Fig-2. This image is acquired through a scanner, digital camera or any other suitable digital input device.

International Journal of Scientific & Engineering Research, Volume 5, Issue 1, January-2014 91

ISSN 2229-5518

Fig-2 Scanned image of Handwritten Text

3.3 Enhancement Image

The median filter is normally used to remove the noise produced in an image; it often does a better job than the mean filter of preserving useful detail in the image. Like the mean filter, the median filter considers each pixel in the image in turn and looks at its nearby neighbors to decide whether or not it is representative of its surroundings. Instead of simply replacing the pixel value with the mean of neighboring pixel values, it replaces it with the median of those values. The me- dian is calculated by first sorting all the pixel values from the surrounding neighborhood into numerical order and then
replacing the pixel being considered with the middle pixel

3.4 Divided Image to Blocks

256x256 pixel image is divided into blocks of typically
3x3 pixels. For each block the Determinant values are calculat- ed, these values change from block to block shown Fig-5.

Fig-5 Divided Image to Blocks size (3×3)

3.5 Theory to Extract Feature using Determinant Value

The term determinant of a square matrix A, denoted det(A) or │A│, refers to both the collection of the elements of the square matrix, enclosed in vertical lines, and the scalar value represented by that array. Thus,

det(A) =│A│ = a11 a12 ………..a1n

IJSER

value divided by 2. (If the neighborhood under consideration
contains an even number of pixels, the average of the two
middle pixel values divided by 2 is used.) Fig-3 illustrates an
example of this calculation.

Fig-3 An example of the Calculation of Median Filter for
Enhancement Image

Fig-4 Enhancement Image using Median Filter
a21 a22 ………..a2n .…………. (Eq.1)
an1 an2 ………. ann
Only square matrices have determinants. The scalar value of the determinant of a 2 × 2 matrix is the product of the ele- ments on the major diagonal minus the product of the ele- ments on the minor diagonal. Thus
det(A) =│A│ a11 a12
a21 a22
= a 11 a22 - a12 a21 ………………(Eq.2)
The scalar value of the determinant f a 3 × 3 matrix is com-
posed; f the sum f six triple products which can be obtained
from the augmented determinant [6]:

a11 a12 a13 a11 a12
det(A) =│A│ = a21 a22 a23 a21 a22
a31 a32 a33 a31 a32 ..…….… (Eq.3)
The 3 × 3 determinant is augmented by repeating the first two columns, f the determinant on the right-hand side of the determinant. Three triple products are formed, starting with the elements of the first row multiplied by the two remaining elements on the downward-sloping diagonals. Three more triple products are formed, starting with the elements of the third row multiplied by the two remaining elements on the right-upward sloping diagonals. The value of the determinant is the sum of the first three triple products minus the sum of the last three triple products. Thus [6],

International Journal of Scientific & Engineering Research, Volume 5, Issue 1, January-2014 92

ISSN 2229-5518

det(A)= │A│ = a11a22 a33 + a12 a23 a31 + a 13a21a32 -- a31a22a13-a32a23all -a33a21a12 ……….……… (Eq.4)
Threshold (T) was practically designed to check the value of image
If im(I,j) > T im(I,j) Else im(I,j) =0
a b c d
Fig.7 chain code algorithm and path type terminated path,
forked path, circular path
Then, the coordinates of all collected pixels are normal- ized to be invariant to translation and scaling. Eq. (5 - 7) were used for mapping x and y coordinates to their corresponding normalized values.

Fig.6 Extract Features using Determinate value for each

xn =

x − xmin

………… (Eq.5)
block

y − y

IJSER

3-6 Determine Centric Point using Chain Code

Algorithm

An algorithm was developed to create the chain code for

max{

min

, y

….……… (Eq.6)

y }

D =

any thinned Features. Chain code representation of object con-

xmaax − xmin

−

max

min

….……… (Eq.7)
tours is extensively used in document analysis and recogni-
tion. It has proven to be an efficient and effective representa-
tion, especially for handwritten documents. Unlike the
thinned skeletons, chain code is a lossless representation in the sense that the pixel image can be fully recovered from its chain code representation. [19]. Chain codes are used to represent a boundary by connecting sequence of straight line segments of
specified length and direction. Typically, this representation is based on the 4- or 8- connectivity of the segment where, direc- tion of each segment is coded using an alphabet scheme such as; the one shown in Fig. (7). Since digital images are usually acquired and processed in a grid format with equal spacing in the x and y directions, the algorithm must choose which path to go first and must return back to the cross point to follow a different path. To solve this problem, the developed chain code is designed to classify the paths, either as a terminated path (as shown in Fig 7-a), forked path (as shown in Fig 7-b), or circular path (as shown in Fig- 7-c and Fig- 7-d). When the tracing reaches a cross point of many paths, it analyzes each path to know its type and the number of pixels it contains. Then, it sorts the traced paths;starting first with the circular paths, then the terminated paths and the forked paths at last.
The circular and terminated paths are sorted according to the number of pixels the path contains, forked paths are sorted according to the number of pixels the path contains to the cross point of other paths.
Where, n is the number of pixels of the traced text segment,
xn and yn are the normalized values, x and y are the old pixel coordinates, xmin is the smallest registered x coordinate value,

xmax is the largest registered x coordinate value, ymin is the smallest registered y coordinate value, ymax is the largest reg- istered y coordinate value.

H1 Center point for each block (10×10)

X1,X2,X3 initial point for each block

Background of image

Fig.8 Center point for each block using chain code
The Euclidean distance between each pixel (x, y) on the boundary and the centric pointwere designed, as eq. (8) shown in Table-1.

International Journal of Scientific & Engineering Research, Volume 5, Issue 1, January-2014 93

ISSN 2229-5518

D( x, y) =

( x − x

centriod

) 2 + ( y − y

centriod )

4.1 Input Handwritten Text Dataset

The handwritten text dataset are recorded by Scanner un- der windows operating system with an attribute of 24-BMP
……..……………….(Eq.8)
Using these key points, points X1, X2, X3, X4 were found to bethe initial points and center points of the each block in the of image. A sample of the way to find these points, is shown in Fig.3. H1 (centric point) was found and then Euclidean dis- tance of pixels on the boundary was calculated.
Finally, the recognition for partially occluded and overlap- ping objects in composite scenes is done. The objects are matched against the scene and their positions are recovered; not effectively applicable to ink of text, color of text and scale invariant cases. Rate of recognition is Successful [7]. As it is can be clearly seen, the similarity between the verified image text and the trained set can be represented by the minimum
distance test (i.e. utilizing the Mean-Square-Error ―MSE‖ cri-
terion), given by:
image. We used the database for footprints recognition exper- iments. Here, we have experimented with nearly 40 images with variations of 20 persons taken by 4 samples; male, fe- male, and verify image is the same font of image-1 But, the character and scaling of font were different, as shown in Fig- (9- 1).

Min{MSE

} = Min{ ∑ (V

, −V

Fig. (9-1) Handwritten Text Dataset

I1, ) 2 }J, for K = 1,2,...S., M ER

K i = K i

M + i

………………..(Eq.9)

Query text image features

codebook

H X1X2X3.....Xk

Fig. (9-2) Median Filter of Handwritten Text Dataset

4 EXPERIMENT AND EVALUATION

To test the general applicability of the proposed approach, the handwritten text recognition system was built to distin- guish the query text in between dataset. The camera takes the image. This research shows that the shapes of pattern spectra differ from person to person. Features of text image are de- fined from Angular relation between characters’ Region. In the following, an explanation about input/output details and the evaluation of the proposed system:
Fig. (9-3) Centric Point for Handwritten Text Dataset

4.2 Output Results

The experiment results show the effectiveness of the pro- posed method. They show clearly the flexibility of the method in relation to step translation of the handwritten Text. A pre- view image of the Database of text is as shown in Fig-(10). The experimental observations of the experiments performed on datasets are shown in Table-2 and Table-3 as follows:

International Journal of Scientific & Engineering Research, Volume 5, Issue 1, January-2014 94

ISSN 2229-5518

Fig10 a- Verify Image b-Extract Features to verify Image
The Euclidean Distance between trained set and the verify- ing handwritten text image is obvious, as listed below:

TABLE 1. EUCLIDIAN DISTANCE BETWEEN INITIAL POINT AND CENTRIC POINT FOR EACH IMAGE AND VERIFIED IMAGE

4.3 Evaluation

In the current computer implementation of determinant problem based class and mapping, a careful computation treatment was needed, especially with that related to the vari- ables precision and the normalization of determinant values and using chain coding . Thereby, the numerical experiments indicate quite optimistic availability of the proposed algorithm for text recognition system. Suppose an existed image within the trained set has been selected to be verified, as illustrated in Fig (9-1), Fig (9-2), Fig (9-3) and Fig (10).

5. CONCLUSION

In this paper, a complete and fully automatic approach for Handwritten Text recognition images is proposed. The algo- rithms used in Handwritten Text recognition are categorized into three stages: gathering sample of handwritten text, pre- processing to bold text and remove noise, feature extraction and template matching. Our recognition makes the computa-
tionally approach inexpensive and significantly robust recog-
nition decision using three-stage feature matching with centric point and the boundary edge of Handwritten Text measures, significantly improved the matching performance. Comparing with other methods a high recognition rate by verifying raw text directly is difficult to obtain, because people stand in var- ious positions with different distances and angles between the characters and ink of pen and press on pen during writing. To achieve robustness in matching an input Handwritten Text, it
The Min {MSE} between trained set and the verifying
Handwritten text image is obvious, between ED image1 and
ED image vi.e. Min {MSEK}=MSE1,which is illustrated in
Eq.(9) as listed below:

TABLE 2. MEAN SQUARE ERROR BETW EEN TRAINING SET OF TEXT IMAGE DATA SET AND VERIFY IMAGE

must be normalized in position and direction. Such normaliza- tion might remove useful information for recognition

References

[1] E. Augustin, M. Carr´e, G. E., J. M. Brodin, E. Geoffrois, and F. Preteux. Rimes evaluation campaign for handwritten mail processing. In Proceedings of the Workshop on Frontiers in Handwriting Recognition, pages 231–235, 2006.

[2] R. Bertolami and H. Bunke. Hidden markov modelbased ensemble methods for offline handwritten text line recognition. 41(11):3452–3460, Nov. 2008.

[3] H. Bunke. Recognition of cursive roman handwriting: past, present and future. In Document Analysis and Recognition, 2003. Proceedings. Seventh International Conference on, pages 448 – 459 vol.1, aug. 2003.

[4] R. G. Casey. Moment normalization of handprinted characters. IBM Journal of Research and Development, 14(5):548 –557, sep. 1970.

[5] P. Dreuw, P. Doetsch, C. Plahl, and H. Ney. Hierarchical hybrid MLP/HMM or rather MLP features for a discriminatively trained gaussian HMM: a com- parison for offline handwriting recognition. In IEEE International Conference on Image Processing, Brussels, Belgium, Sept. 2011.

[6] P. Dreuw, G. Heigold, and H. Ney. Confidence- andmargin-based mmi/mpe discriminative training for offline handwriting recognition. Int. J. Doc. Anal. Recognit., 14(3):273–288, Sept. 2011.

[7] S. Espa˜na-Boquera, M. Castro-Bleda, J. Gorbe-Moya, and F. Zamora-

Martinez. Improving offline handwritten text recognition with hybrid

International Journal of Scientific & Engineering Research, Volume 5, Issue 1, January-2014 95

ISSN 2229-5518

hmm/ann models. Pattern Analysis and Machine Intelligence, IEEE Transac- tions on, 33(4):767 –779, april 2011.

[8] A. Gim´enez, I. Khoury, and A. Juan. Windowed bernoulli mixture hmms for arabic handwritten word recognition. In Frontiers in Handwriting Recogni- tion (ICFHR), 2010 International Conference on, pages 533 –538, nov. 2010.

[9] A. Graves, M. Liwicki, S. Fernandez, R. Bertolami, H. Bunke, and J. Schmid- huber. A novel connectionist system for unconstrained handwriting recogni- tion.31(5):855–868, May 2009.

[10] E. Grosicki and H. El Abed. Icdar 2009 handwriting recognition competition.

In Document Analysis and Recognition, 2009. ICDAR ’09. 10th International

Conference on, pages 1398 –1402, july 2009.

[11] S. Jonas. Improved modeling in handwriting recognition. Master’s thesis, Hu man Language Technology and Pattern Recognition Group, RWTH Aachen University, Aachen, Germany, Jun 2009.

[12] C.-L. Liu, M. Koga, H. Sako, and H. Fujisawa. Aspect ratio adaptive normali- zation for handwritten character recognition. In T. Tan, Y. Shi, and W. Gao, editors, Advances in Multimodal Interfaces — ICMI 2000, volume 1948 of Lecture Notes in Computer Science, pages 418– 425. Springer Berlin / Heidel- berg, 2000. 10.1007/3- 540-40063-X 55.

[13] C.-L. Liu, K. Nakashima, H. Sako, and H. Fujisawa. Handwritten digit recog- nition: benchmarking of state-of-the-art techniques. Pattern Recognition,

36(10):2271–2285, 2003.

[14] C.-L. Liu, H. Sako, and H. Fujisawa. Handwritten chinese character recogni- tion: alternatives to nonlinear normalization. In Document Analysis and Recognition,2003. Proceedings. Seventh International Conference on, pages

524 – 528 vol.1, aug. 2003.

[15] U.-V. Marti and H. Bunke. The iam-database: an English sentence database for offline handwriting recognition. 5(1):39–46, Nov. 2002.

[16] T. Miyoshi, T. Nagasaki, and H. Shinjo. Character normalization methods using moments of gradient features and normalization cooperated feature ex- traction. In Pattern Recognition, 2009. CCPR 2009. Chinese Conferenceon, pages 1 –5, nov. 2009.

[17] M. Pastor, A. Toselli, and E. Vidal. Projection profile based algorithm for slant removal. In A. Campilho and M. Kamel, editors, Image Analysis and Recog- nition,volume 3212 of Lecture Notes in Computer Science, pages 183–190. Springer Berlin / Heidelberg, 2004. 10.1007/978-3-540-30126-4 23.

[18] H. Pesch. Advancements in latin script recognition. Master’s thesis, RWTH Aachen University, Aachen, Germany, Nov. 2011.

[19] J.-F. Rivest, P. Soille, and S. Beucher. Morphological gradients. Journal of

Electronic Imaging, 2(4):326–336,1993.

[20] C.P. Sumathi1, T. Santhanam2 and G.Gayathri Devi3, ‖ A SU RV EY ON VARIOUS APPROACHES OF TEXT EXTRACTION IN IMAGES ‖ Inat-ern tional Journal of Computer Science & Engineering Survey (IJCSES) Vol.3, No.4, August 2012 DOI : 10.5121/ijcses.2012.3403 27

[21] Bremananth R and Prakash A, ―Tamil Numerals Identification ‖,Intae-rn tional Conference onAdvances in Recent Technologies in Communication and Computing, page(s): 620 – 622, 2009

[22] Hewavitharana S and Fernando H.C, ―A Two Stage Classification Approach to Tamil Handwritten Recognition ‖,Tam ilInternet,C alifornia,U SA ,2002.

[23] Indra Gandhi R and Iyakutti K, ―An attempt to Recognize Handwritten Tamil Character usingKohonen SOM ‖,Int.J.ofA dvance d N etw orking and Applications, Volume: 01 Issue: 03 Pages:188-192, 2009