Handwritten Thai Character Recognition Using Fourier Descriptors and

Handwritten Thai Character Recognition Using Fourier Descriptors and Robust C -Prototype Olarik Surinta Supot Nitsuwat NCCIT 05

INTRODUCTION n n n This research proposes the method for Thai handwritten character recognition. The processing is based on Thai characters on which preprocessing have been conducted. There are 44 Thai characters: ������� � ������� NCCIT 05 2

INTRODUCTION Training Scheme Image Processing Feature Extraction (FD) C, c Recognition Scheme Unknown Image Processing RCP Training C, c Database Scheme Feature Extraction (FD) RCP Recognition Scheme Output Figure 1 Thai handwritten recognition scheme flow diagrams. NCCIT 05 3

DATA PREPROCESSING Character-images are images of Thai hand -written characters. n The output will be stored in the term of digital data by scanning. One bitmap file with gray scale pattern and 256 levels specifics one character. n Figure 2 A prototype character-image. NCCIT 05 4

IMAGE PROCESSING n Binarization ¨ Binarization converts gray-level image to black-white image, and to extracting the object component from background, this scheme will check on every point of pixel. Figure 3 The example of binarization scheme. NCCIT 05 5

Binarization n The individual bit bares 2 possible values: 1 refers to background and ¨ 0 refers to object ¨ (B) (A) Figure 4 The diagram of extracting the object from the background component in the image. NCCIT 05 (C) 6

Edge Detection Edge detection is one of an important image processing phases. n This paper uses chain code technique to detect the image’s edge. The direction has been classified by 8 categories: n Figure 5 Chain code with 8 directions. NCCIT 05 7

Edge Detection n n Once the edge of image has discovered, shown in figure 4, the process needs to find the character line. The coordinate is represented by complex number as the formula: Figure 6 coordinate represented in character image. NCCIT 05 8

FOURIER DESCRIPTORS n n n Fourier Features used to describe the edge of the object works by identify coordinate ; K = 0, 1, …, N-1 where N is any other area in the image. All point will be represents as complex number. Therefore, the DFT can be derived as below: NCCIT 05 9

FOURIER DESCRIPTORS n n From the above formula, coefficient vector will be automatically calculated. This vector fits as 1 dimension with the size of 1 x 10 or 1 xn Figure 7 Fourier Descriptors of Image. NCCIT 05 10

ROBUST C-PROTOTYPES (RCP) RCP can be determined in grouping phase in order to estimate C-Prototypes spontaneously, utilizing loss function and square distance to reduce some noise. n The diagram of solving the problem by RCP is shown in figure 8 n NCCIT 05 11

ROBUST C-PROTOTYPES (RCP) Figure 8 RCP algorithm. NCCIT 05 12

EXPERIMENTAL RESULT n n n This research paper proposes the method for Thai Handwritten Character Recognition using Fourier Descriptors and Robust C-Prototype clustering. Recognition scheme is based on features extracted from Fourier transform of the edge of character-image. the character-image is described by a group of descriptors. NCCIT 05 13

EXPERIMENTAL RESULT n n n We train the system using the RCP training scheme to find the centroid of the prototype (44 Prototypes) and membership function. Finally, the FD of unknown character-image is used to perform recognition step. In this way the experimental results of recognition, RCP can perform with accuracy up to 91. 5%. NCCIT 05 14

Figure 9 The character images the adjustment scheme. NCCIT 05 15