Syed Abdul Rahman Syed Abu Bakar

A database of Arabic handwritten characters

Arabic character recognition is an important aspect in pattern recognition because there are many applications that depend on it. Database availability is a key factor that encourages researchers to conduct research in this field. This paper proposed a database with a variety of shapes for each character. The database contains 5,600 images written by 50 writers. Each character has 200 images divided into four groups (beginning, medium, end and isolated). This database can be used by the machine learning community for training and testing, in general, the database will help the researchers to compare and evaluate their algorithm performance.

Efficient online handwritten Chinese character recognition system using a two-dimensional functional relationship model

Efficient online handwritten Chinese character recognition system using a two-dimensional functional relationship model This paper presents novel feature extraction and classification methods for online handwritten Chinese character recognition (HCCR). The X-graph and Y-graph transformation is proposed for deriving a feature, which shows useful properties such as invariance to different writing styles. Central to the proposed method is the idea of capturing the geometrical and topological information from the trajectory of the handwritten character using the X-graph and the Y-graph. For feature size reduction, the Haar wavelet transformation was applied on the graphs. For classification, the coefficient of determination (R2p) from the two-dimensional unreplicated linear functional relationship model is proposed as a similarity measure. The proposed methods show strong discrimination power when handling problems related to size, position and slant variation, stroke shape deformation, close resemblance of characters, and non-normalization. The proposed recognition system is applied to a database with 3000 frequently used Chinese characters, yielding a high recognition rate of 97.4% with reduced processing time of 75.31%, 73.05%, 58.27% and 40.69% when compared with recognition systems using the city block distance with deviation (CBDD), the minimum distance (MD), the compound Mahalanobis function (CMF) and the modified quadratic discriminant function (MQDF), respectively. High precision rates were also achieved.

A Noise Elimination Procedure for Printed Circuit Board Inspection System

Image difference operation is frequently used in automated printed circuit board (PCB) inspection system as well as in many other image processing applications. During the implementation, this operation brings along the unwanted noise due to misalignment and uneven binarization. Thus, this paper proposes a method to eliminate, if possible, or to reduce as much as possible such noise during the computation of defect detection. This paper used a template PCB image and the tested PCB image as the input. Image subtraction operation will be applied between the images. The results of applying the proposed method showed a significant improvement during the real-time inspection of printed circuit boards.

Curvelet transform sub-difference image for crowd estimation

Counting people and estimating their number is a fundamental task for many intelligent security systems, including CCTV systems and other visual surveillance research areas. This paper presents a new approach for crowd counting. The proposed method is independent of any background modelling or background subtraction techniques. Moreover, the new method is able to handle the perspective phenomena in a simple way. To do so, the estimation is determined by an enhanced version of a difference image. Every two sequential frames are used to extract a difference image. The curvelet transform is then applied to both frames. The information stored in every scale in the new sub-band images can be used as a source for different features after a customized inverse curvelet transform. Two different curvelet inverse transforms with three different features are used to evaluate the proposed counting algorithm; a Back Propagation Neural Network (BPNN) is used for crowd quantity predictions. The overall performance is measured over a UCSD benchmark dataset.

Texture-Based Statistical Detection and Discrimination of Some Respiratory Diseases Using Chest Radiograph

This chapter proposes a novel texture-based statistical procedure to detect and discriminate lobar pneumonia, pulmonary tuberculosis (PTB), and lung cancer simultaneously using digitized chest radiographs. A modified principal component method applied to wavelet texture measures yielded feature vectors for the statistical discrimination procedure. The procedure initially discriminated between a particular disease and the normals. The maximum column sum energy texture measure yielded 98 % correct classification rates for all three diseases. The diseases were then compared pair-wise, and the combination of mean of energy and maximum value texture measures gave correct classification rates of 70, 97, and 79 % for pneumonia, PTB, and lung cancer, respectively.