Search Results

You are looking at 1 - 2 of 2 items for

  • Author: Syed Bakar x
Clear All Modify Search
Open access

Ali Farzamnia, Sharifah Syed-Yusof, Norsheila Fisal and Syed Abu-Bakar

Investigation of Error Concealment Using Different Transform Codings and Multiple Description Codings

There has been increasing usage of Multiple Description Coding (MDC) for error concealment in non-ideal channels. A lot of ideas have been masterminded for MDC method up to now. This paper described the attempts to conceal the error and reconstruct the lost descriptions caused by combining MDC and lapped orthogonal transform (LOT). In this work LOT and other transforms codings (DCT and wavelet) are used to decorrelate the image pixels in the transform domain. LOT has better performance at low bit rates in comparison to DCT and wavelet transform. The results show that MSE for the proposed methods in comparison to DCT and wavelet have decreased significantly. The PSNR values of reconstructed images are high. The subjective evaluation of image is very good and clear. Furthermore, the standard deviations of reconstructed images are very small especially in low capacity channels.

Open access

Yun Chang, Jia Lee, Omar Rijal and Syed Bakar

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.