The data fusion is implement to take the survey data remotely from difference sources and have various looks to be combined to get a new agents. To get better quality of data we will present a method of fusion by wavelet transform with IHS Transformation method or PCA Transformation method. From the results showed that both IHS and PCA Transformation method able to be gotten high quality but the specifications of wave from damage is different.

The present research was aimed at systematic surveys and analyses of The Perception of Corporate Social Responsibility that affects to attitude about Siam Cement Group image of people in Bangkok. 440 people were statistically analyzed selected using by frequency percentages arithmetic mean standard deviations. As the result of research: (1) The most respondents were female aged between 18–30 year old graduated bachelor degree and were employed by private companies income between 10001 - 30000 baht. (2) The overall perception toward the management to social responsibilities SCG was also at a highest level. People received information through Television and Radio. (3) The overall attitude toward the management to attitude of about SCG image of people were in high agree with. (4) The level of perception toward the corporate social responsibility in Environment Social and Community at .05 level of significance.

The data fusion is implement to take the survey data remotely from difference sources and have various looks to be combined to get a new agent. To get better quality of data we will present a method of fusion by wavelet transform with IHS Transformation method or PCA Transformation method. From the results showed that both IHS and PCA Transformation method able to be gotten high quality but the specifications of wave from damage is different.

The segmentation of interesting objects within the image is an important process to provide information for other procedures. The major problem of image segmentation is the number of objects suitable for classifying objects. This research aims to present on Image Segmentation using Fuzzy C- Mean Via Image Filter. The objects will be split up using their object intensities. The proposed method can classify several objects at the same process. Therefore it saves time to process less than other existing methods. The proposed method is consisted of three steps: noise reduction histogram smoothing and object classification. The results of the proposed method found that objects are automatically classified by Fuzzy C-Mean. Moreover the algorithm that successfully calculates the proper number of segmentations

This report aims to present the random noise elimination of image based on edge preservation. This solution is a pixel processing using 29 templates. Each template consists of the considered pixel and its neighbor pixels. To eliminate noises the smoothing process replaces the new pixel intensity into the same considered processing pixel by the mean intensity of neighbor pixels. The condition of the template selection is based on the minimum variance of templates. As the experimental results this solution brings the peak signal-to-noise ratio (PSNR) higher than Gaussian filter Tomita’s marks Fukuda’s marks and Nagao’s marks and also gains contrast difference.