IJCSNS International Journal of Computer Science and Network Security, VOL.10 No.1, January 2010 58 Manuscript received January 5, 2010 Manuscript revised January 20, 2010 Comparison of Filters used for Underwater Image Pre-Processing Dr.G.Padmavathi, Dr.P.Subashini, Mr.M.Muthu Kumar and Suresh Kumar Thakur Department of Computer Science, Avinashilingam University for Women, Coimbatore, TN, India Abstract Underwater image pre-processing is absolutely necessary due to the quality of images captured under water. Basically, under water images suffer from quality degradation due to transmission of limited range of light, low contrast and blurred image due to quality of light and diminishing color. When an underwater image is captured, pre-processing is necessarily done to correct and adjust the image for further study and processing. Different filtering techniques are available in the literature for pre-processing of under water images. The filters used normally improve the image quality, suppress the noise, preserves the edges in an image, enhance and smoothen the image. Therefore an attempt has been made to compare and evaluate the performance of three famous filters namely, homomorphic filter, anisotropic diffusion and wavelet denoising by average filter used for under water image pre-processing. Out of the three filters, wavelet denoising by average filter gives desirable results in terms of Mean Square Error and Peak Signal to Noise Ratio. However the elapsed time of the three filters is also studied to identify the suitable filters that process the image quickly by preserving the image quality. Key words: Image processing, denoising, color enhancement, homomorphic filters, SRAD filtering, wavelet denoising, Mean Square Error , Peak Signal to Noise Ratio and elapsed time I. Introduction Underwater instruments are used for remote sensing, because the earth is an aquatic planet and as much as 80% of its surface is covered by water. Moreover, there is a strong interest in knowing what lies in underwater. The optical sensors are used in underwater instruments to capture acoustic signal and the signals are converted into images. The images are disturbed with, the transmission of limited range of light, disturbance of lightening, low contrast and blurring of image, color diminishing during capturing. The large disturbances change the image quality and they show large temporal and spatial variations. Therefore, the image must be pre-processed before operations like segmentation or feature detection, which are the important processes in image processing. To denoise an image without affecting the image quality and edges in an image, edge preserving filters are used. The filtering methods perform several successive independent processing steps which respectively correct non-uniform illumination, suppress noise, enhance contrast and adjust colors. Need for Pre-Processing The pre-processing is required for underwater images due to poor captured image quality. The following reasons justify why the pre-processing is necessary for underwater images. i. Underwater image degradation is due to specific transmission properties of light in the water like absorption and scattering. ii. Specificity of environment like light changing, water turbidness, and blue hue is more or less predominant when vehicles move. iii. Specificity of video captures like unknown rigid scene and unknown color or low light sensitivity due to Marine snow. Therefore an attempt has been made to identify the suitable filter for pre processing the underwater images. This work is organized as follows. Section.2 will describe the algorithm used for underwater pre-processing, Section.3 discusses different filtering methods, and Section.4 presents the results. Finally Section.5gives the conclusion. 2. The algorithm used for underwater pre- processing Basically image processing steps are as follows a.) Image acquison b.) Pre-processing c.) Discretization/Digitization d.) Image Enhancement and Restoration e.) Image segmentation f.) Feature extraction g.) Image representation h.) Image interpretation Pre-Processing is an important step in image processing technique. The algorithm used for underwater pre- processing corrects the underwater perturbation sequentially.