NOISE REDUCTION BASED ON ARTIFICAL BEE COLONY (ABC) ALGORITHM

Abstract

A 2D FIR filters is presented for denoising the digital images. Here the filter coefficients of 2D FIR filters were optimized using the Artificial Bee Colony (ABC) algorithm. To achieve the most tremendous filter design, the filter coefficients were experienced with different mask and connection types during optimization. Initially, the speckle noise with variances was added to the synthetic test image. Soon after, these noisy images were denoised with the proposed approach and other familiar filter types called noise adaptive switched median filter are used. For image quality determination metrics such as mean square error, peak signal-to-noise ratio and signal to noise ratio were used. Even if the noise having maximum variance, the proposed approach performed better than other filtering methods. This noisy image was denoised with high PSNR and SNR values. The performance of the planned approach was tested on several clinical ultrasound images such as kidney and liver tissues. As results, that the 2D FIR filters designed based on ABC optimization can eliminate speckle noise quite well on noise added test images and inherently noisy ultrasound images.