Hybrid Filtering Technique for Image Denoising using Artificial Neural Network
Paras Chawla1, Ruchi Mittal2, Kavita Grewal3
1Er. Paras Chawla, Electronics & Communication Deptt., Kurukshetra University, JMIT Radaur, kurukshaetra, India.
2Er. Ruchi Mittal, Electronics & Communication Deptt., Kurukshetra University, JMIT Radaur, Yamunanagar, India.
3Er. Kavita Grewal, Electronics & Communication Deptt., Kurukshetra University, JMIT Radaur, Yamunanagar, India.
Manuscript received on August 01, 2012. | Revised Manuscript received on August 05, 2012. | Manuscript published on August 10, 2012. | PP: 35-40 | Volume-1 Issue-3, August 2012. | Retrieval Number: C0212071312/2012©BEIESP
Open Access | Ethics and Policies | Cite
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Image enhancement and restoration in a noisy environment are fundamental problems in image processing. Various filtering techniques have been developed to suppress noise in order to improve the quality of images. Many filters for image processing are designed assuming a specific noise distribution. In the medical field image processing play an important role because most of the diseases are diagnosed by means of medical images. In order to use these images for the diagnosing process, it must be noiseless. However, most of the images are affected by noises and artifacts. Hence an effective technique for denoising medical images particularly in Computed Tomography (CT) is necessary, which is a significant and most general modality in medical imaging. In order to achieve this denoising of CT images, an effective CT image denoising technique is proposed. The proposed technique remove the Additive white Gaussian Noise from the CT images and improves the quality of images. The proposed work is comprised of three phases; they are preprocessing, training and testing. In the preprocessing phase, the CT image which is affected by the AWGN noise is transformed using multi wavelet transformation. In the training phase the obtained multi-wavelet coefficients are given as input to the Adaptive Neuro-Fuzzy Inference System (ANFIS). In the testing phase, the input CT image is examined using this trained ANFIS and then to enhance the quality of the CT image thresholding is applied and then the image is reconstructed. Hence, the quality enhanced and the denoising CT images are obtained in an effective manner.
Keywords: CT image; denoising; Additive White Gaussian Noise (AWGN); multi-wavelet transformation; Adaptive Neuro- Fuzzy Inference System (ANFIS); thresholding