Denoising is an indispensable task to restore the image features from the corrupted low-quality images and improve the perceptual quality of images. Besides significant advantages in the field of the denoising images, several kinds of literature face difficulties in reducing the impulse noise in the image. This work designs a novel filter through the hybridization of the fuzzy filter and the Non-Local Means (NLM) filter. The proposed scheme removes the impulse noise in the images in two stages 1) noise identification, and 2) denoising stage. Noise identification is made by constructing the binary map based on the Support Vector Neural Network (SVNN) classifier. The SVNN classifier is trained based on the Genetic Algorithm (GA) for identifying the optimal weights and the bias. The features for the training are extracted from the images, and thus, the training procedure differentiates the noisy pixel from the good pixel. At the denoising stage, the hybrid filter is enabled to remove the impulse noise in the image. The proposed model uses the five standard images, such as Baboon, cameraman, Lena, peppers, and Pemaquid Point Lighthouse image for the experimentation purpose. From the simulation results, it is evident that the proposed hybrid filter along with the SVNN classifier achieved improved results with the values of 47.278 dB, 0.978 and 61.637 dB for the PSNR, SSIM, and the SDME, respectively.
30 March 2026 in Archives of Computational Methods in Engineering
With rising global temperatures attributed to climate change, an increase in fire occurrences worldwide is anticipated. Therefore, a detailed examination of changing fire patterns is essential to improve our understanding of effective control strategies. This study analyzes the long-term trends of fire activity in Southern India (8–20° N, 73–85° E), utilizing MODIS active fire count data from January 2003 to December 2023. The climatological monthly mean results show that Southern India experiences heightened fire activity from December to May, reaching a peak in March. Yearly variations indicate that the highest fire counts occurred in 2021, followed by 2023, 2012, and 2018. The three most significant fire years in recent history reflect an upward trend in fire activity over the past decade, confirming insights from annual trend analysis. The correlation between inter-annual fire anomalies and different meteorological factors reveals a notable negative relationship with precipitation and soil moisture and a positive relationship with surface air temperature (SAT). Soil moisture demonstrates a stronger correlation (−0.45) than precipitation and SAT. In summary, long-term trends show a noteworthy annual increase of 3%. Additionally, monthly trends reveal interesting rising patterns in October, November, December, and January with higher significance levels. Our research supports regional climate action initiatives and policies addressing fire incidents in Southern India in light of the ongoing warming crisis.