DCNN Based Technique to Analyze the Data of Foggy and Snowy Season

Abstract

Abstract Image Quality Analysis (IQA) is most significant concepts that is gaining attention among the researchers. Most images are considerably influenced by ambient lights. HumanVisual System perceives theimages quality in day and night time that causes the deprivation of luminance and features. In this article, we put forward an adaptive fuzzy-based DCNN technique that estimates the loss and enhancement of the images during seasonal changes. The natural scenery images are collected and preprocessed using Gaussian filter method that removes the unwanted noises. The preprocessed image is then guided with a guided filter method that helps to segment the seasonal changes of an image. The statistical features are extracted from the Adaptive Fuzzy-based Gamma Correction method that specifically leverages the gamma parameters using fuzzy-based decisional approach. Further on, the Deep Convolutional Neural Networks (DCNN) is running to classify the seasonal changes on images based on the computed image quality score. Investigational result have proven the accuracy of suggested technique in concerning of accuracy, precision and recall.