EVALUATION OF IMPROVED FUZZY INFERENCE SYSTEM TO PRESERVE IMAGE EDGE FOR IMAGE ANALYSIS

There are numerous applications based on edge detection have been used in the area of image analysis. The technique of edge detection is an important step towards the visual system reliability and security that delivers a better understanding in many applications like object recognition classification, photography, and many more others computer vision application such as pedestrian detection for a vehicle on the road, face detection in biometric, and video surveillance. We know that detection of edge detection is a scientific technique that is practiced to provide better image analysis and towards this purpose, lots of edge identification approach was already implemented by the researchers in the image processing era, but they do not achieve acceptable results for all types of the image that can help in the image analysis. In this research, we introduced a comparative evaluation of edge detection algorithms for instance Sobel, Canny, and Fuzzy logic-based edge detector with an Improved Fuzzy Inference (IFI) system is presented to preserve image edge for image analysis. The key contribution of this research is developing a new hybrid edge mechanism by utilizing the gradient and standard deviation based fuzzy logic approach to achieve better edge detection efficiency. To provide a better edge or non-edge region from an image the proposed IFI has its impact on quality parameters, for instance, Peak Signal to Noise Ratio (PSNR), Mean Square Error (MSE), Entropy and Structural Similarity (SSIM) with the execution time. At last, the performance parameters of the proposed IFI system is compared with other edge technique and we observed that the achieved results justify the proposed work in image processing.