Image Enhancement via Gaussian Low-Pass Filtering, Gradient Operations, and Laplacian Operator

Image enhancement techniques such as Gaussian low-pass filtering, gradient operations, and Laplacian operator can significantly improve image quality by refining texture details and edge features. Gaussian filtering is implemented using a convolutional kernel with adjustable sigma values to smoothly remove high-frequency noise while preserving overall image structure. Gradient operations (e.g., Sobel or Prewitt operators) emphasize edges by calculating intensity variations along horizontal and vertical directions, while the Laplacian operator enhances fine details through second-derivative-based sharpening. These algorithms are integrated into a user-friendly GUI interface, allowing real-time adjustment of parameters like kernel size, threshold values, and blending coefficients. The system enables interactive previewing of effects, making it particularly useful for image restoration, quality improvement, and analytical tasks in computer vision applications. Key functions include modular implementation of filter kernels, edge detection algorithms, and histogram-based contrast optimization for adaptive enhancement.