As core devices for the smartphone RF front end, surface acoustic wave (SAW) filters are in short supply. The detection of SAW filter parameters refers to the connection between layout design and process production, which is an important part of capacity improvement. This paper devises a method based on image processing to detect SAW filter parameters. We improve the morphological operator to recover an image and identify the number of interdigital transducer (IDT) finger bars under noise conditions. The feature points in the color image are selected to extract the scale. The Canny edge detection effect is enhanced through using an adaptive filter, increasing the gradient operator, bilinear interpolation, and other algorithms. We use a minimum shape to enclose the edges to determine the IDT width and period and apply Fourier transform to verify the detection results. The experimental results show that the number of IDT finger bars is accurately identified. The width and period are exactly the same as the real values at the 10th percentile, and the detection requirements are met.