The oil seal spring is important and widely used in mechanical equipment. However, online inspection of the oil seal spring is extremely difficult because of its circular shape with a complex edge. An inspection algorithm for an oil seal spring based on Gaussian filtering was proposed to reduce human operations and ensure consistent product quality. Gaussian filtering can remove the contour shape of the spring and separate its characteristic parameters, which are independent from the shape, size, and location of the spring. This makes it suitable for inspecting the defects of the spring. To fulfill the inspection process, the necessary circle detection and self-calibration algorithms were discussed in details. Experimental results show that the proposed algorithm is fast, accurate, and robust in defect detection and classification of the oil seal spring.