Mismatch-tolerant asynchronous grayscale morphological reconstruction

Mathematical morphology provides powerful methods for image analysis and segmentation both for binary and grayscale images. By implementing the required basic functions directly in hardware, the advantage of using a locally connected massively parallel array processor structure, such as CNN, can be fully realized. This paper presents an improved method and hardware implementation for performing asynchronously propagating morphological reconstruction for grayscale images. The functionality of the new implementation is tolerant to device mismatch with also better accuracy of the resulting output values.