Deep Morphological Neural Networks
This addresses a cumbersome manual process in image analysis for researchers/engineers working with geometric features, though it appears incremental as it integrates morphology into existing deep learning frameworks.
The paper tackles the problem of manually selecting morphological operations and structuring elements for image analysis by proposing a morphological neural network layer that automatically learns these parameters. Experimental results show the approach achieves high computational efficiency and accuracy on shape/geometry classification datasets.
Mathematical morphology is a theory and technique to collect features like geometric and topological structures in digital images. Given a target image, determining suitable morphological operations and structuring elements is a cumbersome and time-consuming task. In this paper, a morphological neural network is proposed to address this problem. Serving as a nonlinear feature extracting layer in deep learning frameworks, the efficiency of the proposed morphological layer is confirmed analytically and empirically. With a known target, a single-filter morphological layer learns the structuring element correctly, and an adaptive layer can automatically select appropriate morphological operations. For practical applications, the proposed morphological neural networks are tested on several classification datasets related to shape or geometric image features, and the experimental results have confirmed the high computational efficiency and high accuracy.