Convex Filter Networks Based on Morphological Filters and their Application to Image Noise and Mask Removal

Kei-ichiro KOBAYASHI
Kiyoaki ITOI

IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences   Vol.E100-A    No.11    pp.2238-2247
Publication Date: 2017/11/01
Online ISSN: 1745-1337
DOI: 10.1587/transfun.E100.A.2238
Type of Manuscript: Special Section PAPER (Special Section on Smart Multimedia & Communication Systems)
Category: Image Processing
mathematical morphology,  maxout,  noise removal,  nonlinear filter,  neural network,  

Full Text: PDF>>
Buy this Article

This paper presents convex filter networks that are obtained from extensions of morphological filters. The proposed filter network consists of a convex and concave filter that are extensions of the dilation and erosion of mathematical morphology with the maxout activation function. Maxout can approximate arbitrary convex functions as piecewise linear functions, including the max function. The class of the convex function hence includes the morphological dilation and can be trained for specific image processing tasks. In this paper, the closing filter is extended to a convex-concave filter network with maxout. The convex-concave filter is trained by the stochastic gradient method for noise and mask removal. The examples of noise and mask removal show that the convex-concave filter can obtain a recovered image, whose quality is comparable to inpainting by using the total variation minimization with reduced computational cost without mask information of the corrupted pixels.