Jung-Hua Wang

Learn More
In this paper, we present a novel approach to the restoration of noise-corrupted image, which is particularly effective at removing highly impulsive noise while preserving image details. This is accomplished through a fuzzy smoothing filter constructed from a set of fuzzy membership functions for which the initial parameters are derived in accordance with(More)
This paper presents a two-stage approach that is effective for performing fast clustering. First, a competitive neural network (CNN) that can harmonize mean squared error and information entropy criteria is employed to exploit the substructure in the input data by identifying the local density centers. A Gravitation neural network (GNN) then takes the(More)
This paper presents a novel adaptive approach to image restoration using fuzzy spatial filtering optimized via image statistics rather than a prior knowledge of specific image data. The proposed histogram adaptive fuzzy (HAF) filter is particularly effective for removing highly impulsive noise while preserving edge sharpness. This is accomplished through a(More)
This paper presents a self-creating neural network in which a conservation principle is incorporated with the competitive learning algorithm to harmonize equi-probable and equi-distortion criteria. Each node is associated with a measure of vitality which is updated after each input presentation. The total amount of vitality in the network at any time is 1,(More)
This paper optimizes the performance of the growing cell structures (GCS) model in learning topology and vector quantization. Each node in GCS is attached with a resource counter. During the competitive learning process, the counter of the best-matching node is increased by a defined resource measure after each input presentation, and then all resource(More)
In a recent publication [1], it was shown that a biologically plausible RCN (Representation-burden Conservation Network) in which conservation is achieved by bounding the summed representation-burden of all neurons at constant 1, is effective in learning stationary vector quantization. Based on the conservation principle, a new approach for designing a(More)
This paper explores internal representation power of product units [1] that act as the functional nodes in the hidden layer of a multi-layer feedforward network. Interesting properties from using binary input provide an insight into the superior computational power of the product unit. Using binary computation problems of symmetry and parity as illustrative(More)