• 沒有找到結果。

Parallel thinning by a recurrent neural network

N/A
N/A
Info
下載
Protected

Academic year: 2022

Share "Parallel thinning by a recurrent neural network"

Copied!
1
0
0

加載中.... (立即查看全文)

立即下載 ( 1 頁 )

全文

(1)

題名: Parallel thinning by a recurrent neural network 作者: R. Y. Wu;W. H. Tsai

貢獻者: Department of Information Communication

關鍵詞: parallel thinning;recurrent neural network;template matching;excessive erosion 日期: 1994-06

上傳時間: 2009-11-25T02:31:04Z 出版者: Asia University

摘要: A 3-layer recurrent neural network is proposed for parallel thinning. This network iteratively removes the contour points of an object shape by template matching.

After the neural network converges, a perfectly 8-connected skeleton is derived.

The set of templates which the neural network tries to match is specially designed for a one-pass parllel thinning algorithm. The proposed neural network is shown both theoretically and experimentally to do the same work as the one-pass parallel thinning algorithm.

參考文獻

立即下載 ( DOC - 1 頁 - 31.50 KB )

相關文件

Exchange rates forecasting using a hybrid fuzzy and neural network model

improve the single-point values problems in BPNs, this paper attempts to propose a BPNs using a fuzzy set architecture, and modified neural network is designed to combine the

Fuzzy neural network approach for 2-D direction finding in multipath environments

Abstract: A fuzzy neural network (FNN) approach for estimating the two-dimensional (2-D) direction of a radiating source in coherent multipath environments via a

A Neural Fuzzy Network Approach to Radar Pulse Compression

Simulation results show that this neural fuzzy network pulse compression (NFNPC) algorithm has significant ad- vantages in noise rejection performance, range resolution ability,

A recurrent neural fuzzy network for word boundary detection in variable noise-level environments

Next, we use the TF-based and RTF-based RSONFIN algo- rithms to repeat the same experiment. The word boundaries de- tected by the TF-based RSONFIN algorithm are shown by solid lines

Single-hidden-layer feed-forward quantum neural network based on Grover learning

The quantum neuron and weights, along with a Grover searching algorithm based learning, result in a novel and efficient neural network characteristic of reduced network, high

Supervisory recurrent fuzzy neural network control of wing rock for slender delta wings

Supervisory Recurrent Fuzzy Neural Network Control of Wing Rock for Slender Delta Wings.. Chih-Min Lin, Senior Member, IEEE, and

A Xerion-based Perl program to train a neural network for grid pattern recognition

Abstract-Neural network training with the back propagation algorithm is an important artificial intelligence technique for grid pattern recognition. The training

An EEG spike detection algorithm using artificial neural network with multi-channel correlation

Abstract--An automatic spike detection algorithm for classification of multi-channel electroencephalographic (EEG) signals based on artificial neural network is