Texture recognition by generalized probabilistic decision-based neural networks
檔案
- 000287419900172.pdf (890.3 KB, Adobe PDF)
日期
2011-05-01
類型
系所
期刊名稱
EXPERT SYSTEMS WITH APPLICATIONS
卷期與頁次
第 38 卷第 5 期,頁 6184–6189
ISSN
0957-4174
語言
英文
摘要
Texture recognition have received tremendous attentions in the past decades, due to its wide applications in computer vision and pattern recognition. For various applications, formulating texture features in distributional forms can sometimes provide meaningful representation than in numerical forms. In this paper, a generalized probabilistic decision-based neural network (GPDNN), based on a novel methodology for the measurement of the difference between two distributions, is proposed for texture recognition. Based on a two-layer pyramid-type network structure, the proposed GPDNN receives texture data via 2-D grid input nodes, and outputs the classification and/or retrieval results at the top layer node. Our prototype system demonstrates a successful utilization of GPDNN to the texture recognition on 40 texture images selected from the MIT Vision Texture (VisTex) database. Regarding the performance, experiment results show that (1) based on the proposed distribution difference measurement method, the texture retrieval accuracy is improved from 77% to 82% by comparing with some recently published leading methods, and (2) the proposed GPDNN has significant improvements in classification accuracy from 82.2% to 90.1% and retrieval accuracy from 79.9% to 88.6% by comparing with traditional approaches. (C) 2010 Elsevier Ltd. All rights reserved.
關鍵詞
Bayesian decision-based neural networksGeneralized probabilistic decision-based neural networksGPDNNTexture recognitionSupervised learning所屬典藏
期刊論文引用此條目
Xu, Y.-Y., Tseng, C. L., & Fu, H.-C. (2011). Texture recognition by generalized probabilistic decision-based neural networks. EXPERT SYSTEMS WITH APPLICATIONS, 38(5), 6184–6189. https://doi.org/10.1016/j.eswa.2010.11.051
引用文字依 APA 第 7 版格式自動產生,使用前請再核對。
分享
永久網址:https://ir.lib.nycu.edu.tw/handle/11536/8980