查詢結果分析
相關文獻
- 適應式影像還原--以計算智慧為方法
- ANFIS理論應用於教師人力需求預測模式之建構
- Fuzzy Cerebellar Model Articulation Controller
- Wavelet Transform Based Denoising in Transient Evoked OAE Measurement
- Learning to Predict Temperature and Time-Series by Using Neural Fuzzy Systems
- 並聯換流器轉換效率提升之控制策略
- 萬大水庫崩塌地之非監督式影像判釋:模糊粒子群演算法與自我組織映射圖研究
- 考量機率特性之結合反應曲面法與非線性時變粒子群演算法於電力諧波濾波器最佳化設計
- A HPSO Approach for Solving the Simultaneous Dynamic DBAP and QCAP in a Container Terminal
- 基於多種群量子粒子群的粗糙集屬性約簡演算法在故障診斷中的應用
頁籤選單縮合
題 名 | 適應式影像還原--以計算智慧為方法=Adaptive Image Restoration--A Computational Intelligence Approach |
---|---|
作 者 | 李俊賢; 陳玟彣; | 書刊名 | 資訊管理學報 |
卷 期 | 19:3 2012.07[民101.07] |
頁 次 | 頁475-507 |
分類號 | 312.1 |
關鍵詞 | 類神經模糊系統; 粒子群演算法; 遞迴最小平方估計法; 雜訊消除; 計算智慧; Neuro-fuzzy system; Particle swarm optimization; Recursive least squares estimator; Noise canceling; Computational intelligence; NFS; PSO; RLSE; |
語 文 | 中文(Chinese) |
中文摘要 | 影像訊號進行傳輸或轉換的過程中經常會受到其它訊號的干擾,導致影像失真的情形發生。為解決此問題,本研究針對灰階影像失真之問題提出一計算智慧之方法,以Takagi-Sugeno類神經模糊系統為架構,結合粒子群最佳化演算法(PSO)與遞迴最小平方估計法(RLSE)建構出複合學習演算法,並且應用於適應性雜訊消除的問題,最終目標在於使受干擾之影像能夠儘量還原接近原始影像。此外,本研究中亦針對類神經模糊系統之模糊規則數目之增減對於系統效能是否有顯著的影響作探討。本研究以灰階影像的雜訊消除進行實驗,將所提出的複合學習演算法與標準的粒子群演算法進行比較,實驗結果顯示本研究所提出之方法優於標準的粒子群演算法。 |
英文摘要 | Image signal may be interfered by some unknown mechanisms during transmission or transformation, resulting in image corruption that useful information or details in the image can be lost more or less. In the paper, we propose a computational intelligence approach with the famous adaptive noise canceling framework to the problem of gray-level image restoration. The approach is based on the theory of Takagi-Sugeno neuro-fuzzy system (NFS) and the proposed PSO-RLSE hybrid learning method which includes the famous particle swarm optimization (PSO) and the well-known recursive least squares estimator (RLSE) algorithm. With the NFS-based image restoration system, the research target is to restore gray-level images from their corrupted versions as possible as can be. In the study, we investigated different sizes of rule base to see the influence by the amount of fuzzy If-Then rules to the restoration performance, and we also compared the proposed PSO-RLSE learning method to the PSO learning method for restoration performance. Several results are shown in the paper. Through the experimental results, the proposed PSO-RLSE method outperforms the PSO method, in terms of restoration performance and learning convergence. |
本系統中英文摘要資訊取自各篇刊載內容。