查詢結果分析
相關文獻
- Vector Quantization of Images with Codeword-Rotation Algorithm
- A High Fidelity Image Coding Using VQ-BTC
- Modified Search Order Coding for Vector Quantization Indexes
- 一個適用於近似週期信號的新自適性向量量化法及其在心電圖資料壓縮上的應用
- 模糊C-均值影像壓縮硬體電路之高階合成與模擬
- Prototype LVQ Based Computerized Tool for Accent Diagnosis among Chinese Speakers of English as a Foreign Language
- 懲罰模糊C-均值群集技術應用於影像壓縮技術之研究
- Camoufleur影像加密系統的設計與製作
- Vector Quantization Using Grey-based Competitive Learning Network in the MDT Domain
- 植基於頻率轉換之影像壓縮整合平臺
頁籤選單縮合
題名 | Vector Quantization of Images with Codeword-Rotation Algorithm=向量量化影像壓縮旋轉編碼法 |
---|---|
作 者 | 瞿忠正; 謝朝和; | 書刊名 | 中國工程學刊 |
卷期 | 21:4 1998.07[民87.07] |
頁次 | 頁389-397 |
分類號 | 312.9 |
關鍵詞 | 向量量化; 模糊C-均值法; LBG法; Vector quantization; Fuzzy C-means algorithm; LBG algorithm; |
語文 | 英文(English) |
中文摘要 | 本文提出應用於向量量化影像壓之旋轉編碼法,利用新的二元分類法將 影像資料依圖型特徵分成六大類,其中包含邊緣區塊與非邊緣區塊,各類區塊 利用模糊C--均值碼本訓練方法產生碼薄。邊緣區丟在訓練前先將相似的區塊 旋轉至相同的角度。此外,本文亦提出兩種編碼與解碼的新方法,與傳統利用 LBG方法所建立的基本向量量化系統比較,本文所提出的系統不但可減少所需 碼本的大小,而且所需的碼本運算時間亦可降低,更重要的是視覺的品質亦更 佳。 |
英文摘要 | A codeword-rotation algorithm is proposed for vector quantization (VQ) of images. A novel binary classifier is presented to preclassify the training vectors into six classes including edge blocks and nonedge blocks. The VQ codebook is generated by applying the modified Fuzzy C-Means (MFCM) algorithm to the training vectors of each class. Similar edge blocks are rotated and coalesced during the edge subcodebook generation process. Furthermore, two schemes for designing the encoder and decoder are also presented. Compared with the basic VQ system constructed by the LBG algorithm, the new method results in a considerable reduction in codebook size and computation time of codebook generation. More importantly, the visual quality achieved is better than the basic VQ system. |
本系統之摘要資訊系依該期刊論文摘要之資訊為主。