聯機識別演算法 的英文怎麼說

中文拼音 [liánjīzhìbiéyǎnsuànfǎ]
聯機識別演算法 英文
on-line identification algorithm
  • 聯 : Ⅰ動詞（聯結; 聯合） unite; join Ⅱ名詞（對聯） antithetical couplet
  • 機 : machineengine
  • 識 : 識Ⅰ動詞[書面語] （記） remember; commit to memory Ⅱ名詞1. [書面語] （記號） mark; sign 2. （姓氏） a surname
  • 別 : 別動詞[方言] （改變） change （sb. 's opinion）
  • 演 : 動詞1 （演變; 演化） develop; evolve 2 （發揮） deduce; elaborate 3 （依照程式練習或計算） drill;...
  • 算 : Ⅰ動詞1 （計算數目） calculate; reckon; compute; figure 2 （計算進去） include; count 3 （謀劃;計...
  • 法 : Ⅰ名詞1 （由國家制定或認可的行為規則的總稱） law 2 （方法; 方式） way; method; mode; means 3 （標...
  • 識別 : 1 （辯別; 辯認） discriminate; distinguish; discern; tell the difference; spot 2 [計算機] identif...
  1. Turbo codes represent the new code structures, which consist of pccc ( parallel serially convolutional code ) and sccc ( serially concatenated convolutional code ). in this paper, the background of turbo codes are firstly introduced, which includes the base principle of error correction code 、 block code and convolutional code ; the principle of turbo code and the iterative decoding is secondly expanded ; the key decoding algorithm : a revised map algorithm and iterative decoding theory are detailed ; then, a new turbo code structure : hccc ( hybrid concatenated convolutional code ) is presented, and the capacity of this code method is analyzed, the average capacity upper bound is derived ; at last, this code is simulated on awgn ( additive white gaussian noise ) channel and rayleigh fading channel

    本文首先介紹了turbo碼的背景知識，包括差錯控制的基本原理、分組碼和卷積碼；然後闡述了turbo碼的基本原理，包括turbo編譯碼器結構及迭代譯碼原理；較為詳細地描述了關鍵的譯碼演算法： ?種改進的最大后驗概率（ map ）譯碼演算法及迭代譯碼演算法；提出了一種新的turbo碼結構：混合turbo碼（混合級聯卷積碼） ；並用編碼性能聯合界分析方法對混合turbo碼進行了性能分析，得出了其平均性能上界；並在高斯白噪聲通道和瑞利衰落通道上分別作了一些應用研究及計算機模擬實驗。
  2. Structural matching is a main approach for on - line chinese character recognition. in order to reduce its great computational comple xity and improve its performance, people have been seeking for a way to guide the whole matching by the result of partial matching. in this paper, the authors prop osed 45 basic components from 3, 755 categories of the daily - used chinese charac ters to guide the stroke segment matching. because they always locate at either the beginning or the end of the stroke segment string, these components are easy to extract and separate from other parts of the character. besides, the reference templates of these components are dynamically extracted from the reference segmen tstring and dependent on the current matched character so that a more accurate matching is carried out. experiments show that the segment matching computation h as reduced almost 50 %. the approach is also enlightening for other similar object matching problem

    結構匹配是一種有效的聯機手寫漢寫識別方法，為了減少匹配運算，人們一直在尋求利用部分匹配的結果來引導整體匹配的方法.在特徵匹配與結構匹配綜合的基礎上，從3 . 755個一級國標漢字中提取出45個子結構，利用它們來引導結構匹配.由於這些子結構總出現在字首或字尾，因而對它們的檢測比較容易.同時，通過建立子結構活動模板及設計子結構動態抽取演算法，使得子結構匹配的準確度得到很大提高.實驗結構表明，該方法使結構匹配的運算量減少約50 % ，並對類似的物體識別問題有一定的啟發意義
  3. This thesis explains the necessity of the character recognition technology of the computer at first, describe the meaning in which the handwritten numeral discerns ; pretreatment technology of handwritten numeral recognition, including two value, line segmentation, word segmentation smooth, removing noising, standardization and thinning are discussed two value concretely discusses whole threshold value, some threshold value, dynamic threshold value and utilize space information to carry on threshold, which are several kinds of common method of choosing threshold value, especially utilize space information to carry on threshold value is describe in detail ; adopting to the foundation of thinning based on mathematics morphology, thinning algorithm of serials same and thinning algorithm of protecting shape are discussed ; afterwards, according to principle ' s diagram of the on - line character recognition, by analyzing the structure feature of the handwritten numeral, this thesis has proposed the online recognition te chnology of the free handwritten numeral based on the stroke feature and the online recognition technology of the free handwritten numeral based on the multistage classifying device. detail narrated noise removing, stroke characteristic definition and discernment, distance criterion of whole word match ; then under the foundation of handwritten numeral segmentation, off - line handwritten numeral recognition is researched. especially minimum distance classifying device, tree classifying device and adaptive resonance ( art ) network classifying device is discussed at the same time, believes degree analyses are introduced to integrate a lot of classifying devices ; at the end, the typical application of the handwritten numeral recognition was briefly narrated, its application in extensive data statistics, financial affairs, tax, finance and mail sorting have been explored

    二值化時對整體閾值二值化、局部閾值二值化、動態閾值二值化和利用空間信息進行閾值選取幾種常用的閾值選取方法進行討論，特別對利用空間信息進行閾值選取進行了詳細論述；在對通過對基於數學形態學的細化的基礎上，討論序貫同倫形態細化演算法和保形的快速形態細化演算法；然後依據聯機字元識別原理框圖，分析了手寫數字的結構特點，提出了基於筆劃特徵的任意手寫數字在線識別技術和基於多級分類器任意手寫數字在線識別技術，對其中涉及的筆劃識別前的噪聲處理、筆劃間特徵量的定義及識別、整字匹配的距離準則進行了詳細敘述；繼而在對手寫數字的分割的基礎下對脫機手寫數字識別進行了研究，對基於最小距離分類器字元識別、基於樹分類器的字元識別、基於自適應共振（ art ）網路的字元識別分別進行了詳細討論，並引入置信度分析將多個分類器進行了混合集成；最後簡單闡述了手寫數字識別的典型應用，對其在大規模數據統計、財務、稅務、金融及郵件分揀中的應用進行了探索。
  4. The integral structure of system are analyzed, and a scheme based on dsps processing board + mcu control board are put forward firstly, following design difficulties and relevant measures. every modules of dsps board are described in details, including chips selection, implementation manners choice, interface and time sequence match and etc. compared otsu single threshold segmentation with multi - threshold segmentations, the latter are preferred to perform the object identification in hardware designed by author. combined to like background rejection, morphology expansion and etc. steps, the paper gets the length of queue ; finally, a - b united control and area united control based on can bus are designed

    首先分析了系統的總體結構，提出了一種基於dsps處理板+單片機控制板的信號機實現方案；在此基礎上，重點介紹了處理板模塊化的硬體電路設計，其中考慮了晶元的選型、實現方式的選擇、工作機制、時序匹配等問題；之後，分析了otsu單閾值目標識別和多閾值目標識別的效果，重點選擇後者在硬體電路板內對圖像進行了目標識別的演算法處理，結合背景的剔除、形態學膨脹等幾個減小誤差的措施，對車輛排隊長度進行了較為精確的提取；最後在控制板上完成了干線a - b信號聯動控制和基於can總線的區域聯網控制的通訊方案設計。
  5. We show that our algorithm require only one scan, regardless of the database size, and during our algorithm working, there are no a good deal of frequent item - sets, which make our algorithm work excellent

    本演算法採取「隨機并行搜索」策略，快速識別出候選關聯規則，整個挖掘過程最後只需掃描數據庫一遍，也不需生成大量的頻繁項目集，從而提高關聯規則挖掘的總體性能。
  6. Sixth, low - order natural frequency has being obtained by the mode analysis experiment of machine tools, the dynamic parameters of combination surface jointed by bolts were identified by the synthesis of fea, optimal algorithm and harmonic response analysis

    6 .研究了如何利用由實驗模態分析測得整機的低階固有頻率，通過將有限元分析和優化演算法、諧波響應分析相結合的方法，完成螺栓聯接結合面的參數識別問題。
  7. A new kind of algorithm on parallel mechanism structural errors detection and modification

    一種並聯機構結構誤差識別與修正的新演算法
  8. Now, the segmentation algorithms that segment the continuous character mainly depend on the intercharacter space. if the intercharacter space doesn ’ t meet the condition in the segmentation algorithm, for example, exiting interconnection among strokes or radicals of the character, the segmentation algorithm will not work well

    現有的分割演算法大多是依賴于字元之間的空間分離性，能否正確分割就決定於書寫時字元之間的間隔能否滿足分割演算法的要求，因此現有的聯機識別系統大多對于字元之間具有粘連或分離的情況會分割失敗或存在過切分。
  9. In chapter 2, several feature extraction methods are discussed. one of these discussions is focused on corner point detection, a new effective detection algorithm is proposed, and compared with the traditional ways in experiments. besides, a set of definitions of the features used in on - line recognition is also given, together with the relational algorithms

    第二章對聯機識別中的特徵提取方法進行了研究，首先對經典的幾種特徵點檢測演算法進行了討論，分析了其優勢和不足之處，在此基礎上提出了一種新的檢測方法，並與經典演算法進行了實驗比較，驗證了該演算法的性能；然後，給出了幾種用於聯機圖形識別的特徵定義，並對其中的幾種定義給出了相應的演算法。
分享友人
分享到 Line

分享到臉書