feature detector 中文意思是什麼
feature detector
解釋
特徵檢測器-
The concept of irradiance signal - to - noise ratio ( snr ) on the target plane and the minimum of the irradiance that can be detected by the detector was taken as the beginning, combined with a thorough analysis of the spectrum radiating feature of the target and the sky background, the atmosphere conditions, spectral filtering and the influence that the various components in the system have on the target irradiance on the detector ' s target plane and the background irradiance snr, the equation of the flying bomb ' s effect range affected by the point of burst measuring system is made, and all related factors that have an impact on the effect range are analyzed as well
從探測器靶面上輻照度信噪比的概念、探測器的可探測輻照度最小值出發，在詳細分析目標、天空背景的光譜輻射特性、大氣條件、光譜濾波技術以及系統各環節對探測器靶面上目標與背景輻照度信噪比的影響的基礎上，推導了炸點測量系統對爆炸的飛行彈體的作用距離方程，分析了影響作用距離的諸因素。 -
Perceptron as feature detector. visual receptive fields
做為特徵探測器的感應機。視覺的接受域。 -
3. the concept of feature fidelity is defined based on principal component analysis ( pca ) and an adaptive threshold based feature detector is then proposed, which takes no advantage of ad hoc knowledge including threshold, photography condition, experimental coefficients, etc., thus greatly expands the applications of facial feature detection technology
3 、提出基於自適應閾值分割的人臉特徵檢測方法和基於主分量分析的特徵真實性概念，將人臉特徵檢測方法建立在無先驗假設的基礎上，克服了現有方法中過分依賴先驗閾值、攝像條件或經驗參數的缺陷，極大擴展了人臉特徵檢測的應用范圍。 -
Experimental study on effect of microwave pulse - width on detector feature
微波脈寬對檢波器性能影響的實驗研究 -
In this paper, we present a multi - feature optimal fusion algorithm, inclusive of skin color, to detect one or multiple faces in color image with complex background. it is a hierarchical approach and integrates the skin color segmentation, face template matching and a neural network frontal face detector. with the elimination of false areas, the search area will become smaller and smaller, and the detection will be accomplished eventually
該演算法是一種層次式、由粗到精的檢測方法，按照「分割-搜索」的檢測模式，將膚色分割、平均臉模板匹配與神經網路驗證結合起來，採取逐步排除的方法，一步一步縮小搜索區域，實現彩色圖像中單個或多個正面端正人臉的檢測與定位。 -
In this thesis a vision model consist of cellular neural network as feature detector and bp network as classifier is proposed, and experiments are described where genetic algorithm is used to evolve an optimal feature detector in order to aid a classifier to generalize across different conditions. application of cellular neural network to image filtering is also studied
論文研究了虛擬生物的視覺建模問題，用細胞神經網路cnn來進行視網膜圖象特徵提取，通過遺傳演算法進化cnn模板，實現特徵提取的優化，從而提高了分類器的泛化能力和識別效果，為生成基於視覺的自適應行為提出了一個新的方法。 -
This method takes the second generation wavelet transformation as a base, using the interrelation between transformation sample and adjacent sample to detect partial feature of the signal, and according to the magnitude of related coefficient to define the optimal pre detector and re - newer of every sample in every dimension, so as to let the wavelet be able to suit fairly the partial feature of the signal
該方法以第二代小波變換為基礎，用變換樣本與相鄰樣本之間的相關性，來檢測信號的局部特徵，並根據相關系數的大小，來確定每一尺度上的每個樣本的最佳預測器和更新器，使小波能夠較好地適應信號的局部特徵。 -
We apply local entropy algorithm to the clutter tracking and detect clutter edge by local entropy filter. we also develop a new method to estimate fractal dimension from clutter surface for region segmentation. regarding the different results of clutter tracking as the background information, we propose clutter feature ( cf ) - cfar detector and structuring element ( se ) - cfar detector
然後針對這兩種不同的雜波跟蹤結果，提出分別採用雜被屬性恆虛警檢測器和結構元素恆虛警檢測器，以改善傳統雷達系統中僅採用單一恆虛警演算法造成的檢測性能低下。 -
Summarizing the development statement of monitoring technology for bridge, based on principle of pulse laser ranger detection and fiber - optic strain measurement, in view of the problem affected by single - chip inherent feature, integrating the goodness of cpld device and single - chip, using a / d converter to measure the count quantization error, a strain measurement system is worked out. the above system chiefly consists of light source, optic fiber sensor, photo detector and signal processing circuit
本文綜述了國內外橋梁監測技術的發展概況，在深入研究脈沖激光測距和光纖應變測試原理的基礎上，針對單片機固有計數頻率低、計數量化誤差大和延時不固定等不足，結合cpld計數頻率高、延時小而固定和單片機控制功能強的優勢，並採用模數轉換技術設計計數量化誤差測量電路，提出了基於激光脈沖時間測量法的光纖應變測量的方案。 -
The eyes can be considered as a salient and relatively stable feature of faces, so firstly eyes - analogue regions in cluttered images are segmented using local adaptive threshold edge detector. then the small eye - analogue regions are grouped together and labeled using a traditional labeling process according to their geometrical and color features. instead of finding potential eye - pairs from eye - analogue regions one by one, all possible pairs of eyes are encode as the solution, and the potential face are searched by gas
新意之處：利用膚色是一種感知現象的特性以及神經網路的強大感知、學習功能，採用進化神經網路對膚色進行感知和分類；以眼睛的幾何和周邊的膚色特徵分割眼睛塊，克服了在完整的膚色區域內檢測人臉方法的局限性；對候選眼睛對的編號而不是人臉在圖像中的位置、人臉的尺度和方向進行編碼，使遺傳演算法用於人臉定位時的問題空間得以大大簡化，採用一個新穎的眼睛及臉頰部位的灰度投影及膚色模板驗證，可以實現多尺度、任意方向的正面人臉檢測，實驗結果令人滿意。
分享友人