该方法将图像投影到SVDQ的各个正交基上,得到投影系数向量。将此向量作为图像的代数特征并用于彩色图像识别中。
Firstly, the image is projected on to the orthogonal basis of SVDQ, then the projection coefficient vector is used as algebraic feature of image and applied to recognition.
本文研究了多层感知器、径向基函数网络、学习向量量化网络和自组织特征映射网络等四种神经网络在回转窑火焰图像分割中的应用。
In this paper, four neural networks, i. e. multi layer perception, radial basis function, learning vector quantization and self organizing feature mapping, are used to segment the flame image.
将信号样本进行小波包变换,并选择最好基,计算各子频带的平均能量,得到14维特征向量。
Signal sample is analyzed through wavelet packet theory, best base is chose, and the average energy of every sub frequency band is calculated, at last 14 links of characteristic vectors are get.
应用推荐