Aim a novel method for three-dimensional (3-d) object rotation-invariant recognition is proposed.
目的提出一种对三维物体进行旋转不变识别的新方法。
Establishing affine invariant similarity measure of shapes is one of the basic problems in pattern recognition, computer vision and image understanding domains.
建立仿射不变的形状相似性度量是模式识别、计算机视觉和图象理解领域中的基本问题之一。
Extracting or construction of the invariant features is one of the key technologies in the field of pattern recognition and computer vision.
图像不变量特征的提取与构造是模式识别和计算机视觉领域中的关键技术之一。
Invariant corner features are often used in pattern recognition.
拐点特征是模式识别中经常用到的一类不变量。
Invariant corner detection is a most important preprocessing step for image shape classification and recognition.
在图像形态分类与识别系统中，不变性角点检测是很重要的预处理环节。
Then according to the properties of discrete Fourier transform, it deduces the discrete Fourier invariant features that are employed on facial image recognition.
依据离散傅里叶变换性质，推导出离散傅里叶变换的不变特征，并将其用于人脸图像识别。
A face recognition method based on discrete Fourier invariant features is presented.
给出了一种基于离散傅里叶不变特征的人脸识别方法。
We propose a multistage SAR target recognition process based on target detection, target segmentation, target aspect estimation and invariant feature extraction.
提出一种以目标检测、目标分割、目标方位角估计和目标不变性特征提取为线索的SAR目标识别框架。
By the analysis and comparison of target characteristics, invariant moments are chosen as recognition characteristics.
通过对目标特征的分析比较，选取不变矩作为识别特征。
Translation invariant lies at the heart of many image processing and pattern recognition.
平移不变性在图像处理和模式识别等应用中具有十分重要的意义。
By this filter, the shift, scale and rotation invariant optical pattern recognition was realized with a high signal noise ratio of correlation output.
用这种滤波器实现了平移、旋转、尺度三重不变光学图像识别，且有较高的信噪比。
Invariant moments are important measure in the pattern recognition. Invariant moments are independent of position, scale and orientation.
不变矩是模式识别中的一种重要方法，它具有平移不变性、比例不变性和旋转不变性等优点。
The existing approaches to invariant two dimensional pattern recognition are useless when the pattern is blurred.
现存的基于不变特征的二维模式识别方法在目标被模糊了的情况下都无法精确识别。
It is an effective method to use the invariant moment features for target recognition.
利用图像的不变矩特征进行目标识别是一种有效的方法。
Extraction of invariant moments used for pattern recognition is a subject in optics to be further studied.
提取用于模式识别的不变矩特征量在光学上始终是一个有待进一步研究的问题。
Those salient regions are represented by 3 invariant features of gradient orientation, moment and canonical hue. They are used for scene recognition in terms of their match ratio.
对场景图像中的显著区域采用梯度方向、二阶不变矩、归一化色调3种特征进行不变性表示，并根据其匹配率实现场景识别。
The experimental results are perfect and show that improved moment invariant can satisfied the stored-grain microbe′s recognition.
实验取得理想结果，说明改进的形状不变矩能够满足储粮微生物识别要求。
A 2d object recognition algorithm based on geometry invariant and BP Network.
提出了一种基于几何不变性和BP网络的二维目标识别算法。
The algorithm can adapt to object recognition, invariant not only under rotation? Scaling? Translation, but under affine and projective transformation.
算法不仅能适应目标物体在旋转、缩放、平移变换下的不变性识别。而且能适应仿射及射影变换下的不变性识别。
The topological properties for translation, rotation and scale is invariant pattern recognition.
拓扑性质具有对图形的平移、伸缩、旋转的不变性。
In this paper a method of the three-dimensional object recognition with rotation-invariant based on moire fringe is proposed.
本文提出一种基于莫尔条纹的三维物体旋转不变识别方法。
Experimental result shows that the algorithm is invariant to rotations and robust to outliers and nonlinear problems, and it has higher correct recognition rate.
实验结果表明，该算法具有旋转不变性，对异常值和非线性问题具有稳定性，且正确识别率较高。
Based on their method, we suggest a new filter design for space-invariant and rotation-invariant in a given Angle range pattern recognition system.
本文在他们的基础上提出一种实现空间平移不变和在一定的角度范围内转动不变的特征识别方法，给出相应的滤波器设计具体公式。
For geometric invariance of the invariant moment, it has been used in pattern recognition, computer vision and image reconstruction.
不变矩的几何变换不变性特点，使其在模式识别、计算机视觉和图像重构中被广泛使用。
In this article Invariant Theory is used in the image recognition to resolve the image distortions problems.
为解决此类问题，本文将不变量理论应用于目标识别中，以解决因目标移动造成的失真问题。
Focus on this problem, a detection method of space small targets is presented based on moment invariant which is a concept of pattern recognition.
针对该问题，引入模式识别中的不变矩概念，提出基于不变矩的空间小目标检测方法。
Moreover, by extracting shape invariant moment characteristics of object region, this paper also presents a BP neural network based object recognition method.
对分割后的目标，提取不变矩特征，然后利用人工神经网络实现了运动目标的快速识别。
SIFT has proved to be the most robust local invariant feature descriptor in object recognition and matching.
目前，SIFT已经被证明鲁棒性最好的局部不变特征描述符。
Experiments show that the algorithm has high correct recognition ra (?) IO, and is invariant to translation, rotation and scale.
实验证明，本文方法具有较高的识别率，且该算法是平移、旋转和比例变化不变的。
The recognition of object figure is by invariant moments.
目标图像的形状识别采用基于图形的不变矩理论。
应用推荐