传统上，用计算机进行人脸识别是基于局部区域的特征例如眼睛、鼻子的形状，或者嘴巴宽度等。
Traditionally, computer face recognition is based on such factors as the characteristics of the eye region, the shape of the nose, or the width of the mouth.
这样可以识别在项目整个运行时间中覆盖较少范围的区域，可以显示测试的什么位置需要按行展开有代码变更和增添新特征的区域。
This can identify areas of the project that achieve less coverage over time, to show where testing needs to expand in line with code changes and added features.
对于海面图像，分别采用感兴趣舰船目标区域的方差值、目标和背景亮度对比度这两个特征对目标进行融合识别。
As to sea image, the variance feature of region of interest and the luminance contrast feature between target and background are used to fusion recognition.
方法中采用基于类椭圆边缘属性对特征区域进行自动识别，采用最小二乘椭圆拟合精确求取类椭圆亚像素定位中心。
In the method, the automatic identification of feature area is fulfilled based on the edge attribute, and the sub-pixel center location is accomplished with the least-square approach.
文中提出了利用人脸面部几何特征地理区域分布的差异性进行人脸识别的新方法。
In this paper a new method about face recognition is presented based on the regional distribution of facial geometric feature in China.
感兴趣区域定位是提取目标特征，进行目标识别与跟踪等后续处理的重要基础。
Detecting regions of interest(ROIs) is the base step for object's feature extraction, identification and tracking.
以自适应门限值提取前景区域，通过扩展的连通分量提取算法实现了目标的快速搜索，最后几何特征对目标加以识别。
Foreground area is extracted by adaptive threshold method, the object is searched by extending the connected components extraction method, the object is recognized based on the geometrical character.
最后用基于连通域特征值的方法进行区域识别。
Region recognition approach is based on connected component features.
然后，利用跑道边缘的平行直线特征和跑道边缘与可能机场区域的重叠关系识别出军用机场。
Then, the recognition is achieved based on geometry characteristics of the airport, such as the paralleled edges of runway, the superposing location between the edges of runway and the airport region.
当跑道区域面积超过一定阈值时，通过采用搜索跑道边缘特征灯光的方法来识别跑道，准确性较高。
While the area of runway is big, the runway is recognized by the method of searching characteristic light of runway boundary.
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。
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.
在区域分割与边界跟踪基础上，对卫星图像进行水体形状特征的抽取与描述，实现不同水体类型的识别。
The experiments of the recognition of various types of water bodies on the satellite image prove this recognizing method is feasible with high spatial resolution satellite images.
然后采用区域统计、参数识别、噪声区域去除以及聚类分析等手段进行目标特征识别，提取出棒材的质心点坐标作为特征；
Object centroid as the features was computed by means of regional statistics, parameter recognition, noise region removal and cluster analysis.
最终识别结果是：图像中目标区域的40个特征组合可以达到较高的识别概率，而阴影区域的40个特征组合的识别概率比较低。
The recognition results show that 40 features are effective on the target region and is not useful on the shadow region.
然后利用图像分析技术，采用基于边缘的图像分割方法，提取图像的主体区域并进行视觉特征提取与（分类）识别。
Then we use the technology of image analysis and image division based on the edge to extract the main object and to recognize (classify) the visual characteristic.
提出了一种基于分段轮廓平滑的目标识别算法。首先通过曲率将轮廓划分为特征区域和非特征区域；
An object recognition algorithm based on segmented-smoothing contour is proposed. The contour is divided into two kinds of zones by curvature:feature zones and non-feature zones.
轮廓与边界定义了目标的外表形状，确定了区域之间的分界线，它们是人类与计算机进行目标识别的重要特征。
Contours and boundaries that define object shape and indicate outer limits for regions. They are critical for human or computer recognition of objects.
在身份识别这一部分，首先构建客户眼睛周边区域的生物特征数据库用于进行身份验证。在身份验证阶段使用了施瓦茨不等式算法和误差平方和（SSE）算法。
In the person identification part, we construct databases of biometrical features around the eye area of clients and, for authentication, Schwartz inequality and the sum square error (SSE) are used.
本文针对空间目标旋转、尺度、视点及亮度变化等问题，提出了一种基于特征区域的空间有形目标识别方法。
This paper proposes a new approach for finding expressive and geometrically invariant parts for recognizing space visible targets.
本文针对空间目标旋转、尺度、视点及亮度变化等问题，提出了一种基于特征区域的空间有形目标识别方法。
This paper proposes a new approach for finding expressive and geometrically invariant parts for recognizing space visible targets.
应用推荐