it adopts k-means clustering methods to divide image pixels into three categories and extract regions of interest of image according to color clustering index generate regional segmentation map and the combination of saliency map and regional segmentation map.

the value of each pixel in an image is represented as a quaternion composed of intensity, color and motion feature, and its phase spectrum is used to calculate the spatio-temporal saliency map.

把一幅图像每个像素的值用四元数表示，并利用其傅立叶相位谱来获得时空显著图。

互联网摘选

the method overcomes the drawbacks existing in the original rules to generate saliency map and improves the color salient feature. then the accurate face detection is carried out by use of snow classifier.

然后，对生成显著图的各个特征结合规则进行了优化，改进其中的颜色显著特征提取方式，利用SNoW人脸检测算法在所生成的显著区域进行人脸位置的精确检测。

互联网摘选

considering the saliency map of an image as a feature descriptor, we combine the saliency feature and the gist feature together to describe the airport region.

我们把显著性分析本身作为图像的一种特征，并结合主旨性特征来共同描述机场和非机场区域。

互联网摘选

then the texture image is highly relaxed according to this saliency map. in other words, the essential signals in the texture image are accordingly redistributed.

然后，根据模型重要性特征图，对纹理进行松弛操作，以重新分布图像中的信号信息。

互联网摘选

the experimental result is good enough. ( 4) based on saliency map extracted, we proposed a method to obtain region of interest.

在显著图提取的基础上，提出一种感兴趣区域获取方法。

互联网摘选

these methods use the significance of saliency map and shift rule of focus obtained from visual attention model in the process of detecting.

该方法利用视觉注意模型生成的显著图的显著性信息和注意焦点的转移进行目标检测。

互联网摘选

after that, target detection is completed when the saliency map is segmented using a simple and convenient threshold method.

之后对显著图进行简便的阈值分割，完成目标探测。

互联网摘选

according to saliency map, an image can be divided into salient part and background part roughly.

根据显著特征图，图像可以大致分为显著特征区域和背景区域。

互联网摘选

beyond vision face feature extraction based on saliency map and the model of visual information processing

基于视觉显著性和视觉信息处理模型的特征提取方法

互联网摘选

the contrast prior and the proposed center prior are combined to compute an initial saliency map.

而后将对比度先验和新的中心先验结合来得到初始的显著图。

互联网摘选

we introduce a new evaluation criterion for saliency map.

提出了一个全新的显著图评价标准。

互联网摘选

Measurement of body fat percentage of college students and optimized selection of regressive equations

大学生体脂百分比测量及回归方程的优选

互联网摘选

Correlation analysis of body fat percentage, BMI and WHR: BMI was not the main factor that influenced the body fat percentage of college students, and it could result in more errors when estimating body fat percentage.

体脂百分比与身体质量指数、腰臀比的相关分析：身体质量指数不是决定体育专业大学生体脂百分比的主要因素，且对于体育专业学生误差较大。

互联网摘选

My body fat percentage is another matter.

我身体脂肪百分比是另外一件事件。

互联网摘选

Assorted regressive equations were established with body fat percentage as dependent variable, WHR and BMI as independent variables.

以腰臀比和身体质量指数作为自变量，建立以大学生体脂百分比为因变量的多种回归方程，然后进行筛选并检验信度。

互联网摘选

Establish teaching groups according to body fat percentage, and arrange the sports load and intensity for various groups according to their body fat amount, the teaching results improved clearly.

采用体脂百分率确定教学分组，并根据其体脂含量来安排不同组别的运动量与强度，教学效果有明显的提高。

互联网摘选

Results: 1. Body mass and body fat percentage of rats increased during the aging progress. Body fat percentage of rats markedly decreased after endurance training.

结果：1.增龄过程中，体重和体脂百分比增加；耐力训练对各年龄组体重影响较小，但可以显著降低大鼠体脂百分比。

互联网摘选

In this paper, 81 children were divided into obese, normal and thin group according to Body Fat Percentage ( BFP), PRL and thyroid hormone were determined to analyze the relationship of body composition and these two hormones.

按体脂百分比将81名8～12岁儿童分为肥胖组、正常组和消瘦组，并进行催乳素（PRL）、甲状腺素的测定，分析儿童体成分与两种激素之间的关系。

互联网摘选

The mean values of body fat percentage in each male and female groups tended to a range of the physical capacity status, it was 12.97% to 18.59% for males and 18.44% to 21.39% for females.

男女各组体脂百分比均值趋向最佳体力状况范围，男为12.97%～18.59%，女为18.44%～21.39%。

互联网摘选

Results Change in body weight and body fat percentage did not differ between the diet groups overall.

结果：体重和身体脂肪百分比在全部的不同的饮食组没有差异。

互联网摘选