根据行车标记确定感兴趣区域。
生长结果再经过后续处理最终得到感兴趣区域。
Then ROI can be extracted by region growing and the following treatment.
最后利用形态梯度的算法探测出感兴趣区域的边缘。
At last, the edges of ROIs are detected by using morphological grads.
提出了一种基于用户选择感兴趣区域的图像检索方法。
An image retrieval method based on user selected region of interest was proposed.
对感兴趣区域的提升位S，本文方法具有灵活的可调性。
The method proposed in the paper has flexible adjustability for the lifting bit S on ROI.
利用运动估计预测目标在下一帧的感兴趣区域，即跟踪窗。
Firstly the regions of interest which contained the target in the next frame, namely tracking windows, were predicted by motion estimator.
本文主要介绍感兴趣区域ROI编码技术的几种主要方法。
This text introduces several kinds of main methods of interested regional ROI code technology mainly.
提出了一种基于单调推进曲线进化的感兴趣区域提取新方法。
In this paper, an efficient approach to ROI extraction based on monotonically marching curve evolution is proposed.
本文提出了一种基于MPEG 4的感兴趣区域视频编码新方法。
首先利用运动估计预测目标在下一帧的感兴趣区域，也就是跟踪窗。
The regions of interest which contain the target in the next frame, namely tracking windows, are predicted by motion estimator.
感兴趣区域）作为新一代图像压缩标准JPEG2000所增加的一个功能。
ROI(Region Of Interest) method is a new function of JPEG2000. Applying ROI we can compress image with different accuracy in different region.
针对上述两者的缺点，文中提出了一种基于用户感兴趣区域的图像检索算法。
An image retrieval algorithm based on region-of-interest is proposed in this paper aiming at covering those two shortages.
同时，本文还就图像感兴趣区域掩膜生成的问题进行了一些总结和推广工作。
Furthermore, the paper summarizes and extends the problem of the generation of ROI mask.
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.
同时还将说明roi的掩模概念和计算，并实现ROI感兴趣区域图像的重建。
Will prove the mask concept and calculation of ROI even meanwhile, and it is interested in the reconstruction of the regional picture to realize ROI.
实验结果表明，该方法能较好地考虑感兴趣区域的重要性，更符合人的主观视觉质量。
Experimental results show that our model considers more about the importance of regions of interest and is more consistent with perceived image quality.
最后，将感兴趣区域比特位提升与SPIHT编码算法结合，完成了图像的压缩编码。
Finally, the bit lifting on ROI is combined with SPIHT algorithm, accomplishing the image coding.
图像分割是从输入图像中提取目标或感兴趣区域的过程，是目标检测和识别过程中的重要步骤。
Image segmentation is the process of detecting objects or interesting areas from input image, and it is an important step in object detection and recognition.
接着基于车辆的对称性特征，阴影和边缘特征对兴趣区域进行过滤，进一步缩小感兴趣区域；
Then filter the region of interest based on the symmetry, the shadow and the edge of the car and narrow the region of interest even more.
研究了等级树集分割编码方法(SPIHT)在任意形状感兴趣区域(ROI)编码中的应用。
The application of Set Partitioning in Hierarchical Trees (SPIHT) to the image coding of arbitrarily shaped Region of Interest (ROI) is investigated.
研究了基于整数到整数形状自适应离散小波变换对任意形状感兴趣区域的有损和无损编码技术。
Arbitrary shape region of interest lossily and losslessly coding technology based on integer-to-integer shape adaptive discrete wavelet transform has also been studied.
实验结果证明，该方法对于纹理较强的侧扫声纳图像中感兴趣区域（目标）的检测有较好的效果。
Results show that the method has a perfect performance for regions of interest (target) detection of side-scan sonar image with strong texture.
最后，在基于感兴趣区域的隐藏策略方面，本文提出了一种交互式的信息隐藏方法，并给出实验结果。
Finally the paper gives out a mutual hiding strategy, which is based on interested region.
该方法先在静态图像中分割出感兴趣区域，继而仅在感兴趣区域中应用变形的时间差分法来检测运动目标。
Those regions of interest are quickly segmented first and then a modified temporal differencing method is applied to detecting the moving objects.
实验结果表明，与平均码率分配算法相比，该算法可以显著降低视频图像中人眼感兴趣区域重建质量的波动。
The experimental results show that, compared with the conventional average rate allocation algorithm, the proposed algorithm can significantly eliminate the quality fluctuation of ROI.
为了既能满足人们对图像质量的要求，又能降低传输时间，节省存储空间，于是提出了感兴趣区域编码技术。
To meet people's demand for image quality and reduce transmission time and save memory space, region of interest coding is advanced.
首先通过交互式分割选择出感兴趣区域(ROI)，提取出roi的轮廓点并根据位置关系对轮廓点排序。
First, the region of interest (ROI) is selected by interactive segmentation method. The boundary points of the ROI is extracted and ordered according to their positions.
针对以往提供的各种方法都对一个感兴趣区域进行编码的缺点，提出了实现多个感兴趣区域的无损压缩的方法。
Concerning about the disadvantage of formerly provided each method all aimed at coding a Region of interest, a new approach was proposed to realize multiple ROIs coding.
图像分割是图像测量、识别和分析等研究的基础，它将感兴趣区域从图像中分离出来，便于对其作进一步处理。
Image segmentation is a foundation of image measurement, recognition and analysis. It divide image into different parts, find the region of interest and to facilitate further processing.
另外，对于特定的感兴趣区域，通过绘制草图线可以对曲线周围各顶点的曲率进行调整，构造显著的模型特征。
In addition, when a sketch line is drawn on a specified region of interest, it can create a remarkable feature with the curvature of vertices along the line tuned.
应用推荐