本文的工作主要从以下四个方面展开：(1)图象边界的链码表示研究。
The main work in the thesis are as follows: (1) Research on the representation of image boundary using chain code.
介绍了一种综合利用图象力矩及图象边界提取等方法来实现对数字图象的大小归一化的算法。
Authors introduce a new algorithm which can normalize digital images with image moments and image edge detection.
实验结果表明，位错类型和颗粒边界图象清晰，又便于观察。
Experimental results indicate that dislocation patterns and grain boundaries are a clear bright image and easily observable.
从被噪声干扰的图象中提取边界是图象测试与分析的关键之一。
Detecting edge from noisy images is a key step for image test and analysis.
另一种模型是将图象颜色及其边界强度的联合分布集成到一个直方图中。
One model is presented to integrate both color distribution and detail signal energy into a single histogram.
提出宫颈癌细胞图象的数据采集，原始图象的平滑与边缘增强、分割与边界跟踪等处理方法。
Pressents a method for the data acquisition of cervical cancer cell image, the smooth, boundary enhancement, segmentation and edge track of original image.
该方法根据所给定的物体和边缘特征信息将原始医学图象转换到模糊连通空间，获得模糊边界。
When given characteristic information about the desired object and its edge, the new algorithm transformed the original images into fuzzy connective space and extracted their fuzzy boundary.
结果分割后的超声心脏图象具有光滑连续的边界，且心脏的各腔清晰、准确。
Result The segmented image had smooth continuous edges, few noises or speckles, and the contour of ventricle was clear and accurate.
针对边界部分有重叠的图象，提出了一种基于网格匹配的快速对准算法，并通过平滑因子对图象实现了无缝拼接。
In this paper, we present a fast stitching algorithm for the overlapping images based on grid matching, which makes images matching correctly, stitching images seamless and smooth.
本文研究与开发的面向对象计算流动显示系统分别由工具模块、边界条件设置模块、流场显示模块及光学图象模块构成。
The object-oriented visualization system developed in the thesis is made up of Tool Module, Boundary Condition Module, Flow Display Module and Optical Picture Module.
在数字图象或图形处理中，常用到边界填充技术。
In image and graphics processing, contour filling often is used.
提出一种基于小波变换的迭代正则化图象恢复算法，兼顾抑制噪声的增长和保留图象重要边界。
A wavelet based on iteration regularized image restoration algorithm is presented. Consideration is given to both the noise suppression and edge preservation.
对于以局部细节为目的的增强采用ANHE效果较好，而以已整幅图象的边界信息为目的的增强采用FFHE方法效果较好。
To enhance the edge of full image, which the full information must been taken into account, it is better to use FFHE metho…
编译程序（7）以空行为边界使原稿文本改页，将转移区设定在原稿文本中包含的图象的上端及下端。
The compiler (7) starts a new page when the compiler (7) finds a blank line in the original text and sets jump areas at the upper and lower ends of pictures contained in the text.
编译程序（7）以空行为边界使原稿文本改页，将转移区设定在原稿文本中包含的图象的上端及下端。
The compiler (7) starts a new page when the compiler (7) finds a blank line in the original text and sets jump areas at the upper and lower ends of pictures contained in the text.
应用推荐