首页>
外国专利>
Generalized neighborhoods parameter transform for image features extraction
Generalized neighborhoods parameter transform for image features extraction
展开▼
机译：用于图像特征提取的广义邻域参数变换
展开▼
页面导航
摘要
著录项
相似文献
摘要
Geometric features in image data are extracted by correlation of local information contained in multiple neighborhoods or windows comprising the image. Features of interest are extracted from data contained in the neighborhoods. Nodes are created for each feature. Support values are assigned to each node as well as a list of neighborhoods containing the feature parameters. Inhibitory links are built between the nodes based upon the list of neighborhoods and the geometric properties of the feature. Competitive integration is performed until the surviving nodes are no longer connected by inhibitory links. The result is a complete segmentation of the image in terms of the features.
展开▼
