公开(公告)号：US06738513B1

公开(公告)日：2004-05-18

申请号：US09530174

申请日：2000-10-30

申请人： Gerd Binnig ,  Günter Schmidt ,  Martin Baatz ,  Richard Voss ,  Peter Eschenbacher

发明人： Gerd Binnig ,  Günter Schmidt ,  Martin Baatz ,  Richard Voss ,  Peter Eschenbacher

IPC分类号： G06K900

CPC分类号： G06K9/52 ,  G06T11/00

摘要： A method for fractal-darwinian object generation consists of the steps of: preparing a fractal object library including predetermined objects and associated rules of property and context, forming objects and comparing the formed objects with the objects in the fractal object library. By using the property rules, a local classification likelihood is allocated to each formed object. Thereupon, by using the context rules for each object, a respective fractal classification likelihood is formed. For optimisation of the fractal classification likelihood, alteration rules are applied to the objects. The above method is carried out iteratively, whereby a process of gradual optimisation takes place.

摘要翻译： 分形态对象生成的方法包括以下步骤：准备包括预定对象的分形对象库以及相关的属性和上下文规则，形成对象并将形成的对象与分形对象库中的对象进行比较。 通过使用属性规则，对每个形成的对象分配局部分类似然性。 因此，通过使用每个对象的上下文规则，形成相应的分形分类似然。 为了优化分形分类的可能性，将变更规则应用于对象。 上述方法被迭代地进行，由此进行逐渐优化的过程。

公开(公告)号：US06832002B2

公开(公告)日：2004-12-14

申请号：US09818299

申请日：2001-03-26

申请人： Martin Baatz ,  Gerd Binnig ,  Peter Eschenbacher ,  Andreas Melchinger ,  Michael Sogtrop

发明人： Martin Baatz ,  Gerd Binnig ,  Peter Eschenbacher ,  Andreas Melchinger ,  Michael Sogtrop

IPC分类号： G06K900

CPC分类号： G06T7/11 ,  G06T2207/10044 ,  G06T2207/10116

摘要： The present invention relates to a method for segmentation of a digital picture consisting of a multiplicity of single picture elements comprising determining if one of one and several features relating to contiguous picture objects comprising picture elements and picture segments are conforming or not conforming based on a specific homogeneity criterion by means of referencing a predetermined tolerance for each feature as a termination criterion, within which feature values relating to the contiguous picture objects in question may differ; if one of one feature and several features relating to the contiguous picture objects are determined to be conforming then merging the conforming picture objects; and repeating the resulting segmentation until the resulting segmentation converges in a stable or approximately stable condition in which no further contiguous picture objects are determined to be conforming.

摘要翻译： 本发明涉及一种用于分割由多个单个图像元素组成的数字图像的方法，包括确定与包括图像元素和图像片段的连续图像对象相关的一个和多个特征中的一个是否符合或不一致， 通过参考每个特征的预定公差作为终止标准，其中与所讨论的连续图像对象有关的特征值可以不同; 如果确定与邻接图像对象相关的一个特征和若干特征中的一个符合，则合并图像对象; 并重复所得到的分割，直到所得到的分割收敛于稳定或近似稳定的条件，其中没有进一步的连续图像对象被确定为符合。

公开(公告)号：US20060195407A1

公开(公告)日：2006-08-31

申请号：US11414000

申请日：2006-04-28

申请人： Maria Athelogou ,  Konstantinos Bobolas ,  Renate Binnig ,  Peter Eschenbacher ,  Guenter Schmidt

发明人： Maria Athelogou ,  Konstantinos Bobolas ,  Renate Binnig ,  Peter Eschenbacher ,  Guenter Schmidt

IPC分类号： G06F15/18

CPC分类号： G06N5/02 ,  Y10S707/99942

摘要： A computer-implemented network structure includes a semantic network machine comprised of nodes containing informational contents and links containing relational contents. Relational contents describe the relationship between linked nodes. Some of the nodes are semantic Janus units. Based on time-variable states of each semantic Janus unit, the semantic Janus units perform operations on nodes and links. The operations are focused on selected portions of the semantic network machine such that each semantic Janus unit need not deal with all possible informational and relational contents within the semantic network machine. The computational resources of the computer network are thereby efficiently managed, and artificial intelligence tasks such as inferential retrieval are performed quicker. The amount of data that is processed is substantially reduced by focusing on bundled information. The semantic network is used for pattern recognition, for example, to recognize blood vessels in a medical image or streets on a digital satellite image.

公开(公告)号：US07523079B2

公开(公告)日：2009-04-21

申请号：US11414000

申请日：2006-04-28

申请人： Maria Athelogou ,  Konstantinos Bobolas ,  Renate Binnig ,  Peter Eschenbacher ,  Guenter Schmidt

发明人： Maria Athelogou ,  Konstantinos Bobolas ,  Renate Binnig ,  Peter Eschenbacher ,  Guenter Schmidt

IPC分类号： G06F15/18

CPC分类号： G06N5/02 ,  Y10S707/99942

摘要： A computer-implemented network structure includes a semantic network machine comprised of nodes containing informational contents and links containing relational contents. Relational contents describe the relationship between linked nodes. Some of the nodes are semantic Janus units. Based on time-variable states of each semantic Janus unit, the semantic Janus units perform operations on nodes and links. The operations are focused on selected portions of the semantic network machine such that each semantic Janus unit need not deal with all possible informational and relational contents within the semantic network machine. The computational resources of the computer network are thereby efficiently managed, and artificial intelligence tasks such as inferential retrieval are performed quicker. The amount of data that is processed is substantially reduced by focusing on bundled information. The semantic network is used for pattern recognition, for example, to recognize blood vessels in a medical image or streets on a digital satellite image.

摘要翻译： 计算机实现的网络结构包括由包含信息内容的节点和包含关系内容的链接组成的语义网络机器。 关系内容描述链接节点之间的关系。 一些节点是语义Janus单元。 基于每个语义Janus单元的时变状态，语义Janus单元对节点和链路执行操作。 这些操作集中在语义网络机器的选定部分，使得每个语义的Janus单元不需要处理语义网络机器内的所有可能的信息和关系内容。 从而有效地管理计算机网络的计算资源，更快地执行诸如推理检索的人工智能任务。 通过关注捆绑的信息，大大减少了处理的数据量。 语义网络用于模式识别，例如，识别医学图像中的血管或数字卫星图像上的街道。