发明名称 Information processing apparatus, processing method therefor, and non-transitory computer-readable storage medium
摘要 An information processing apparatus creates, for each of a plurality of nodes, a query to be executed for a learning pattern input to the node; inputs a plurality of learning patterns to a root node of the plurality of nodes; executes, for the learning pattern input to each node, the query created for the node; determines whether the query has been effectively executed for the individual learning pattern input to each node; distributes and inputs, to a lower node of each node, an individual learning pattern for which it has been determined in the determining that the query was effectively executed in the node; deletes a learning pattern for which it has been determined in the determining that the query was not effectively executed in each node; and stores an attribute of the learning pattern input to a terminal node of the plurality of nodes in association with the node.
申请公布号 US8930286(B2) 申请公布日期 2015.01.06
申请号 US201113281115 申请日期 2011.10.25
申请人 Canon Kabushiki Kaisha 发明人 Yoshii Hiroto
分类号 G06F15/18;G06N99/00 主分类号 G06F15/18
代理机构 Fitzpatrick, Cella, Harper & Scinto 代理人 Fitzpatrick, Cella, Harper & Scinto
主权项 1. An information processing apparatus which creates a classifier for classifying an attribute of a pattern image using a plurality of nodes consisting of a tree structure, comprising: an input unit configured to input a plurality of learning pattern images to each of the plurality of nodes, each of the plurality of learning pattern images including a target object; a selection unit configured to select, from each of the plurality of learning pattern images inputted to the node, at least one point; a determination unit configured to determine, for each of the plurality of learning pattern images inputted to the node, whether the selected point belongs to a region of the target object in the learning pattern image; a distribution unit configured to distribute and input, to a lower node of each node, a learning pattern image for which said determination unit has determined that the selected point belongs to the region; a deletion unit configured to delete a learning pattern image for which said determination unit has determined that the selected point does not belong to the region; and a storage unit configured to store an attribute of the learning pattern image input to a terminal node of the plurality of nodes in association with the node, wherein said selection unit selects, from each of the plurality of learning pattern images inputted to the node, a plurality of points, said determination unit determines, for each of the plurality of learning pattern images inputted to the node, whether a ratio of the selected plurality of points belonging to the region of the target object in the learning pattern image is larger than a threshold, said distribution unit distributes and inputs, to a lower node of each node, a learning pattern image for which said determination unit has determined that the ratio of the selected plurality of points belonging to the region of the target object in the learning pattern image is larger than the threshold, and said deletion unit deletes a learning pattern image for which said determination unit has determined that the ratio of the selected plurality of points belonging to the region of the target object in the learning pattern image is not larger than the threshold.
地址 Tokyo JP