公开(公告)号：US20130322743A1

公开(公告)日：2013-12-05

申请号：US13904911

申请日：2013-05-29

Applicant: CASIO COMPUTER CO., LTD.

Inventor： Kazuhisa MATSUNAGA ,  Masayuki HIROHAMA ,  Kouichi NAKAGOME ,  Michihiro NIHEI

IPC: G06K9/62

CPC classification number: G06K9/6227 ,  G06K9/6256 ,  G06K9/6281

Abstract: A multi-class identifier identifies a kind of an imager, and identifies in detail with respect to a specified kind of a group. The multi-class identifier includes: an identification fault counter providing the image for test that includes any of class labels to the kind identifiers so that the kind identifiers individually identify the kind of the provided image, and counting, for a combination of arbitrary number of kinds among the plurality of kinds, the number of times of incorrect determination in the arbitrary number of kinds that belongs to the combination; a grouping processor, for a group of the combination for which count result is equal to or greater than a predetermined threshold, adding a group label corresponding to the group to the image for learning that includes the class label corresponding to any of the arbitrary number of kinds that belongs to the group.

Abstract translation: 多类标识符识别一种成像器，并且相对于指定类型的组来详细识别。 多类标识符包括：提供测试图像的识别故障计数器，其包括类型标识符的任何类别标签，以便种类标识符单独地识别所提供的图像的种类，并且对于任意数量的 多种种类，属于组合的任意种类的不正确确定次数; 分组处理器，对于其计数结果等于或大于预定阈值的组合组，将与该组相对应的组标签与用于学习的图像相加，所述组标签包括与任意数量 属于该组的种类。

公开(公告)号：US20140029806A1

公开(公告)日：2014-01-30

申请号：US13926835

申请日：2013-06-25

Applicant: CASIO COMPUTER CO., LTD.

Inventor： Michihiro NIHEI ,  Kazuhisa MATSUNAGA ,  Masayuki HIROHAMA ,  Kouichi NAKAGOME

IPC: G06T7/00

CPC classification number: G06T7/70 ,  G01C3/22 ,  H04N5/232 ,  H04N5/23287

Abstract: In an object searching apparatus for searching through a database of objects, an image pickup unit repeatedly shoots a subject with the optical axis moved to obtain plural pieces of image data. A distance from the image pickup unit to the subject is calculated based on the plural pieces of image data, and a main object of the subject is clipped from the obtained image data. A calculating unit calculates a real size of the main object of the subject based on a size of the clipped main object on the image data, the calculated distance from the image pickup unit to the subject and a focal length of the image pickup unit. A searching unit accesses the database to search for a sort of the main object of the subject, using the calculated real size of the main object.

Abstract translation: 在用于通过数据库搜索对象的对象搜索装置中，图像拾取单元重新拍摄光轴移动的对象以获得多个图像数据。 基于多个图像数据计算与图像拾取单元到被摄体的距离，并且从获得的图像数据中剪切被摄体的主要对象。 计算单元基于图像数据上的剪切主要对象的大小，从图像拾取单元到被摄体的计算距离和图像拾取单元的焦距来计算被摄体的主要对象的实际大小。 搜索单元使用所计算的主要对象的实际大小访问数据库以搜索主题的主要对象。

公开(公告)号：US20130251266A1

公开(公告)日：2013-09-26

申请号：US13831293

申请日：2013-03-14

Applicant: CASIO COMPUTER CO., LTD.

Inventor： Kouichi NAKAGOME ,  Masayuki HIROHAMA ,  Kazuhisa MATSUNAGA ,  Michihiro NIHEI

IPC: G06T1/60

CPC classification number: G06T1/60 ,  G06F17/30247 ,  G06K9/00657

Abstract: In the present invention, a database has feature information stored in association with flower sample images flower names, leaf sample images, and images indicating attention points for narrowing down the flower names. An extracting section extracts flower sample images having a high similarity to the image of the imaged flower as candidate images by comparing feature information of the image of the imaged flower and feature information stored in the database. A control section causes the image of the imaged flower, the extracted candidate images, flower names corresponding to the candidate images, and attention points for narrowing down the candidate images to be arranged and displayed on a display section, and changes the candidate images to their respective leaf sample images for display. The control section also changes the candidate images to images indicating their respective attention points and causes them to be displayed on the display section.

Abstract translation: 在本发明中，数据库具有与花样图像花名，叶示例图像和指示用于缩小花名称的注意点的图像相关联地存储的特征信息。 提取部通过比较成像花的图像的特征信息和存储在数据库中的特征信息，提取具有与成像花的图像相似度高的花样品图像作为候选图像。 控制部分使得成像的花的图像，所提取的候选图像，与候选图像相对应的花名，以及用于缩小待排列并显示在显示部上的候选图像的注意点，并将候选图像改变为它们 各叶片样本图像进行显示。 控制部分还将候选图像改变成指示其各自注意点的图像，并使它们显示在显示部分上。

公开(公告)号：US20140119646A1

公开(公告)日：2014-05-01

申请号：US14063311

申请日：2013-10-25

Applicant: CASIO COMPUTER CO., LTD.

Inventor： Kazuhisa MATSUNAGA ,  Kouichi NAKAGOME ,  Michihiro NIHEI ,  Masayuki HIROHAMA

IPC: G06K9/62

CPC classification number: G06K9/6281 ,  G06K9/6234 ,  G06K9/6256 ,  G06K9/6292

Abstract: A multi-class discriminating device for judging to which class a feature represented by data falls. The device has a first unit for generating plural first hierarchical discriminating devices for discriminating one from N, and a second unit for combining score values output respectively from the plural first hierarchical discriminating devices to generate a second hierarchical feature vector and for entering the second hierarchical feature vector to generate plural second hierarchical discriminating devices for discriminating one from N. When data is entered, the plural first hierarchical discriminating devices output score values, and these score values are combined together to generate the second hierarchical feature vector. When the second hierarchical feature vector is entered, the second hierarchical discriminating device which outputs the maximum score value is selected. The class corresponding to the selected second hierarchical discriminating device is discriminated as the class, into which the feature represented by the entered data falls.

Abstract translation: 一种用于判断由数据表示的特征属于哪个类的多类鉴别装置。 该装置具有第一单元，用于产生用于从N中识别的多个第一分级鉴别装置，以及用于组合分别从多个第一层次鉴别装置输出的分数值的第二单元，以产生第二分层特征向量，并用于输入第二分层特征 生成多个用于从N中识别的第二层次鉴别装置。当输入数据时，多个第一层次鉴别装置输出得分值，并将这些得分值组合在一起以产生第二层次特征向量。 当输入第二层次特征向量时，选择输出最大得分值的第二层次鉴别装置。 对应于所选择的第二层次鉴别装置的类别被鉴别为由输入的数据表示的特征落入的类别。

公开(公告)号：US20130251253A1

公开(公告)日：2013-09-26

申请号：US13847673

申请日：2013-03-20

Applicant: CASIO COMPUTER CO., LTD.

Inventor： Kouichi NAKAGOME ,  Shigeru KAFUKU ,  Kazuhisa MATSUNAGA ,  Michihiro NIHEI

IPC: G06F17/30

CPC classification number: G06F17/30247 ,  G06F17/3025 ,  G06F17/30259

Abstract: The image acquisition unit 41 acquires an image including an object. By comparing information related to the shape of a relevant natural object that is included as the object in the target image acquired by the image acquisition unit 41, and information related to respective shapes of a plurality of types prepared in advance, at least one flower type for the natural object in question is selected. The secondary selection unit 43 then selects data of a representative image from among data of a plurality of images of different color, of the same flower type as prepared in advance, for each of at least one flower type selected by the primary selection unit 42, based on information related to color of the relevant natural object included as the object in the image acquired by the image acquisition unit 41.

Abstract translation: 图像获取单元41获取包括对象的图像。 通过将与由图像获取单元41获取的目标图像中包括的作为对象的相关自然物体的形状相关的信息与预先准备的多种类型的各种形状相关的信息进行比较，至少一种花型 对于所讨论的自然对象是选择的。 次要选择单元43然后从由主要选择单元42选择的至少一种花型中的每一种，从与预先制作的相同花型的不同颜色的多个图像的数据中选择代表图像的数据， 基于与由图像获取单元41获取的图像中包括的对象相关的相关自然对象的颜色相关的信息。