Image generating apparatus generating reconstructed image, method, and computer-readable recording medium
    13.
    发明授权
    Image generating apparatus generating reconstructed image, method, and computer-readable recording medium 有权
    产生重构图像,方法和计算机可读记录介质的图像产生装置

    公开(公告)号:US09386297B2

    公开(公告)日:2016-07-05

    申请号:US13774952

    申请日:2013-02-22

    Abstract: A reconstructed image which further reflects the photo shooting information of a main object is generated. A layer determiner defines a layer of a reconstructed image. A layer image generator reconstructs an image of an object included in the allocated depth range from a light field image and the depth map of the light field image for each layer. A conversion pixel extractor extracts corresponding pixels on a conversion layer which corresponds to an object to be modified. The object to be modified is designated by an operation acquired by a modification operation acquirer. A reconstructed image generator converts layer images using a conversion matrix defined by a conversion matrix determiner and generates an image whose composition has been modified by superimposing the layer images.

    Abstract translation: 产生进一步反映主要对象的照片拍摄信息的重建图像。 层确定器定义重构图像的层。 层图像生成器从光场图像和每层的光场图像的深度图重建包含在所分配的深度范围中的对象的图像。 转换像素提取器提取对应于要修改的对象的转换层上的相应像素。 要修改的对象由通过修改操作获取器获取的操作来指定。 重建图像生成器使用由转换矩阵确定器定义的转换矩阵来转换层图像,并且通过叠加层图像生成其组合已被修改的图像。

    Voice recognition device and voice recognition method

    公开(公告)号:US10997979B2

    公开(公告)日:2021-05-04

    申请号:US16441348

    申请日:2019-06-14

    Abstract: A voice recognition device provided with a processor configured to determine a breathing period immediately before uttering which is a period in which a lip of a target person has moved with breathing immediately before uttering based on a captured image of the lip of the target person, to detect a voice period which is a period in which the target person is uttering without including the breathing period immediately before uttering determined above based on the captured image of the lip of the target person captured, to acquire a voice of the target person, and to recognize the voice of the target person based on the voice of the target person acquired above within the voice period detected above.

    Expression determination device, expression determination method, and recording medium

    公开(公告)号:US10713477B2

    公开(公告)日:2020-07-14

    申请号:US15989688

    申请日:2018-05-25

    Abstract: A determination result is easily obtained even in expression determination on a face image that is not a front view. A Robot includes a camera, a face detector, a face angle estimator, and an expression determiner. The camera acquires image data. The face detector detects a face of a person from the image data acquired by the camera. The face angle estimator estimates an angle of the face detected by the face detector. The expression determiner determines an expression of the face based on the angle estimated by the face angle estimator.

    Multi-class identifier, method, and computer-readable recording medium
    19.
    发明授权
    Multi-class identifier, method, and computer-readable recording medium 有权
    多类标识符,方法和计算机可读记录介质

    公开(公告)号:US09098775B2

    公开(公告)日:2015-08-04

    申请号:US13904911

    申请日:2013-05-29

    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。

    Image processing device that displays retrieved image similar to target image
    20.
    发明授权
    Image processing device that displays retrieved image similar to target image 有权
    显示与目标图像类似的检索图像的图像处理设备

    公开(公告)号:US08958634B2

    公开(公告)日:2015-02-17

    申请号:US13847673

    申请日:2013-03-20

    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。

Patent Agency Ranking