Information processing device, information processing method and recording medium

    公开(公告)号:US11100677B2

    公开(公告)日:2021-08-24

    申请号:US16647696

    申请日:2018-09-14

    Inventor: Takashi Shibata

    Abstract: The disclosure is an information processing device including: a memory; and at least one processor coupled to the memory and performing operations. The operations includes: generating, based on a target image including a target and a standard image not including the target, a target structure image indicating a shape feature of an object included in the target image and a standard structure image indicating a shape feature of an object included in the standard image, in each of a plurality of imaging conditions; calculating an individual difference being a difference between the target structure image and the standard structure image, and a composite difference based on the individual differences; calculating an individual smoothness being a smoothness of the target structure image, and a composite smoothness based on the individual smoothness; and generating a silhouette image of the target, based on the composite difference and the composite smoothness.

    Image compositing system, image compositing method, and image compositing program recording medium

    公开(公告)号:US10943339B2

    公开(公告)日:2021-03-09

    申请号:US16344214

    申请日:2017-10-26

    Abstract: The present invention enables a high-quality filtered image to be generated even from multimodal and multispectral images containing positional deviations. An image perturbation part generates a perturbed guide image group comprising first to K-th perturbed guide images obtained by deforming a guide image. A filtering part generates a filtered image group comprising first to K-th filtered images by applying first to K-th filtering processing to a target image by using the perturbed guide image group. A reliability calculation part calculates a reliability group comprising first to K-th reliabilities for the first to K-th filtered images of the filtered image group on the basis of first to K-th correlation values between the first to K-th perturbed guide images and the target image. A weight optimization part generates, on the basis of the first to K-th reliabilities, a weight group comprising first to K-th weights to be respectively used when compositing the first to K-th filtered images. An output image compositing part composites an output image from the weight group and the filtered image group.

    Information processing device, information processing apparatus, information processing method, and program
    15.
    发明授权
    Information processing device, information processing apparatus, information processing method, and program 有权
    信息处理装置,信息处理装置,信息处理方法和程序

    公开(公告)号:US09547913B2

    公开(公告)日:2017-01-17

    申请号:US14845462

    申请日:2015-09-04

    Inventor: Takashi Shibata

    Abstract: An information processing device, apparatus, method and non-transitory computer-readable storage medium are disclosed. An information processing device may include a memory storing instructions, and at least one processor configured to process the instructions to generate a comparison image by transforming a reference image, associate the comparison image with a class variable representing an object included in the reference image, calculate a degree of difference between an input patch which is an image representing a sub-region of an input image and a comparison patch which is an image representing a sub-region of the comparison image, estimate a displacement vector between the input patch and the comparison patch, calculate a first degree of reliability corresponding to the displacement vector and the class variable on the basis of the displacement vector and the degree of difference, calculate a second degree of reliability for each comparison patch on the basis of the first degree of reliability, and identify the object is represented by the class variable associated with the comparison image including the comparison patch whose second degree of reliability is greater than a predetermined threshold value, as a recognition target.

    Abstract translation: 公开了一种信息处理设备,设备,方法和非暂时性计算机可读存储介质。 信息处理装置可以包括存储指令的存储器,以及至少一个处理器,被配置为通过变换参考图像来处理指令以生成比较图像,将比较图像与表示参考图像中包括的对象的类变量相关联,计算 作为表示输入图像的子区域的图像的输入贴片与作为表示比较图像的子区域的图像的比较贴片之间的差异程度,估计输入贴片和比较之间的位移矢量 基于位移矢量和差异度计算与位移矢量和类变量相对应的第一可靠度,基于第一可靠度计算每个比较片的第二可靠度, 并且识别对象由与比较图像相关联的类变量包括 将第二可靠度大于预定阈值的比较补丁作为识别目标。

    Image processing device, image processing method and medium
    16.
    发明授权
    Image processing device, image processing method and medium 有权
    图像处理装置,图像处理方法和介质

    公开(公告)号:US09542725B2

    公开(公告)日:2017-01-10

    申请号:US14647531

    申请日:2013-11-28

    CPC classification number: G06T3/4053 H04N1/407

    Abstract: An image processing device according to the present invention includes: a weight calculation unit that determines an area where a feature value of an input image is saved, based on a gradient of a feature value of a pixel of the input image and a direction of the gradient, and calculates a weight for reducing a regularization constraint that is a constraint based on regularization of image processing in the area where the feature value is saved; a regularization term calculation unit that calculates a regularization constraint of a high resolution image restored based on the input image by using the weight; a reconstruction constraint calculation unit that calculates a reconstruction constraint that is a constraint based on reconstruction of the high resolution image; and an image restoring unit that restores the high resolution image from the input image based on the regularization constraint and the reconstruction constraint.

    Abstract translation: 根据本发明的图像处理装置包括:权重计算单元,其基于输入图像的像素的特征值的梯度和所述输入图像的方向来确定输入图像的特征值被保存的区域 并且计算用于减少作为基于在保存特征值的区域中的图像处理的正则化的约束的正则化约束的权重; 正则化项计算单元,其通过使用所述权重来计算基于所述输入图像而恢复的高分辨率图像的正则化约束; 重建约束计算单元,其基于所述高分辨率图像的重建来计算作为约束的重建约束; 以及图像恢复单元,其基于正则化约束和重建约束从输入图像恢复高分辨率图像。

    Surface property estimation system
    18.
    发明授权

    公开(公告)号:US12196545B2

    公开(公告)日:2025-01-14

    申请号:US17764697

    申请日:2019-10-04

    Abstract: A surface property estimation system includes an image acquisition means for acquiring an image of a surface of an object, an estimation means for estimating a surface property from the acquired image by using an estimation model obtained through machine learning with use of an image of a surface of an object and a surface property shown by the image as training data, an extraction means for extracting, from the acquired image, a feature amount unique to the image, and a registration means for storing the estimated surface property and the extracted feature amount in a storage means in association with each other.

Patent Agency Ranking