利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

161 条记录 (耗时 0.084 秒)

    IMAGE PROCESSING DEVICE, IMAGE PROCESSING METHOD, PROGRAM AND RECORDING MEDIUM
    11.
    发明申请
    IMAGE PROCESSING DEVICE, IMAGE PROCESSING METHOD, PROGRAM AND RECORDING MEDIUM 审中-公开
    图像处理装置，图像处理方法，程序和记录介质

    公开(公告)号：US20130016920A1

    公开(公告)日：2013-01-17

    申请号：US13543075

    申请日：2012-07-06

    申请人： Yasuhiro Matsuda ,  Takahiro Nagano ,  Masashi Uchida

    发明人： Yasuhiro Matsuda ,  Takahiro Nagano ,  Masashi Uchida

    IPC分类号： G06K9/32

    CPC分类号： G06T3/4053

    摘要： Provided is an image processing device including a model-based processing portion that generates an estimated low resolution image from a high resolution image, using an observation model that performs motion compensation processing and down-sampling processing, a feature amount calculation portion that calculates a feature amount of at least one of a spatial feature amount and a temporal feature amount from one of an observed low resolution image, which is a low resolution image that is actually observed, and the high resolution image, and a prediction operation portion that predicts and generates an image with higher image quality based on the high resolution image, using a parameter which corresponds to the calculated feature amount and which is obtained from the observed low resolution image, from the estimated low resolution image and from learning that is performed in advance.

    摘要翻译： 提供了一种图像处理装置，其特征量计算部分包括：基于模型的处理部分，其使用执行运动补偿处理和下采样处理的观察模型从高分辨率图像生成估计的低分辨率图像;特征量计算部分， 以及作为实际观察到的低分辨率图像的观察低分辨率图像和高分辨率图像之一的空间特征量和时间特征量中的至少一个的量和预测和生成的预测操作部分 基于高分辨率图像具有较高图像质量的图像，使用与所计算的特征量相对应的参数，并且从所观察到的低分辨率图像获得的参考值与所估计的低分辨率图像和预先执行的学习相对应。

    IMAGE PROCESSING APPARATUS AND METHOD, PROGRAM, AND RECORDING MEDIUM
    12.
    发明申请
    IMAGE PROCESSING APPARATUS AND METHOD, PROGRAM, AND RECORDING MEDIUM 审中-公开
    图像处理装置和方法，程序和记录介质

    公开(公告)号：US20120321214A1

    公开(公告)日：2012-12-20

    申请号：US13463274

    申请日：2012-05-03

    申请人： Kenichiro Hosokawa ,  Takahiro Nagano

    发明人： Kenichiro Hosokawa ,  Takahiro Nagano

    IPC分类号： G06K9/40

    CPC分类号： G06T5/003 ,  G06T3/4007 ,  G06T5/20 ,  G06T2207/20012

    摘要： Provided is an image processing apparatus including a sharpness improvement feature quantity calculation unit for calculating a sharpness improvement feature quantity of a pixel-of-interest, which is a feature quantity of sharpness improvement of a pixel-of-interest, according to a product-sum operation on pixel values of a plurality of peripheral pixels around a pixel of an input image corresponding to the pixel-of-interest, strengths of band limitation and noise addition, and filter coefficients corresponding to phases of the pixel-of-interest and the peripheral pixels, by designating a pixel of a prediction image as the pixel-of-interest when an image subjected to high image-quality processing is output as the prediction image, and a prediction calculation unit for calculating a prediction value of the pixel-of-interest by calculating a prediction expression defined by a product-sum operation on the sharpness improvement feature quantity and a prediction coefficient pre-obtained by learning.

    摘要翻译： 提供了一种图像处理装置，其包括：锐度改善特征量计算单元，用于根据产品特性量计算单元计算作为感兴趣像素的锐度改善的特征量的兴趣像素的锐度改善特征量; 对与感兴趣像素对应的输入图像的像素周围的多个周边像素的像素值进行和运算，频带限制和噪声添加的强度以及对应于感兴趣像素的相位的滤波器系数 周边像素，通过将输出高图像质量处理的图像作为预测图像输出，将预测图像的像素指定为感兴趣像素，以及预测计算单元，计算像素的像素的预测值 通过计算由锐积度改善特征量和预先获得的预测系数的乘积和运算定义的预测表达式来计算兴趣 学习。

    Learning device, learning method, and learning program
    13.
    发明授权
    Learning device, learning method, and learning program 失效
    学习设备，学习方法和学习方案

    公开(公告)号：US07940993B2

    公开(公告)日：2011-05-10

    申请号：US11722141

    申请日：2005-12-21

    申请人： Takahiro Nagano ,  Tetsujiro Kondo ,  Tsutomu Watanabe ,  Junichi Ishibashi ,  Hisakazu Shiraki ,  Naoki Fujiwara ,  Masanori Kanemaru ,  Shinichiro Kaneko ,  Yasuhiro Suto

    发明人： Takahiro Nagano ,  Tetsujiro Kondo ,  Tsutomu Watanabe ,  Junichi Ishibashi ,  Hisakazu Shiraki ,  Naoki Fujiwara ,  Masanori Kanemaru ,  Shinichiro Kaneko ,  Yasuhiro Suto

    IPC分类号： G06K9/40 ,  G06K9/00 ,  H04N5/228

    CPC分类号： H04N5/21 ,  H04N5/142 ,  H04N5/144

    摘要： A motion-setting section (61) sets a motion amount and a motion direction for obtaining processing coefficients. A student-image-generating section (62) generates student images obtained by adding a motion blur to a teacher image not only based on the set motion amount and the set motion direction but also by changing at least one of the motion amount and motion direction in a specific ratio and student images obtained by adding no motion blur to the teacher image. A prediction-tap-extracting section (64) extracts, in order to extract a main term that mainly contains component of the target pixel, at least a pixel value of pixel in the student image whose space position roughly agrees with space position of the target pixel in the teacher image. A processing-coefficient-generating section (65) generates processing coefficients for predicting the target pixels in the teacher images from the pixel values of extracted pixels based on a relationship between the pixels thus extracted and the target pixels in the teacher images. The processing coefficients that are suitable for any motion blur removing which is robust against any shift of the motion vector can be generated through learning.

    摘要翻译： 运动设定部（61）设定用于获得处理系数的运动量和运动方向。 学生图像生成部（62）生成不仅基于设定的运动量和设定的运动方向而将运动模糊添加到教师图像而获得的学生图像，而且通过改变运动量和运动方向中的至少一个 以特定比例和学生图像通过添加没有运动模糊获得的教师图像。 预测抽头部（64）为了提取主要包含目标像素的成分的主项，提取学生图像中的空间位置大致与目标的空间位置一致的像素的像素值 像素在老师的形象。 处理系数生成部（65）基于所提取的像素与教师图像中的目标像素之间的关系，从提取的像素的像素值生成用于预测教师图像中的目标像素的处理系数。 可以通过学习来产生适用于对运动矢量的任何移动而鲁棒的任何运动模糊去除的处理系数。

    Image processing device and method, recording medium, and program
    18.
    发明授权
    Image processing device and method, recording medium, and program 失效
    图像处理装置和方法，记录介质和程序

    公开(公告)号：US07561188B2

    公开(公告)日：2009-07-14

    申请号：US10545081

    申请日：2004-02-13

    申请人： Tetsujiro Kondo ,  Takahiro Nagano ,  Junichi Ishibashi ,  Takashi Sawao ,  Naoki Fujiwara ,  Seiji Wada ,  Toru Miyake

    发明人： Tetsujiro Kondo ,  Takahiro Nagano ,  Junichi Ishibashi ,  Takashi Sawao ,  Naoki Fujiwara ,  Seiji Wada ,  Toru Miyake

    IPC分类号： H04N5/228 ,  G06K9/40 ,  G06K9/36

    CPC分类号： G06K9/4609 ,  G06T1/00 ,  G06T7/12 ,  G06T7/66 ,  G06T7/74 ,  G06T7/77

    摘要： The present invention relates an image processing device and method, recording medium, and program. A simple-type angle detecting unit 901 simply detects the angle as continuity using correlation from an input image. A determining unit 902, based on the angle thus simply obtained, connects a switch 903 to a terminal 903a in the event the angle is closer to the horizontal direction or the vertical direction, and outputs the angle information simply detected to a regression-type angle detecting unit 904. The regression-type angle detecting unit 904 statistically detects and outputs the angle as continuity in a regression equation. On the other hand, in the event that the angle as continuity simply obtained is closer to 45 degrees, the determining unit 902 connects the switch 903 and a terminal 903b. At this time, a gradient-type angle detecting unit 905 detects and outputs the direction of continuity from the input image in a gradient equation. As a result, the angle as continuity may be detected more accurately.

    摘要翻译： 本发明涉及一种图像处理装置和方法，记录介质和程序。 简单型角度检测单元901使用来自输入图像的相关性简单地检测作为连续性的角度。 确定单元902基于如此简单地获得的角度，在角度更接近水平方向或垂直方向的情况下将开关903连接到端子903a，并将简单检测到的角度信息输出到回归型角度 回归型角度检测单元904统计地检测并输出角度作为回归方程中的连续性。 另一方面，在简单获得的连续角度接近45度的情况下，确定单元902连接开关903和端子903b。 此时，梯度型角度检测单元905在梯度方程中检测并输出来自输入图像的连续方向。 结果，可以更精确地检测作为连续性的角度。

    Image reading apparatus and method
    19.
    发明授权
    Image reading apparatus and method 失效
    图像读取装置及方法

    公开(公告)号：US07551328B2

    公开(公告)日：2009-06-23

    申请号：US10471344

    申请日：2003-01-08

    申请人： Tetsujiro Kondo ,  Takashi Sawao ,  Junichi Ishibashi ,  Takahiro Nagano ,  Naoki Fujiwara ,  Toru Miyake ,  Seiji Wada

    发明人： Tetsujiro Kondo ,  Takashi Sawao ,  Junichi Ishibashi ,  Takahiro Nagano ,  Naoki Fujiwara ,  Toru Miyake ,  Seiji Wada

    IPC分类号： H04N1/04

    CPC分类号： H04N1/191 ,  H04N1/028 ,  H04N1/1013

    摘要： The present invention enables image data with good S/N and high resolution to be obtained reliably in a short reading time. A CCD 102 is formed by arranging line sensors, in which detecting elements having a time integration effect are arranged in a direction orthogonal to a relative movement direction in which the CCD 102 moves relative to an original, in a plurality of columns in the relative movement direction. A signal processing unit 107 detects pixel components on the basis of a model for separating first pixel values obtained in a processing unit time by the CCD 102 into a plurality of the pixel components corresponding to detection positions of the object being detected, and generates second pixel values corresponding to the detection positions of the object being detected on the basis of the detected pixel components. The present invention is applicable to scanners.

    摘要翻译： 本发明能够在短的读取时间内可靠地获得具有良好S / N和高分辨率的图像数据。 通过布置线传感器形成CCD 102，其中具有时间积分效应的检测元件在与CCD 102相对于原稿移动的相对移动方向正交的方向上以相对运动的多列排列 方向。 信号处理单元107基于用于将由CCD 102在处理单元时间中获得的第一像素值分离成与被检测对象的检测位置相对应的多个像素分量的模型来检测像素分量，并且生成第二像素 基于检测到的像素分量对应于被检测物体的检测位置的值。 本发明适用于扫描仪。

    Image processing apparatus and method and image pickup apparatus
    20.
    发明授权
    Image processing apparatus and method and image pickup apparatus 失效
    图像处理装置和方法以及图像拾取装置

    公开(公告)号：US07511730B2

    公开(公告)日：2009-03-31

    申请号：US10362792

    申请日：2002-06-26

    申请人： Tetsujiro Kondo ,  Junichi Ishibashi ,  Takashi Sawao ,  Takahiro Nagano ,  Naoki Fujiwara ,  Toru Miyake ,  Seiji Wada

    发明人： Tetsujiro Kondo ,  Junichi Ishibashi ,  Takashi Sawao ,  Takahiro Nagano ,  Naoki Fujiwara ,  Toru Miyake ,  Seiji Wada

    IPC分类号： H04N13/00 ,  H04N15/00

    CPC分类号： H04N13/261 ,  H04N13/122 ,  H04N13/128 ,  H04N13/189 ,  H04N13/194 ,  H04N13/221 ,  H04N13/275 ,  H04N2013/0081 ,  H04N2013/0092

    摘要： A system to generate a three-dimensional image from a two-dimensional image in accordance with the mixture state of images. A foreground/background component image generator generates, from image data including a foreground area consisting of only foreground object components, a background area consisting of only background object components, and a mixed area in which the foreground object components and the background object components are mixed, a foreground component image consisting of only the foreground object components and a background component image consisting of only the background object components. A foreground-parallax-image generator generates a right-eye foreground parallax image by adding the parallax to the foreground component image, and also generates a left-eye foreground parallax image by adding the parallax to the foreground component image. A synthesizer generates a right-eye parallax image by combining the right-eye foreground parallax image with a background image, and a synthesizer generates a left-eye parallax image by combining the left-eye foreground parallax image with the background image.

    摘要翻译： 根据图像的混合状态从二维图像生成三维图像的系统。 前景/背景分量图像生成器从包括仅前景对象分量的前景区域，仅由背景对象分量构成的背景区域和混合前景对象分量和背景对象分量的混合区域的图像数据生成 ，仅由前景对象分量组成的前景分量图像和仅由背景对象分量组成的背景分量图像。 前景视差图像生成器通过将视差加到前景分量图像来产生右眼前景视差图像，并且还通过将视差加到前景分量图像来产生左眼前景视差图像。 合成器通过将右眼前景视差图像与背景图像组合来生成右眼视差图像，并且合成器通过将左眼前景视差图像与背景图像组合来生成左眼视差图像。