会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 1. 发明授权
    • Blur estimation
    • 模糊估计
    • US08494282B2
    • 2013-07-23
    • US12838857
    • 2010-07-19
    • Matthew D. GaubatzSteven J Simske
    • Matthew D. GaubatzSteven J Simske
    • G06K9/40G02B5/00G06K19/06
    • G06K7/1469G06K7/146G06T5/003G06T7/136G06T2207/20201G06T2207/30176
    • A method and apparatus for removing blur in an image is disclosed. The blur in the image is caused by relative motion between the imaging device and the object being imaged. A set of differences between the pixel values in the image is calculated. The set of differences in pixel values are divided into two groups, wherein the first group of differences in pixel values corresponds to differences in pixel values due to noise, and the second group of differences in pixel values corresponds to differences in pixel values due to noise and motion. An estimate of the motion blur is determined using the second group of differences in pixel values. The estimate of the blur is then used to remove the blur from an image.
    • 公开了一种用于去除图像中的模糊的方法和装置。 图像中的模糊是由成像装置和成像对象之间的相对运动引起的。 计算图像中像素值之间的一组差异。 像素值的差异集合被分成两组,其中像素值中的第一组差异对应于由于噪声引起的像素值差异,并且第二组像素值对应于由噪声引起的像素值差异 和运动。 使用像素值中的第二组差异来确定运动模糊的估计。 然后使用模糊的估计来从图像中去除模糊。
    • 9. 发明授权
    • Automatic redeye detection based on redeye and facial metric values
    • 基于红眼和面部度量值的自动红眼检测
    • US08446494B2
    • 2013-05-21
    • US12865855
    • 2008-02-01
    • Matthew D. GaubatzRobert Alan Ulichney
    • Matthew D. GaubatzRobert Alan Ulichney
    • H04N5/217
    • H04N1/62G06K9/00228G06K9/00604G06T7/90G06T2207/30216H04N1/624
    • Candidate redeye areas (24) are determined in an input image (20). In this process, a respective set of one or more redeye metric values (28) is associated with each of the candidate redeye areas (24). Candidate face areas (30) are ascertained in the input image (20). In this process, a respective set of one or more face metric values (34) is associated with each of the candidate face areas (30). A respective joint metric vector (78) is assigned to each of the candidate redeye areas (24). The joint metric vector (78) includes metric values that are derived from the respective set of redeye metric values (28) and the set of face metric values (34) associated with a selected one of the candidate face areas (30). Each of one or more of the candidate redeye areas (24) is classified as either a redeye artifact or a non-redeye artifact based on the respective joint metric vector (78) assigned to the candidate redeye area (24).
    • 在输入图像(20)中确定候选红眼区域(24)。 在该过程中,相应的一组一个或多个红眼度量值(28)与候选红眼区域(24)中的每一个相关联。 在输入图像(20)中确定候选面部区域(30)。 在该过程中,一组或多个面部度量值(34)与候选面部区域(30)中的每一个相关联。 各个联合度量矢量(78)被分配给每个候选红眼区域(24)。 联合度量矢量(78)包括从相应的红眼度量值集合(28)和与候选面部区域(30)中选择的一个相关联的面部度量值(34)的集合导出的度量值。 基于分配给候选红眼区域(24)的各个联合度量矢量(78),候选红眼区域(24)中的一个或多个被分类为红眼人造物或非红眼人造物。