Method and apparatus for image enhancement

    公开(公告)号:US09704227B2

    公开(公告)日:2017-07-11

    申请号:US14784281

    申请日:2014-07-28

    Abstract: Embodiments of the present invention relate to a method and apparatus for image enhancement. In particular, there is provided a method for image enhancement, the method comprising: estimating unsharpness of the image (S201-S204); determining a protection level of at least one pixel in the image based on the unsharpness (S205); and modifying a value of the at least one pixel to enhance the image, an amount of the modifying being determined at least in part based on the protection level (S206-S210). A corresponding apparatus and user device are disclosed. The invention may be applied to fog or haze removal from images or video without producing over-removal artifacts. In some embodiments, the invention may also be used to remove noise from low-light images.

    CLASSIFYING IMAGE SAMPLES
    4.
    发明申请
    CLASSIFYING IMAGE SAMPLES 审中-公开
    分类图像样本

    公开(公告)号:US20150243049A1

    公开(公告)日:2015-08-27

    申请号:US14431927

    申请日:2012-10-22

    Abstract: It is inter alia disclosed to classify samples of a set of samples of an image regarding whether or not a respective sample comprises optical information on a specific object type based on classification information. Therein, the classification information comprises a plurality of classifiers, each classifier being associated exclusively with one colour channel of a plurality of colour channels.

    Abstract translation: 公开的是对图像的一组样本的样本进行分类,以便相应的样本是否包括基于分类信息的特定对象类型的光学信息。 其中,分类信息包括多个分类器,每个分类器仅与多个颜色通道中的一个颜色通道相关联。

    METHOD AND APPARATUS FOR DETECTING IMAGING CONDITIONS

    公开(公告)号:US20170208234A1

    公开(公告)日:2017-07-20

    申请号:US15326630

    申请日:2015-07-03

    Abstract: Embodiments of the present invention relate to a method and apparatus for detecting an imaging condition. In one embodiment, there is provided a method for detecting an imaging condition. The method comprises: determining, based on luminance distribution in a first image of a scene, imaging lightness of the first image, the first image being captured by a first camera; determining, based on detection of a highlighted region in a second image of the scene, imaging exposureness of the second image, the second image being captured by a second camera, the first image and the second image being captured under a same or similar imaging condition, an exposure amount of the first camera being lower than an exposure amount of the second camera. There is also disclosed a relevant apparatus, electronic device, and a computer program product.

    Apparatus for Authenticating Pairing of Electronic Devices and Associated Methods
    6.
    发明申请
    Apparatus for Authenticating Pairing of Electronic Devices and Associated Methods 有权
    用于认证电子设备配对和相关方法的设备

    公开(公告)号:US20160149905A1

    公开(公告)日:2016-05-26

    申请号:US14903361

    申请日:2013-07-18

    Abstract: An apparatus comprising: a processor; and a memory including computer program code, the memory and the computer program code configured, with the processor, to cause the apparatus to perform at least the following: compare received biometric face vectors, wherein each received biometric face vector is received from a respective electronic device of a plurality of electronic devices and comprises one or more biometric face values determined from a respective image of a person captured by the corresponding electronic device; and provide for pairing authentication of the plurality of electronic devices if the comparison meets a predetermined similarity criterion.

    Abstract translation: 一种装置,包括:处理器; 以及存储器,包括与处理器配置的计算机程序代码,存储器和计算机程序代码,以使得设备至少执行以下操作:比较接收到的生物特征面向量,其中从相应的电子数据接收每个接收到的生物特征面向量 多个电子设备的设备,并且包括从由相应电子设备捕获的人的相应图像确定的一个或多个生物特征面值; 并且如果所述比较满足预定的相似性标准,则提供所述多个电子设备的配对认证。

    A METHOD AND TECHNICAL EQUIPMENT FOR PEOPLE IDENTIFICATION
    7.
    发明申请
    A METHOD AND TECHNICAL EQUIPMENT FOR PEOPLE IDENTIFICATION 审中-公开
    人类识别的方法和技术设备

    公开(公告)号:US20160063335A1

    公开(公告)日:2016-03-03

    申请号:US14783977

    申请日:2013-05-03

    Abstract: A method and a technical equipment for people identification. The method comprises detecting a person segment in video frames; extracting feature vector sets for several feature categories from the person segment; generating a person feature model of the extracted feature vectors sets; and transmitting the person feature model to a people identification model pool. The solution can provide more extensive people identification.

    Abstract translation: 人员识别的方法和技术设备。 该方法包括:在视频帧中检测人物段; 从人物段中提取几个要素类别的特征向量集; 生成所提取的特征向量集合的人物特征模型; 并将人特征模型发送到人员识别模型池。 该解决方案可以提供更广泛的人员识别。

    METHOD AND APPARATUS FOR PROCESSING A VIDEO FRAME IN A VIDEO FILE
    8.
    发明申请
    METHOD AND APPARATUS FOR PROCESSING A VIDEO FRAME IN A VIDEO FILE 有权
    在视频文件中处理视频帧的方法和装置

    公开(公告)号:US20150348276A1

    公开(公告)日:2015-12-03

    申请号:US14720074

    申请日:2015-05-22

    Abstract: The present invention provides a method and apparatus for processing a video frame in a video file, the method comprising: for each predetermined numerical value of one or more predetermined numerical values, comparing the video frame with a video frame spaced prior to the video frame by the predetermined numerical value of frames to obtain a first inter-frame difference; comparing the video frame with a video frame spaced after the video frame by the predetermined numerical value of frames to obtain a second inter-frame difference; and for each pixel of the video frame, obtaining a confidence map associating the video frame by the predetermined numerical value based on a smaller value of the first inter-frame difference and the second inter-frame difference; and determining, at least based on a value of each pixel in one or more of the confidence maps associated with a corresponding predetermined numerical value, whether the pixel belongs to a foreground.

    Abstract translation: 本发明提供了一种用于处理视频文件中的视频帧的方法和装置,该方法包括:对于一个或多个预定数值的每个预定数值,将视频帧与在视频帧之前间隔开的视频帧进行比较, 帧的预定数值以获得第一帧间差; 将所述视频帧与在所述视频帧之间间隔的视频帧进行比例以预定的数值,以获得第二帧间差; 并且对于所述视频帧的每个像素,获得基于所述第一帧间差和所述第二帧间差的较小值将所述视频帧与所述预定数值相关联的置信图; 以及至少基于与相应的预定数值相关联的一个或多个置信图中的每个像素的值,确定所述像素是否属于前景。

    Classifying image samples
    10.
    发明授权

    公开(公告)号:US10096127B2

    公开(公告)日:2018-10-09

    申请号:US14431927

    申请日:2012-10-22

    Abstract: It is inter alia disclosed to classify samples of a set of samples of an image regarding whether or not a respective sample comprises optical information on a specific object type based on classification information. Therein, the classification information comprises a plurality of classifiers, each classifier being associated exclusively with one color channel of a plurality of color channels.

Patent Agency Ranking