公开(公告)号：US20080118160A1

公开(公告)日：2008-05-22

申请号：US11562547

申请日：2006-11-22

Applicant: Lixin Fan ,  Timo Pylvanainen

Inventor： Lixin Fan ,  Timo Pylvanainen

IPC: G06K9/62

CPC classification number: G06F16/51

Abstract: Systems and methods for organization and browsing a set of images allow a user to find and identify desired images. A collection of images (e.g., stored in an image database) may be organized using a tree or pyramid hierarchy such that each level of the hierarchy represents a finer level of similarity between images in an image cluster. In one arrangement, images are stored as leaf nodes and each ascendant node of the leaf nodes represents a cluster to which the images belong. Each ascendant node may include an animation image representing the set of images belonging to the cluster. A user may browse an image database by identifying and accessing clusters of images that are progressively more refined. A hybrid browsing method and system may also be used wherein images may be displayed simultaneously with the animation images to which they correspond.

Abstract translation: 用于组织和浏览一组图像的系统和方法允许用户找到并识别所需的图像。 可以使用树或金字塔层级来组织图像集合（例如，存储在图像数据库中），使得层级的每个级别表示图像簇中的图像之间更好的相似性水平。 在一种布置中，图像被存储为叶节点，叶节点的每个上升节点表示图像所属的簇。 每个上升节点可以包括表示属于集群的图像集合的动画图像。 用户可以通过识别和访问逐渐更完善的图像群来浏览图像数据库。 还可以使用混合浏览方法和系统，其中图像可以与它们对应的动画图像同时显示。

公开(公告)号：US08396303B2

公开(公告)日：2013-03-12

申请号：US12251087

申请日：2008-10-14

Applicant: Lixin Fan ,  Timo Pylvanainen

Inventor： Lixin Fan ,  Timo Pylvanainen

IPC: G06K9/62 ,  G06K9/74 ,  G06K9/00 ,  G06K9/46 ,  G06K9/66

CPC classification number: G06K9/6298 ,  G06K9/4609 ,  G06K9/6211

Abstract: An apparatus for providing pattern detection may include a processor. The processor may be configured to iteratively test different models and corresponding scales for each of the models. The models may be employed for modeling parameters corresponding to a visually detected data. The processor may be further configured to evaluate each of the models over a plurality of iterations based on a function evaluation of each of the models, select one of the models based on the function evaluation of the selected one of the models, and utilize the selected one of the models for fitting the data.

公开(公告)号：US20100092026A1

公开(公告)日：2010-04-15

申请号：US12251087

申请日：2008-10-14

Applicant: Lixin Fan ,  Timo Pylvanainen

Inventor： Lixin Fan ,  Timo Pylvanainen

IPC: G06K9/00

CPC classification number: G06K9/6298 ,  G06K9/4609 ,  G06K9/6211

Abstract: An apparatus for providing pattern detection may include a processor. The processor may be configured to iteratively test different models and corresponding scales for each of the models. The models may be employed for modeling parameters corresponding to a visually detected data. The processor may be further configured to evaluate each of the models over a plurality of iterations based on a function evaluation of each of the models, select one of the models based on the function evaluation of the selected one of the models, and utilize the selected one of the models for fitting the data.

Abstract translation: 用于提供图案检测的装置可以包括处理器。 处理器可以被配置为迭代地测试每个模型的不同模型和对应的尺度。 可以使用这些模型来建模与视觉检测数据相对应的参数。 处理器还可以被配置为基于每个模型的功能评估来评估多个迭代中的每个模型，基于所选择的一个模型的功能评估来选择一个模型，并且利用所选择的 用于拟合数据的模型之一。

公开(公告)号：US08718324B2

公开(公告)日：2014-05-06

申请号：US13161428

申请日：2011-06-15

Applicant: Lixin Fan

Inventor： Lixin Fan

IPC: G06K9/00 ,  H04N5/225

CPC classification number: G06T7/248 ,  G06T2207/20004 ,  G06T2207/30201

Abstract: A method, apparatus and computer program product are provided that may enable devices to provide improved object tracking, such as in connection with computer vision, multimedia content analysis and retrieval, augmented reality, human computer interaction and region-based image processing. In this regard, a method includes adjusting parameters of a portion of an input frame having a target object to match a template size and then performing feature-based image registration between the portion of the input frame and an active template and at least one selected inactive template. The method may also enable switching the selected inactive template to be an active template for a subsequent frame based at least on a matching score between the portion of the input frame and the selected inactive template and determine a position of a target object in the input frame based on one of the active template or the selected inactive template.

Abstract translation: 提供了一种方法，装置和计算机程序产品，其可以使得设备能够提供改进的对象跟踪，例如结合计算机视觉，多媒体内容分析和检索，增强现实，人机交互和基于区域的图像处理。 在这方面，一种方法包括调整具有目标对象的输入帧的一部分的参数以匹配模板大小，然后在输入帧的部分和活动模板之间执行基于特征的图像配准，以及至少一个选择的非活动模式 模板。 该方法还可以使得至少基于输入帧的部分和所选择的非活动模板之间的匹配分数，将所选择的非活动模板切换为后续帧的活动模板，并且确定目标对象在输入框架中的位置 基于活动模板之一或所选非活动模板。

公开(公告)号：US09271344B2

公开(公告)日：2016-02-23

申请号：US14000508

申请日：2012-08-14

Applicant: Lixin Fan

Inventor： Lixin Fan

IPC: H03K3/017 ,  H03K7/08 ,  H03K5/156 ,  H05B33/08 ,  H05B37/02

CPC classification number: H05B33/0809 ,  H03K3/017 ,  H03K7/08 ,  H05B33/0815 ,  H05B37/0281 ,  Y02B20/346

Abstract: A PWM circuit is disclosed in the application, which includes: a PWM counter, a reference value setting register, a frequency multiplier and a comparator, where the frequency multiplier is adapted to increase the frequency of a clock signal input and to output the clock signal with the increased frequency to the PWM counter. An LED drive circuit is further disclosed in the application. The frequency of a PWM input clock signal is increased to N times of the original frequency of the PWM input clock signal by the frequency multiplier, so that the counting cycle of the PWM counter is shortened to 1/N of the original counting cycle of the PWM counter. Therefore, in the dynamic LED display screen, the refresh frequency can be increased to N times of the original refresh frequency while the original resolution is maintained.

Abstract translation: 在本申请中公开了PWM电路，其包括：PWM计数器，参考值设置寄存器，倍频器和比较器，其中倍频器适于增加时钟信号输入的频率并输出时钟信号 增加到PWM计数器的频率。 在本申请中进一步公开了LED驱动电路。 PWM输入时钟信号的频率由倍频器增加到PWM输入时钟信号的原始频率的N倍，使得PWM计数器的计数周期缩短到原始计数周期的1 / N PWM计数器。 因此，在动态LED显示画面中，在保持原始分辨率的同时，将刷新频率提高到原来的刷新频率的N倍。

公开(公告)号：US07907786B2

公开(公告)日：2011-03-15

申请号：US11145710

申请日：2005-06-06

Applicant: Lixin Fan ,  Jutta K. Willamowski ,  Christopher R. Dance

Inventor： Lixin Fan ,  Jutta K. Willamowski ,  Christopher R. Dance

IPC: G06K9/40

CPC classification number: G06K9/0061 ,  G06T5/005 ,  G06T7/11 ,  G06T7/143 ,  G06T7/90 ,  G06T2207/10024 ,  G06T2207/30201 ,  G06T2207/30216

Abstract: A method suited to the detection and correction of red-eyes includes assigning a probability to pixels of a digital image of the pixel being in a red-eye, the probability being a function of a color of the pixel. Optionally, generally circular regions in the image of contiguous pixels which satisfy at least one test for a red-eye are identified. The test may include determining a size or shape of the region or an extent of overlap with a region comprising pixels having at least a threshold probability of being in a red-eye. For each of a plurality of the pixels, such as simply those in identified regions, or for all pixels or a larger group of the pixels, a color correction for the pixel is determined. The correction is a function of the assigned probability that the pixel is within a red-eye and a color of the pixel.

Abstract translation: 适合于红眼的检测和校正的方法包括将概率分配给红眼中的像素的数字图像的像素，该概率是像素的颜色的函数。 可选地，识别满足至少一个红眼测试的连续像素的图像中的大致圆形区域。 该测试可以包括确定该区域的大小或形状或与包括具有至少阈值概率处于红眼的像素的区域的重叠程度。 对于多个像素中的每一个，例如简单地在识别的区域中的像素，或者对于所有像素或者较大的像素组，确定像素的颜色校正。 校正是像素在红眼内和像素的颜色之间的分配概率的函数。

公开(公告)号：US07865492B2

公开(公告)日：2011-01-04

申请号：US11237229

申请日：2005-09-28

Applicant: Lixin Fan

Inventor： Lixin Fan

IPC: G06F7/00

CPC classification number: G06F17/30256

Abstract: An improved method, device and computer program product for enabling a system to learn, categorize and search items such as images and video clips according to their semantic meanings. According to the present invention, prominent features can be separated from low-level features in an item using supervised learning approaches. Prominent features are used to categorize and annotate new target items. Users can then use key words and/or template items for searching through the respective database.

Abstract translation: 一种改进的方法，设备和计算机程序产品，用于使系统能够根据其语义意义学习，分类和搜索诸如图像和视频剪辑的项目。 根据本发明，使用监督学习方法，突出特征可以与项目中的低级特征分离。 突出特征用于对新的目标项目进行分类和注释。 然后，用户可以使用关键词和/或模板项目来搜索相应的数据库。

公开(公告)号：US20070073749A1

公开(公告)日：2007-03-29

申请号：US11237229

申请日：2005-09-28

Applicant: Lixin Fan

Inventor： Lixin Fan

IPC: G06F7/00

CPC classification number: G06F17/30256

Abstract: An improved method, device and computer program product for enabling a system to learn, categorize and search items such as images and video clips according to their semantic meanings. According to the present invention, prominent features can be separated from low-level features in an item using supervised learning approaches. Prominent features are used to categorize and annotate new target items. Users can then use key words and/or template items for searching through the respective database.

Abstract translation: 一种改进的方法，设备和计算机程序产品，用于使系统能够根据其语义意义学习，分类和搜索诸如图像和视频剪辑的项目。 根据本发明，使用监督学习方法，突出特征可以与项目中的低级特征分离。 突出特征用于对新的目标项目进行分类和注释。 然后，用户可以使用关键词和/或模板项目来搜索相应的数据库。

公开(公告)号：US20070009159A1

公开(公告)日：2007-01-11

申请号：US11452761

申请日：2006-06-14

Applicant: Lixin Fan

Inventor： Lixin Fan

IPC: G06K9/62

CPC classification number: G06K9/4642 ,  G06K9/527 ,  G06K9/6211

Abstract: A method and system for holistic Harr-like feature matching for image recognition includes extracting features from a test image where the extracted features are Harr-like features extracted from key points in the test image, matching extracted features from the test image with features from a template image, transforming the test image according to matched extracted features, and providing match results

Abstract translation: 用于图像识别的整体Harr样特征匹配的方法和系统包括从测试图像中提取特征，其中提取的特征是从测试图像中的关键点提取的类Harr特征，将来自测试图像的特征与来自 模板图像，根据匹配的提取特征变换测试图像，并提供匹配结果

公开(公告)号：US20060274950A1

公开(公告)日：2006-12-07

申请号：US11145710

申请日：2005-06-06

Applicant: Lixin Fan ,  Jutta Willamowski ,  Christopher Dance

Inventor： Lixin Fan ,  Jutta Willamowski ,  Christopher Dance

IPC: G06K9/62 ,  G06K9/00

CPC classification number: G06K9/0061 ,  G06T5/005 ,  G06T7/11 ,  G06T7/143 ,  G06T7/90 ,  G06T2207/10024 ,  G06T2207/30201 ,  G06T2207/30216

Abstract: A method suited to the detection and correction of red-eyes includes assigning a probability to pixels of a digital image of the pixel being in a red-eye, the probability being a function of a color of the pixel. Optionally, generally circular regions in the image of contiguous pixels which satisfy at least one test for a red-eye are identified. The test may include determining a size or shape of the region or an extent of overlap with a region comprising pixels having at least a threshold probability of being in a red-eye. For each of a plurality of the pixels, such as simply those in identified regions, or for all pixels or a larger group of the pixels, a color correction for the pixel is determined. The correction is a function of the assigned probability that the pixel is within a red-eye and a color of the pixel.

Abstract translation: 适合于红眼的检测和校正的方法包括将概率分配给红眼中的像素的数字图像的像素，该概率是像素的颜色的函数。 可选地，识别满足至少一个红眼测试的连续像素的图像中的大致圆形区域。 该测试可以包括确定该区域的大小或形状或与包括具有至少阈值概率处于红眼的像素的区域的重叠程度。 对于多个像素中的每一个，例如简单地在识别的区域中的像素，或者对于所有像素或者较大的像素组，确定像素的颜色校正。 校正是像素在红眼内和像素的颜色之间的分配概率的函数。