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
    • 11. 发明申请
    • SYSTEM AND METHOD FOR DETERMINING ESTIMATED AGE USING AN IMAGE COLLECTION
    • 使用图像采集来确定估计年龄的系统和方法
    • US20120308087A1
    • 2012-12-06
    • US13118897
    • 2011-05-31
    • Hui CHAOTong ZhangDaniel R. Tretter
    • Hui CHAOTong ZhangDaniel R. Tretter
    • G06K9/00
    • G06K9/00221G06K2009/00322
    • A system and a method are provided for determining an estimated age of an individual of interest based on images in an image collection. An example system includes a memory for storing computer executable instructions, and a processing unit for accessing the memory and executing the computer executable instructions. The computer executable instructions include an age class estimator to classify a plurality of images of the individual into age classes, each age class corresponding to an interval of age, and each image having a known time stamp, a probability determination engine to determine, for each age class, a value of class probability that an image in the collection falls within the age class, an age determination engine to determine a transition time based on the values of class probability and the known time stamp, and to determine the estimated age of the individual based on the determined transition time.
    • 提供了一种系统和方法,用于基于图像集合中的图像来确定感兴趣的个体的估计年龄。 示例系统包括用于存储计算机可执行指令的存储器,以及用于访问存储器并执行计算机可执行指令的处理单元。 计算机可执行指令包括:年龄类别估计器,用于将个体的多个图像分类为年龄类别,每个年龄段对应于年龄间隔;每个图像具有已知时间戳;概率确定引擎,用于为每个 年龄级别,集合中的图像属于年龄类别的类概率的值,基于类概率和已知时间戳的值来确定转换时间的年龄确定引擎,并且确定估计的年龄 个人基于确定的过渡时间。
    • 12. 发明申请
    • Face Recognition Apparatus and Methods
    • 人脸识别装置及方法
    • US20120230545A1
    • 2012-09-13
    • US13501300
    • 2009-11-30
    • Tong ZhangWei Zhang
    • Tong ZhangWei Zhang
    • G06K9/48
    • G06K9/6253G06K9/00221G06K9/6227
    • One or more facial recognition categories are assigned to a face region detected in an input image (24). Each of the facial recognition categories is associated with a respective set of one or more different feature extraction modules (66) and a respective set of one or more different facial recognition matching modules (76). For each of the facial recognition categories assigned to the face region, the input image (24) is processed with each of the feature extraction modules (66) associated with the facial recognition category to produce a respective facial region descriptor vector of facial region descriptor values characterizing the face region. A recognition result (96) between the face region and a reference face image (28) is determined based on application of the one or more facial recognition matching modules (76) associated with the facial recognition categories assigned to the face region to the facial region descriptor vectors produced for the face region detected in the input image (24).
    • 一个或多个面部识别类别被分配给在输入图像(24)中检测到的面部区域。 每个面部识别类别与相应的一组一个或多个不同的特征提取模块(66)和相应的一组或多个不同的面部识别匹配模块(76)相关联。 对于分配给面部区域的每个面部识别类别,与与面部识别类别相关联的每个特征提取模块(66)处理输入图像(24),以产生面部区域描述符值的相应面部区域描述符向量 表征脸部区域。 基于与分配给面部区域的面部识别类别相关联的一个或多个面部识别匹配模块(76)到面部区域的应用来确定面部区域和参考面部图像(28)之间的识别结果(96) 为在输入图像(24)中检测到的面部区域产生的描述符向量。
    • 14. 发明申请
    • FACE RECOGNITION APPARATUS AND METHODS
    • 脸部识别装置和方法
    • US20120170852A1
    • 2012-07-05
    • US13395458
    • 2009-09-25
    • Wei ZhangTong Zhang
    • Wei ZhangTong Zhang
    • G06K9/48
    • G06K9/00281
    • Interest regions are detected in respective images (18) having face regions labeled with respective facial part labels. For each of the detected interest regions, a respective facial region descriptor vector of facial region descriptor values characterizing the detected interest region is determined. Ones of the facial part labels are assigned to respective ones of the facial region descriptor vectors. For each of the facial part labels, a respective facial part detector (20) that detects facial region descriptor vectors corresponding to the facial part label is built. The facial part detectors (20) are associated with rules (30) that qualify segmentation results of the facial part detectors (20) based on spatial relations between interest regions detected in images and the respective face part labels assigned to the facial part detectors (20). Faces in images are detected and recognized based on application of the facial part detectors (20) to images.
    • 在具有用相应的面部标签标记的面部区域的各个图像(18)中检测兴趣区域。 对于每个检测到的感兴趣区域,确定表征检测到的兴趣区域的面部区域描述符值的相应面部区域描述符向量。 面部部分标签的一部分被分配给面部区域描述符向量中的相应的一个。 对于每个面部部分标签,构建检测与面部部分标签相对应的面部区域描述符向量的相应面部部分检测器(20)。 面部部分检测器(20)与根据图像中检测到的兴趣区域和分配给面部部分检测器的相应面部部分标签(20)之间的空间关系来限定面部部分检测器(20)的分割结果的规则(30)相关联 )。 基于面部部件检测器(20)对图像的应用来检测和识别图像中的面部。
    • 15. 再颁专利
    • Single-mode operation and frequency conversions for solid-state lasers
    • 固态激光器的单模操作和频率转换
    • USRE43421E1
    • 2012-05-29
    • US10820561
    • 2004-04-08
    • Tong Zhang
    • Tong Zhang
    • H01S3/098H01S3/10H01S3/13
    • Key technologies have been developed in realizing single longitudinal mode CW operation with a regular standing-wave cavity for intracavity frequency doubling and intracavity frequency conversions, so as to produce all solid-state, true cw devices with operation over wide spectral ranges including green, blue and UV. In one method laser arrangement, a beam expander (23 or 41) is applied to render a large mode waist and an improved beam divergence so as to greatly reduce the insertion losses for intracavity optical elements (17, 18 or 44). In another method laser arrangement, when spatial hole burning interference effect is minimized by using a pump head (12) with a thin gain zone (2) in contact with an end cavity mirror, then a low resolving-power spectral filter with low loss can be utilized. In addition, several novel optical multipass constructions, typically by use of total-internal-reflection, have also been devised for pumping laser chips, laser rods, laser slabs, and for the use of multipass optical amplifier and pumping fiber lasers.
    • 已经开发了关键技术,用于实现单纵向CW操作,并具有用于腔内倍频和腔内频率转换的常规驻波腔,以便产生在宽光谱范围内运行的所有固态,真正的cw器件,包括绿色,蓝色 和紫外线。 在一种激光装置的方法中,施加光束扩展器(23或41)以呈现大模式腰部和改进的光束发散,从而大大减小腔内光学元件(17,18或44)的插入损耗。 在另一种激光装置的方法中,当通过使用具有与端腔镜接触的薄增益区(2)的泵头(12)来最小化空间空穴燃烧干扰效应时,则具有低损耗的低分辨率功率谱滤波器 被利用。 此外,还设计了通常使用全内反射的几种新颖的光学多通道结构,用于泵浦激光芯片,激光棒,激光板以及用于多通道光放大器和泵浦光纤激光器。
    • 16. 发明授权
    • Illumination system and display including same
    • 照明系统和显示器包括相同
    • US08136955B2
    • 2012-03-20
    • US12446277
    • 2007-10-18
    • Stephen James FashamDavid James MontgomeryEmma Jayne WaltonTong Zhang
    • Stephen James FashamDavid James MontgomeryEmma Jayne WaltonTong Zhang
    • G09F13/04
    • G02B6/0028G02B6/0018G02B6/0046G02B6/0068
    • An illumination system comprises at least one light source (2) and a light-guide (1). A first part of the light-guide (1) is defined by a surface (12) for light emission and a back surface (13), and a second part of the light-guide is defined by a light receiving surface (14) and a light reflecting surface (15). The light source (2) is disposed adjacent or substantially adjacent to the light receiving surface (14), and light from the light source enters the light-guide through the light receiving surface (14), and is reflected by the light reflecting surface (15) into the first part of the light-guide. Light is emitted from the waveguide through the surface (12) for light emission, and may be used to illuminate, for example, a display device placed over the surface (12) for light emission. The light source and the light receiving surface are on the same side of the waveguide as the surface for light emission.
    • 照明系统包括至少一个光源(2)和光导(1)。 导光体(1)的第一部分由用于发光的表面(12)和背面(13)限定,导光体的第二部分由光接收表面(14)和 光反射表面(15)。 光源(2)与光接收表面(14)相邻或基本相邻设置,并且来自光源的光通过光接收表面(14)进入导光体,并被光反射表面( 15)进入导光板的第一部分。 光从波导通过用于发光的表面(12)发射,并且可以用于照亮例如放置在表面(12)上的用于发光的显示装置。 光源和光接收表面在与发光表面相同的波导侧。
    • 17. 发明申请
    • INTEGRATED OPTICAL FIBER GYROSCOPE CHIP BASED ON SURFACE PLASMON POLARITON WAVEGUIDE
    • 基于表面等离子体波导的集成光纤陀螺切片
    • US20120051691A1
    • 2012-03-01
    • US13264615
    • 2009-09-23
    • Tong ZhangXiaojun XuePengqin WuXiaoyang ZhangQiuyue Chen
    • Tong ZhangXiaojun XuePengqin WuXiaoyang ZhangQiuyue Chen
    • G02B6/12G01C19/72
    • G01C19/721
    • An integrated optical fiber gyroscope chip based on surface Plasmon Polariton waveguide is an integrated optical fiber gyroscope chip in which optical signal is transmitted through the surface Plasmon Polariton waveguide and the polymer optical waveguide which are connected with each other, and it is used in the optical fiber gyroscope field. From the input end to the output end, the optical fiber gyroscope chip sequentially has: an input waveguide (1) and the third output waveguide (7), a directional coupler (2), a symmetrical triple waveguide splitter (3), the first output waveguide (61) and the second output waveguide (62), wherein the input waveguide (1), the first output waveguide (61), the second output waveguide (62) and the third output waveguide (7) are polymer optical waveguides, but the directional coupler (2) and the symmetrical triple waveguide splitter (3) are made from the surface Plasmon Polariton waveguide. The chip utilizes the transmission characteristics of the surface Plasmon Polariton waveguide to realize the single polarization of long-distance transmission of the optical signal, and directly modulates the surface Plasmon Polariton waveguide core layer, and removes influence of the leakage light to the precision of the fiber gyroscope through the specific structure.
    • 基于表面等离子体Polariton波导的集成光纤陀螺仪芯片是一种集成的光纤陀螺仪芯片,其中光信号通过表面等离子体Polariton波导和聚合物光波导传输,彼此连接,并被用于光学 光纤陀螺仪领域。 从输入端到输出端,光纤陀螺仪芯片依次具有:输入波导(1)和第三输出波导(7),定向耦合器(2),对称三波导分路器(3),第一 输出波导(61)和第二输出波导(62),其中输入波导(1),第一输出波导(61),第二输出波导(62)和第三输出波导(7)是聚合物光波导, 但定向耦合器(2)和对称三波导分路器(3)由表面等离子体极化波导制成。 该芯片利用表面等离子体Polariton波导的传输特性,实现光信号长距离传输的单极化,直接调制表面等离子体Polariton波导芯层,并将泄漏光的影响消除为 光纤陀螺通过具体结构。
    • 18. 发明申请
    • CANTILEVER BEAM STRUCTURAL RESONANT-TYPE INTEGRATED OPTICAL WAVEGUIDE ACCELEROMETER
    • CANTILEVER梁结构谐振型集成光波导加速度计
    • US20110303008A1
    • 2011-12-15
    • US13202755
    • 2009-09-23
    • Tong ZhangXiaojun XueXiaoyang ZhangPengqin Wu
    • Tong ZhangXiaojun XueXiaoyang ZhangPengqin Wu
    • G01P15/093
    • G01P15/093G01P15/097G02B6/12007G02B6/1221G02B2006/12138
    • A cantilever beam structural resonant-type integrated optical waveguide accelerometer, includes an input waveguide (1), a dissymmetrical structural Mach-Zehnder interferometer (2), a micro-mechanical vibration cantilever beam (3), a short curved waveguide (4) and an output waveguide (5); all the waveguide structures and the cantilever beam use the integrated optical micromachining technique, and the device single-scale integration can be realized by using the temperature-insensitive organic polymer optical waveguide structure and the organic polymer substrate, the key technique indexes such as detection sensitivity, dynamic range are extensively adjusted. The phase difference of the optical signal can be measured by detecting the optical intensity of the resonant frequency of the optical circuit so as to achieve high sensitive acceleration detection, and to be free from the effect of the ambient temperature disturbance and waveguide birefringence.
    • 一种悬臂梁结构谐振型集成光波导加速度计,包括输入波导(1),不对称结构马赫 - 策德尔干涉仪(2),微机械振动悬臂梁(3),短弯曲波导(4)和 输出波导(5); 所有波导结构和悬臂梁均采用集成光学微机械加工技术,通过使用温度不敏感的有机聚合物光波导结构和有机聚合物基板实现了器件单尺度集成,检测灵敏度等关键技术指标 ,动态范围被广泛调整。 可以通过检测光电路的谐振频率的光强度来测量光信号的相位差,从而实现高灵敏度的加速度检测,并且不受环境温度干扰和波导双折射的影响。
    • 19. 发明授权
    • Detecting blocks of commercial content in video data
    • 检测视频数据中的商业内容块
    • US07982797B2
    • 2011-07-19
    • US11479405
    • 2006-06-30
    • Tong Zhang
    • Tong Zhang
    • H04N7/12G06F13/00
    • H04N5/4401H04N5/147H04N21/434H04N21/435H04N21/44008H04N21/478H04N21/812
    • Systems and methods of detecting blocks of commercial content in video data are described. In one aspect, visual parameter values and audio parameter values are extracted from the video data. Visual boundary events, audio boundary events, and commercial content transition events are detected in the video data. Candidate commercial blocks of consecutive commercial content are detected in the video data from a combination of the detected visual boundary events and the detected audio boundary events. Each of the candidate commercial blocks is defined between respective candidate starting and ending boundary points. Ones of the starting and ending boundary points of the candidate commercial blocks are adjusted based on occurrence of one or more of the detected commercial content transition events within temporal windows respectively encompassing the starting and ending points.
    • 描述了在视频数据中检测商业内容块的系统和方法。 在一个方面,从视频数据中提取视觉参数值和音频参数值。 在视频数据中检测视觉边界事件,音频边界事件和商业内容转换事件。 从检测到的视界边界事件和检测到的音频边界事件的组合在视频数据中检测到连续商业内容的候选商业广告块。 每个候选商业广告块被定义在相应的候选开始和结束边界点之间。 基于分别包含开始点和结束点的时间窗口内的检测到的商业内容转换事件中的一个或多个的发生来调整候选商业广告块的开始和结束边界点的区域。