利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

44 条记录 (耗时 0.012 秒)

    Method, apparatus and system for identifying distracting elements in an image
    3.
    发明公开
    Method, apparatus and system for identifying distracting elements in an image 审中-公开
    过程，装置和系统，用于偏转元件上的图像的识别

    公开(公告)号：EP2605187A1

    公开(公告)日：2013-06-19

    申请号：EP12196765.7

    申请日：2012-12-12

    申请人： CANON KABUSHIKI KAISHA

    发明人： Fredembach, Clement

    IPC分类号： G06K9/46 ,  G06T7/00

    CPC分类号： G06K9/40 ,  G06K9/4623 ,  G06K9/4638 ,  G06K9/4671 ,  G06T7/11 ,  G06T7/187

    摘要： A method of identifying a distracting element in an image (e.g., 1100), is disclosed. A visual attention map (e.g., 1120) is determined for the image (1100), the visual attention map (1120) representing one or more regions of the image, at least one of the regions corresponding to at least a portion of a subject of the image. A salient region map (e.g., 1110) is determined for the image (1100), the salient region map comprising a distribution of visual attraction values defining one or more further regions of the image (1100), the one or more further regions being categorised as salient. An intersection between the visual attention map (1120) and the salient region map (1110) is determined to identify a distracting element in the image (1100). The distracting element corresponds to at least one of the salient regions.

    摘要翻译： 的图像（E.C.，1100）中确定的干扰元素的方法是游离缺失盘。 视觉注意图（例如，1120）是确定性的开采表示所述图像的一个或多个区域的图像（1100），视觉注意图（1120），该区域中的至少一个对应于对象的至少一部分 图像。 显着区域的地图（例如，1110）是确定性的开采的图像（1100），显着区域图包括视觉吸引力的分布值限定的图像（1100）的一个或多个另外的区域，所述一个或多个另外的区域被分类 为突出。 视觉注意图（1120）和所述显着区域图（1110）之间的交叉点是确定的采空图像（1100）中，以确定一个干扰元素。 所述干扰元素对应于显着的区域中的至少一个。

    DEVICE AND METHOD FOR CREATING A SALIENCY MAP OF AN IMAGE
    5.
    发明公开
    DEVICE AND METHOD FOR CREATING A SALIENCY MAP OF AN IMAGE 有权
    装置和方法，用于在图像中生成映射出尖锐特征

    公开(公告)号：EP1695288A1

    公开(公告)日：2006-08-30

    申请号：EP04804828.4

    申请日：2004-12-14

    申请人： Thomson Licensing

    发明人： LE MEUR, Olivier ,  THOREAU, Dominique ,  FRANCOIS, Edouard ,  LE CALLET, Patrick ,  BARBA, Dominique

    IPC分类号： G06T5/00 ,  G06T7/20

    CPC分类号： G06K9/4623 ,  G06K9/4652 ,  G06K9/4671 ,  G06T5/003 ,  G06T7/262 ,  G06T2207/10024

    摘要： The invention concerns a device and a method for creating a saliency map of an image. It comprises the steps of: Projection (E1) of said image according to the luminance (A) component and if said image is a color image, according to the luminance (A) component and according to the chrominance components (Cr1, Cr2); Perceptual sub-bands decomposition (E3, T2, T'2, T’’2) of said components (A, Cr1, Cr2) according to the visibility threshold of a human eye; Extraction (E7) of the salient elements of the sub-bands related to the luminance (A) component; Contour enhancement (E8, T7) of said salient elements in each sub-band related to the luminance (A) component; Calculation (T7) of a saliency map from the contour enhancement, for each sub-band related to the luminance (A) component. Creation (T8) of the saliency map as a function of the saliency maps obtained for each sub-band.

    SYSTEM AND METHOD FOR DECODING SPIKING RESERVOIRS WITH CONTINUOUS SYNAPTIC PLASTICITY
    6.
    发明公开
    SYSTEM AND METHOD FOR DECODING SPIKING RESERVOIRS WITH CONTINUOUS SYNAPTIC PLASTICITY 审中-公开
    系统和方法用于解码具有连续突发性的尖峰储层

    公开(公告)号：EP3271872A1

    公开(公告)日：2018-01-24

    申请号：EP16765882.2

    申请日：2016-03-18

    申请人： HRL LABORATORIES, LLC

    发明人： CHO, Youngkwan ,  SRINIVASA, Narayan

    IPC分类号： G06N3/02 ,  G06F17/10 ,  G06F15/18

    CPC分类号： G06N3/08 ,  G06K9/00543 ,  G06K9/00805 ,  G06K9/4623 ,  G06K9/66 ,  G06N3/0445 ,  G06N3/049 ,  G06N3/088

    摘要： Described is a system for decoding spiking reservoirs even when the spiking reservoir has continuous synaptic plasticity. The system uses a set of training patterns to train a neural network having a spiking reservoir comprised of spiking neurons. A test pattern duration d is estimated for a set of test patterns P, and each test pattern is presented to the spiking reservoir for a duration of d/P seconds. Output spikes from the spiking reservoir are generated via readout neurons. The output spikes are measured and the measurements are used to compute firing rate codes, each firing rate code corresponding to a test pattern in the set of test patterns P. The firing rate codes are used to decode performance of the neural network by computing a discriminability index (DI) to discriminate between test patterns in the set of test patterns P.

    ANALOG SIGNAL RECONSTRUCTION AND RECOGNITION VIA SUB-THRESHOLD MODULATION
    7.
    发明公开
    ANALOG SIGNAL RECONSTRUCTION AND RECOGNITION VIA SUB-THRESHOLD MODULATION 审中-公开
    ERKENNUNGÜBERUNTERSCHWELLENMODULATION的模拟反应

    公开(公告)号：EP3117372A2

    公开(公告)日：2017-01-18

    申请号：EP15710992.7

    申请日：2015-02-27

    申请人： Qualcomm Incorporated

    发明人： CAREY, Ryan Michael ,  CHAN, Victor Hokkiu

    IPC分类号： G06N3/04 ,  G06K9/62

    CPC分类号： G06N3/049 ,  G06K9/4623 ,  G06K9/627

    摘要： Certain aspects of the present disclosure support a method and apparatus for analog signal reconstruction and recognition via sub-threshold modulation. The analog waveform recognition in a sub-threshold region of an artificial neuron of the artificial nervous system can be performed by providing a predicted waveform in parallel to an input associated with the artificial neuron. The predicted waveform can be compared with the input and the signal can be generated based at least in part on the comparison. The signal can be a detection signal that detects matching and mismatching between the input and the predicted waveform

    摘要翻译： 本公开的某些方面支持通过子阈值调制进行模拟信号重建和识别的方法和装置。 人造神经系统的人造神经元的亚阈值区域中的模拟波形识别可以通过提供与与人造神经元相关联的输入并行的预测波形来执行。 可以将预测波形与输入进行比较，并且可以至少部分地基于比较来生成信号。 该信号可以是检测输入和预测波形之间的匹配和不匹配的检测信号

    IMAGE PROCESSING
    9.
    发明公开
    IMAGE PROCESSING 审中-公开
    图像处理

    公开(公告)号：EP3044733A1

    公开(公告)日：2016-07-20

    申请号：EP14781464.4

    申请日：2014-09-12

    申请人： Cortexica Vision Systems Limited

    发明人： KWONG, Jeffrey Ng Sing ,  GIDARIS, Spyridon ,  LI, Yin ,  BHARATH, Anil Anthony ,  AWAIS, Muhammad ,  VAZQUEZ, Eduardo ,  YU, Qian

    IPC分类号： G06K9/46

    CPC分类号： G06T7/403 ,  G06K9/4623 ,  G06K9/4652 ,  G06T7/44 ,  G06T2207/10024

    摘要： A method of generating a descriptor of at least part of an image includes receiving image data representing the at least part of the image. The image data is processed to identify at least one texture characteristic of the at least part of the image, thereby generating texture data indicative of a texture of the at least part of the image. The texture data is processed with the image data, thereby generating weighted texture data. A descriptor of the at least part of the image is generated using the weighted texture data.

    摘要翻译： 生成图像的至少一部分的描述符的方法包括接收表示图像的至少一部分的图像数据。 处理图像数据以识别至少一部分图像的至少一个纹理特征，从而生成指示至少部分图像的纹理的纹理数据。 用图像数据处理纹理数据，从而生成加权纹理数据。 使用加权纹理数据来生成图像的至少一部分的描述符。

    TECHNIQUES FOR FEATURE EXTRACTION
    10.
    发明公开
    TECHNIQUES FOR FEATURE EXTRACTION 审中-公开
    方法进行特征提取

    公开(公告)号：EP2740074A1

    公开(公告)日：2014-06-11

    申请号：EP11870265.3

    申请日：2011-08-01

    申请人： Google Inc.

    发明人： WANG, Zhiyu ,  CHANG, Edward Y.

    IPC分类号： G06K9/46

    CPC分类号： G06T7/90 ,  G06K9/00684 ,  G06K9/4619 ,  G06K9/4623 ,  G06K9/4652 ,  G06K9/4671 ,  G06K9/623

    摘要： A computer-implemented technique for feature extraction includes obtaining an electronic image of an object and performing an edge detection algorithm on the electronic image. The technique further includes performing an edge pooling algorithm and sampling the electronic image edge patches, color patches and texture patches. A set of patches is selected from the edge patches, color patches and texture patches by selecting an (
    i
    th + 1) patch to be within the set of patches based on a Euclidean distance from an
    i
    th patch of the set of patches for each of the set of edge patches, the set of color patches and the set of texture patches. A part selection algorithm and a part pooling algorithm is performed to obtain parts that are registered to the object.