专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US6151025A Method and apparatus for complexity reduction on two-dimensional convolutions for image processing 失效
标题翻译：用于图像处理的二维卷积复杂度降低的方法和装置
公开(公告)号：US6151025A
公开(公告)日：2000-11-21
申请号：US852620
申请日：1997-05-07
申请人： Jonathan Yen , Luca Chiarabini
发明人： Jonathan Yen , Luca Chiarabini
IPC分类号： H04N1/409 , G06T3/40 , G06T5/00 , G06T5/20 , G06T3/20
CPC分类号： G06T5/20
摘要： A method and apparatus are provided for reducing the complexity of two-dimensional linear convolutions. All possible pixel patterns for a row of a pixel array are determined and multiplied by a corresponding row in a convolution kernel matrix. The partial convolution results are stored in a lookup table. In a processing step, each row of an input pixel window is compared to the possible pixel rows. Partial results associated with a matching pixel row are accessed from the lookup table. In one preferred embodiment of the invention, each row of an input pixel window is stored in a line cache. In another, equally preferred embodiment, a hash function is optionally used to derive an index value for each possible pixel row. The partial result associated with an equal index value is accessed. In another, equally preferred embodiment, double buffer stores two consecutive input pixel windows for processing. After each row of the first buffer is processed, the double buffer is shifted by one pixel. After the entire contents of the second buffer have been shifted into the first buffer, the next input pixel window is moved into the second buffer. Thus, the invention requires only one main memory access for each input pixel window. The partial convolution results are preferably calculated in floating point arithmetic and converted to a fixed point precision before they are stored as table entries.
摘要翻译：提供了一种用于降低二维线性卷积的复杂度的方法和装置。确定一行像素阵列的所有可能的像素图案并乘以卷积核心矩阵中的相应行。部分卷积结果存储在查找表中。在处理步骤中，将输入像素窗口的每一行与可能的像素行进行比较。从查找表访问与匹配像素行相关联的部分结果。在本发明的一个优选实施例中，输入像素窗口的每行被存储在行高速缓存中。在另一个，同样优选的实施例中，可选地使用散列函数来导出每个可能的像素行的索引值。访问与索引值相等的部分结果。在另一个同样优选的实施例中，双缓冲器存储用于处理的两个连续的输入像素窗口。在处理第一缓冲器的每一行之后，双缓冲器被移位一个像素。在第二缓冲器的全部内容已被移入第一缓冲器之后，下一个输入像素窗口移动到第二缓冲器中。因此，本发明对于每个输入像素窗口仅需要一个主存储器访问。部分卷积结果优选以浮点算术计算，并在作为表条目存储之前转换为固定点精度。

2. 发明授权

US07916905B2 System and method for image facial area detection employing skin tones 失效
标题翻译：使用肤色的图像面部区域检测的系统和方法
公开(公告)号：US07916905B2
公开(公告)日：2011-03-29
申请号：US12322394
申请日：2009-02-02
申请人： Jonathan Yen , Tony Quach
发明人： Jonathan Yen , Tony Quach
IPC分类号： G06K9/00 , G06K9/46 , G06K9/66
CPC分类号： G06K9/00234
摘要： The subject application is directed to a system and method for image facial detection employing skin tones. Image data comprised of a plurality of pixels encoded in at least a three dimensional component space is received and sub-sampled region data is generated from the received image data. A percentage of pixels having a low chroma value below a threshold value is then calculated and tested against a predetermined percentage threshold value. Each pixel is then classified in accordance with a skin tone model. Skin tone map data is then generated based on classification and a skin tone mask is output form the map data.
摘要翻译：本申请涉及使用肤色的图像面部检测系统和方法。接收由至少三维分量空间中编码的多个像素构成的图像数据，并从接收到的图像数据生成子采样区域数据。然后根据预定百分比阈值计算和测试具有低于阈值的低色度值的像素的百分比。然后根据肤色模型对每个像素进行分类。然后基于分类生成皮肤色调图数据，并且从地图数据输出肤色蒙版。

3. 发明申请

US20110051161A1 Digital Image Tone Adjustment 有权
标题翻译：数字图像色调调整
公开(公告)号：US20110051161A1
公开(公告)日：2011-03-03
申请号：US12941876
申请日：2010-11-08
申请人： Jonathan Yen , William C. Kress , Robert Poe
发明人： Jonathan Yen , William C. Kress , Robert Poe
IPC分类号： H04N1/60
CPC分类号： G06T5/40 , G06T5/009
摘要： Image tone adjustment systems and methods are disclosed. The system of the present invention includes an input to accept an input image. A curve generator is also disclosed that is used to generate a tone reproduction curve including a contrast stretch of the input image, a white stretch of the input image and a black stretch of the input image. Backlit correction is also applied by the tone adjustment corrector to thereby generate a tone adjusted image.
摘要翻译：公开了图像色调调节系统和方法。本发明的系统包括接收输入图像的输入。还公开了一种曲线发生器，其用于产生包括输入图像的对比度伸展，输入图像的白色拉伸和输入图像的黑色拉伸的色调再现曲线。背光校正也由色调调整校正器应用，从而产生色调调整图像。

4. 发明申请

US20110044541A1 System and method for backlit image detection 失效
标题翻译：用于背光图像检测的系统和方法
公开(公告)号：US20110044541A1
公开(公告)日：2011-02-24
申请号：US12583624
申请日：2009-08-24
申请人： William C. Kress , Jonathan Yen
发明人： William C. Kress , Jonathan Yen
IPC分类号： G06K9/00
CPC分类号： G06T7/0002 , G06T2207/10004 , G06T2207/30168
摘要： The subject application is directed to a system and method for detecting backlit images. Encoded color image data is first received into a computer having a processor and associated data storage. Histogram data is then calculated from the received encoded color image data, and a mid-tone range in normalized histogram data is then detected. A zone of normalized pixel counts within the mid-tone range is then selected. Data representing an entry point and an exit point of the normalized histogram data relative to the selected zone is then generated. A plateau area is detected in the histogram data in the selected zone between the entry point and the exit point. Thereafter, a backlit image detection signal is generated indicating whether a backlit image portion is present in the color image data according to the plateau detection.
摘要翻译：本申请涉及用于检测背光图像的系统和方法。编码的彩色图像数据首先被接收到具有处理器和相关联的数据存储器的计算机中。然后从接收到的编码彩色图像数据计算直方图数据，然后检测归一化直方图数据中的中间色调范围。然后选择中音范围内的归一化像素计数区域。然后生成表示归一化直方图数据相对于所选择的区域的入口点和出口点的数据。在入口点和出口点之间的所选区域的直方图数据中检测到平台区。此后，产生背光图像检测信号，指示根据平台检测在彩色图像数据中是否存在背光图像部分。

5. 发明授权

US07747071B2 Detecting and correcting peteye 有权
标题翻译：检测和纠正peteye
公开(公告)号：US07747071B2
公开(公告)日：2010-06-29
申请号：US11260636
申请日：2005-10-27
申请人： Jonathan Yen , Daniel Tretter , Huitao Luo , Suk Hwan Lim
发明人： Jonathan Yen , Daniel Tretter , Huitao Luo , Suk Hwan Lim
IPC分类号： G06K9/00
CPC分类号： G06K9/0061
摘要： Peteye is the appearance of an unnatural coloration (not necessarily red) of the pupils in an animal appearing in an image captured by a camera with flash illumination. Systems and methods of detecting and correcting peteye are described. In one aspect a classification map segmenting pixels in the input image into peteye pixels and non-peteye pixels is generated based on a respective segmentation condition on values of the pixels. Candidate peteye pixel areas are identified in the classification map. The generating and the identifying processes are repeated with the respective condition replaced by a different respective segmentation condition on the pixel values.
摘要翻译： Peteye是出现在用闪光照相机拍摄的图像中出现的动物中的不自然着色（不一定是红色）的瞳孔的出现。描述了检测和修正peteye的系统和方法。在一个方面，基于对像素的值的相应分割条件来生成将输入图像中的像素分割成peteye像素和非peteye像素的分类图。候选peteye像素区域在分类图中被识别。重复生成和识别处理，其中各个条件由像素值上的不同的相应分割条件替换。

6. 发明申请

US20060181614A1 Providing optimized digital images 有权
公开(公告)号：US20060181614A1
公开(公告)日：2006-08-17
申请号：US11060526
申请日：2005-02-17
申请人： Jonathan Yen , Mei Chen , Ramin Samadani , Pere Obrador , Huitao Luo
发明人： Jonathan Yen , Mei Chen , Ramin Samadani , Pere Obrador , Huitao Luo
IPC分类号： H04N5/228
CPC分类号： H04N5/232
摘要： An exemplary method for providing an optimized digital image comprises obtaining digital image data by a digital image capture device, based on the digital image data, automatically determining at least two setting types, and a plurality of setting values therefor, for capturing a plurality of digital images, automatically capturing the plurality of digital images using the digital image capture device, each image being captured with at least one setting value different than another image, and providing an optimized digital image based on the plurality of digital images. In one exemplary embodiment, the optimized image is selected from the plurality of digital images. In another exemplary embodiment, the optimized image is synthesized based on the plurality of digital images.

7. 发明授权

US07017816B2 Extracting graphical bar codes from template-based documents 失效
标题翻译：从基于模板的文档中提取图形条形码
公开(公告)号：US07017816B2
公开(公告)日：2006-03-28
申请号：US10675026
申请日：2003-09-30
申请人： Jonathan Yen , Jian Fan , Daniel Tretter
发明人： Jonathan Yen , Jian Fan , Daniel Tretter
IPC分类号： G02B26/10
CPC分类号： G06K7/10 , G06K9/2054 , G06K19/06009
摘要： Systems and methods of extracting from an input image a graphical bar code containing graphically encoded information are described. In one aspect, a document template is matched to the input image. The document template is selected from a set of document templates each having a respective predetermined page layout corresponding to a respective document type and including a predetermined graphical bar code location. The input image is cropped based on information relating to the graphical bar code location in the page layout of the document template matched to the input image to produce a cropped graphical bar code candidate for decoding.
摘要翻译：描述从输入图像提取包含图形编码信息的图形条形码的系统和方法。在一个方面，文档模板与输入图像匹配。从一组文档模板中选择文档模板，每个文档模板具有对应于相应文档类型并且包括预定图形条形码位置的相应预定页面布局。基于与输入图像匹配的文档模板的页面布局中的图形条形码位置相关的信息裁剪输入图像，以产生用于解码的剪切图形条形码候选。

8. 发明授权

US06915020B2 Generating graphical bar codes by halftoning with embedded graphical encoding 有权
标题翻译：通过使用嵌入式图形编码进行半色调生成图形条形码
公开(公告)号：US06915020B2
公开(公告)日：2005-07-05
申请号：US10027523
申请日：2001-12-19
申请人： Niranjan Damera-Venkata , Jonathan Yen
发明人： Niranjan Damera-Venkata , Jonathan Yen
IPC分类号： G06T5/00 , G06K7/00 , G06K7/10 , G06K19/06 , H04N1/387 , H04N1/40 , H04N1/405 , G06K9/36
CPC分类号： G06K19/06028 , G06K19/06037
摘要： Systems and methods for generating graphical bar codes (i.e., images that contain inconspicuous graphical modulations that encode embedded information) by halftoning with embedded graphical encoding are described. In one aspect, a graphical bar code is generated by halftoning regions of an original image. The original image regions incorporate errors diffused among regions of the original image and computed based at least in part upon modulations in the graphical bar code corresponding to a graphical encoding of a message. In another aspect, a graphical bar code is decoded by generating a base image having halftone regions representative of an original image. Regions of the base image are compared probabilistically to a set of graphical code words to obtain a sequence of graphical code words corresponding to a graphical encoding of a message. The sequence of graphical code words is decoded to produce a decoded message.
摘要翻译：描述了通过利用嵌入式图形编码进行半色调来生成图形条形码（即，包含编码嵌入信息的不显眼图形调制的图像）的系统和方法。在一个方面，通过对原始图像的区域进行半色调生成图形条形码。原始图像区域包括在原始图像的区域之间扩散的错误，并且至少部分地基于对应于消息的图形编码的图形条形码的调制来计算。在另一方面，通过产生具有表示原始图像的半色调区域的基本图像来对图形条形码进行解码。将基本图像的区域概率地与一组图形代码字进行比较，以获得与消息的图形编码相对应的图形代码字的序列。图形代码字的序列被解码以产生解码的消息。

9. 发明授权

US06724945B1 Correcting defect pixels in a digital image 失效
标题翻译：纠正数字图像中的缺陷像素
公开(公告)号：US06724945B1
公开(公告)日：2004-04-20
申请号：US09578251
申请日：2000-05-24
申请人： Jonathan Yen , Daniel R. Tretter , Truong-Thao Nguyen
发明人： Jonathan Yen , Daniel R. Tretter , Truong-Thao Nguyen
IPC分类号： G06K940
CPC分类号： H04N5/2176 , G06T5/005 , G06T5/20 , G06T2207/10024 , G06T2207/20032 , H04N5/21 , H04N5/772 , H04N5/907 , H04N9/045 , H04N9/646 , H04N19/18 , H04N19/527 , H04N19/593 , H04N19/895
摘要： Systems and methods of correcting one or more defect pixels in a source image are described. The source image is formed from a plurality of pixels each having a respective value. In one scheme, a defect pixel is corrected based upon curvature information computed from pixel values located near the defect pixel. In another scheme, a median pixel value is determined from values of pixels located near a defect pixel, and the defect pixel is corrected based upon the median pixel value.
摘要翻译：描述校正源图像中的一个或多个缺陷像素的系统和方法。源图像由各自具有相应值的多个像素形成。在一个方案中，基于从位于缺陷像素附近的像素值计算的曲率信息来校正缺陷像素。在另一方案中，从位于缺陷像素附近的像素的值确定中值像素值，并且基于中值像素值校正缺陷像素。

10. 发明授权

US06655592B2 Graphically demodulating graphical bar codes without foreknowledge of the original unmodulated base image 有权
公开(公告)号：US06655592B2
公开(公告)日：2003-12-02
申请号：US09975278
申请日：2001-10-10
申请人： Doron Shaked , Avi Levy , Jonathan Yen
发明人： Doron Shaked , Avi Levy , Jonathan Yen
IPC分类号： G06K710
CPC分类号： G06K7/1093 , G06K7/10722 , G06K7/10861 , G06K7/14
摘要： Systems and methods of graphically demodulating a graphical bar code (i.e., an image that contains inconspicuous graphical modulations that encode information embedded in an original base image) are described. The graphical bar code may be graphically demodulated automatically without foreknowledge of the original unmodulated base image, but rather based upon a base image that is derived based upon intrinsic features of the graphical bar code.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式