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
    • 1. 发明专利
    • Image detection device and image detection method
    • 图像检测装置和图像检测方法
    • JP2010027000A
    • 2010-02-04
    • JP2008191316
    • 2008-07-24
    • Sony Corpソニー株式会社
    • SUZUKI YOSHIHIRO
    • G06T1/00
    • PROBLEM TO BE SOLVED: To track and detect a seamless face by using an inspection processing speed that follows the frame of a moving image in order to clearly photograph a moving image that changes with time.
      SOLUTION: This image detection device includes a scaling part 201 for expanding or reducing image data on a screen, an image detecting part 203 for detecting a specific image in image data subjected to scaling processing by scanning a rectangular area of a prescribed size on the screen provided with a plurality of sections horizontally, or horizontally and vertically, wherein the image data obtained by the scaling part includes the plurality of sections having the prescribed number of pixels, a candidate area processing part 204 for setting a detection likelihood value corresponding to the degree of overlap of the sections of the screen of the specified image obtained by the detection, and a storing part 202 for storing the set detection likelihood value.
      COPYRIGHT: (C)2010,JPO&INPIT
    • 要解决的问题:通过使用跟随运动图像的帧的检查处理速度来跟踪和检测无缝面,以便清楚地拍摄随时间变化的运动图像。 解决方案:该图像检测装置包括用于在屏幕上展开或缩小图像数据的缩放部分201,用于通过扫描规定尺寸的矩形区域来检测经过缩放处理的图像数据中的特定图像的图像检测部分203 在水平或水平和垂直地设置有多个部分的屏幕上,其中由缩放部分获得的图像数据包括具有规定数量的像素的多个部分;候选区域处理部分204,用于将检测似然度值对应 到通过检测获得的指定图像的屏幕部分的重叠程度,以及用于存储设置的检测似然值的存储部分202。 版权所有(C)2010,JPO&INPIT
    • 2. 发明专利
    • Unit, method and program for image processing, imaging unit, and control method for imaging unit
    • 图像处理单元,方法和程序,成像单元和成像单元的控制方法
    • JP2009110486A
    • 2009-05-21
    • JP2007285022
    • 2007-11-01
    • Sony Corpソニー株式会社
    • SUZUKI YOSHIHIROFUKUDA KYOKO
    • G06T1/00
    • G06K9/00228H04N1/2166H04N5/232H04N5/23219H04N2101/00
    • PROBLEM TO BE SOLVED: To detect a face in an imaged image with higher accuracy.
      SOLUTION: To face candidate image data in a rectangular area F31 being read out from a face candidate database, with the provision of an identity decision frame F30 having distances of widths M respectively in the horizontal and vertical directions, it is decided whether rectangular area image data decided as duplication are included in the identity decision frame F30. When the image data in the rectangular area F32 decided as duplication are included in the identity decision frame F30, the image data in the rectangular area F32 is a rectangular area image data relative to the same face as in the face candidate image data of the rectangular area F31. On the other hand, when the image data in the rectangular area F33 decided as duplication is not included in the identity decision frame F30, it is decided that the image data in the rectangular area F33 is either different from the rectangular area image data relative to the same face as in the face candidate image data of the rectangular area F31, or a rectangular area image data having low degree of certainty.
      COPYRIGHT: (C)2009,JPO&INPIT
    • 要解决的问题:以更高的精度检测成像图像中的脸部。 解决方案:为了面对从面部候选数据库读出的矩形区域F31中的候选图像数据,通过分别在水平和垂直方向上提供具有宽度M的距离的身份确定帧F30,确定是否 被确定为重复的矩形区域图像数据被包括在身份确定帧F30中。 当决定为复制的矩形区域F32中的图像数据被包括在身份确定帧F30中时,矩形区域F32中的图像数据是相对于矩形的面部候选图像数据中的相同脸部的矩形区域图像数据 区域F31。 另一方面,当确定为复制的矩形区域F33中的图像数据不包括在身份确定帧F30中时,确定矩形区域F33中的图像数据与相对于矩形区域F33的矩形区域图像数据不同 与矩形区域F31的面部候选图像数据相同的面,或具有低确定性的矩形区域图像数据。 版权所有(C)2009,JPO&INPIT
    • 3. 发明专利
    • Image processor, imaging device, image processing method, and program
    • 图像处理器,成像装置,图像处理方法和程序
    • JP2009009198A
    • 2009-01-15
    • JP2007167415
    • 2007-06-26
    • Sony Corpソニー株式会社
    • FUKUDA KYOKOSUZUKI YOSHIHIROKINOSHITA HIROMASAYONEDA YUTAKA
    • G06T1/00G06T7/00H04N5/225H04N5/232
    • G06K9/00234G06K9/6212H04N5/23219
    • PROBLEM TO BE SOLVED: To improve a real-time property by reducing an amount of computation of subject detection.
      SOLUTION: A resolution converting unit 210 gradually reduces a photographed image. An image cut-out unit 220 cuts out a window image from a reduced image to hold it in a window memory 230. A frequency analysis unit 250 analyzes a frequency component of the window image. A brightness component analysis unit 260 analyzes a brightness component of the window image. A color component analysis unit 270 analyzes a color component of the window image. A subject candidate determining unit 280 determines whether or not the window image is a subject candidate on the basis of each of the analysis results. As a result, if the window image is the candidate, a face detection control unit 290 makes a subject detection unit 240 execute subject detection from the window image. Meanwhile, if the window image is not the candidate, the control unit 290 does not make the detection unit 240 execute the subject detection.
      COPYRIGHT: (C)2009,JPO&INPIT
    • 要解决的问题:通过减少对象检测的计算量来提高实时性。 解决方案:分辨率转换单元210逐渐减少拍摄的图像。 图像切出单元220从缩小图像中切出窗口图像以将其保持在窗口存储器230中。频率分析单元250分析窗口图像的频率分量。 亮度分量分析单元260分析窗口图像的亮度分量。 颜色分量分析单元270分析窗口图像的颜色分量。 被摄体候选者确定单元280基于每个分析结果来确定窗口图像是否是主题候选。 结果,如果窗口图像是候选者,则面部检测控制单元290使被摄体检测单元240从窗口图像执行被摄体检测。 同时,如果窗口图像不是候选者,则控制单元290不使检测单元240执行被摄体检测。 版权所有(C)2009,JPO&INPIT
    • 5. 发明专利
    • Image signal processor and processing method
    • 图像信号处理器和处理方法
    • JP2006140572A
    • 2006-06-01
    • JP2004326223
    • 2004-11-10
    • Sony Corpソニー株式会社
    • UEDA HIROYUKISUZUKI YOSHIHIRO
    • H04N7/01
    • PROBLEM TO BE SOLVED: To provide image signal processor and processing method in which interlace progressive conversion can be carried out with high precision even when the image size changes for every field. SOLUTION: The image signal processor comprises a read control circuit 17 for receiving an interlace signal having an image size changing for every field and adding extra data dependent on the image data in the vicinity of the border region of an inputted field to a region smaller than a set image size when the image data of a field having an image size smaller than that set for each field is inputted thus generating the image data of a field having the set image size, and a DSP 11 performing movement detection processing based on the image data of a field having an image size set by the read control circuit 17, generating interpolation data based on the results of movement detection processing and performing IP conversion of the image data based on the interpolation data. COPYRIGHT: (C)2006,JPO&NCIPI
    • 要解决的问题:提供图像信号处理器和处理方法,其中即使每个场的图像尺寸变化,也可以以高精度执行交错渐进转换。 解决方案:图像信号处理器包括一个读取控制电路17,用于接收具有每个场变化的图像尺寸的隔行扫描信号,并且将依赖于输入场边界附近的图像数据的附加数据加到一个 输入图像尺寸小于为每个场设定的图像尺寸的图像数据的图像数据小于设定图像尺寸的区域,从而生成具有设定图像尺寸的场的图像数据,并且执行基于运动检测处理的DSP 11 在具有由读取控制电路17设置的图像尺寸的场的图像数据上,基于移动检测处理的结果生成插值数据,并且基于插值数据执行图像数据的IP转换。 版权所有(C)2006,JPO&NCIPI
    • 6. 发明专利
    • Image processing device
    • 图像处理装置
    • JP2006072658A
    • 2006-03-16
    • JP2004254781
    • 2004-09-01
    • Sony Corpソニー株式会社
    • SHIMURA KATSUJIYAMANAKA KATSUHIKOSUZUKI YOSHIHIRO
    • G06T1/60
    • PROBLEM TO BE SOLVED: To issue access requests at a frequency depending on a throughput requested by a client without complicating hardware (client) that issues access requests.
      SOLUTION: An image processing device has a clock thinning control block 10 for optimizing a bandwidth request for access requests to a memory by distributing the frequency of access requests within a specified period according to the size of image data to be processed by the access requests and processing time allowable to complete the processing.
      COPYRIGHT: (C)2006,JPO&NCIPI
    • 要解决的问题:根据客户端请求的吞吐量发送访问请求,而不会使发生访问请求的硬件(客户端)复杂化。 解决方案:图像处理装置具有时钟稀疏控制块10,用于通过在指定的时间段内分配访问请求的频率来根据要处理的图像数据的大小来分配对存储器的访问请求的带宽请求, 访问请求和处理时间可以完成处理。 版权所有(C)2006,JPO&NCIPI
    • 7. 发明专利
    • Method and device for data processing
    • 用于数据处理的方法和装置
    • JP2003009095A
    • 2003-01-10
    • JP2001186314
    • 2001-06-20
    • Sony Corpソニー株式会社
    • YAMAMOTO YOSUKETOMITA MITSUHIKOSUMIOKA TETSUJISUZUKI YOSHIHIRO
    • H04H20/00H04H40/18H04N5/44H04N7/025H04N7/03H04N7/035H04H1/00
    • PROBLEM TO BE SOLVED: To manage a decoding and reproducing time without burden on a host CPU when data such as captions transmitted by the stream of an MPEG2 are decoded and reproduced.
      SOLUTION: An event generation timing control circuit 36 constituted of an event generation time register 61, an STC time register 62 and a comparison circuit 63 gives an interruption signal to the host CPU 1 when relation between a reference time STC and an event generation time REF
      - TIME becomes (STC >=REF
      - TIME). The host CPU 1 is triggered by the interruption signal and the subtitles are reproduced. Thus, the host CPU 1 is operated for another processing till the interruption signal is inputted after setting interruption permission so that burden on the host CPU is reduced when the captions are displayed.
      COPYRIGHT: (C)2003,JPO
    • 要解决的问题:当解码和再现由MPEG2的流传输的诸如字幕的数据时,管理解码和再现时间,而不会对主机CPU造成负担。 解决方案:当事件产生时间寄存器61,STC时间寄存器62和比较电路63构成的事件产生定时控制电路36在基准时间STC和事件发生时间REF之间的关系时向主机CPU 1发出中断信号 - TIME变为(STC> = REF- TIME)。 主机CPU 1由中断信号触发,字幕被再现。 因此,在设置中断许可之后,主机CPU 1进行另一处理,直到输入了中断信号,从而当显示字幕时,主机CPU的负担减小。
    • 8. 发明专利
    • Imaging system, processing method for the imaging system, and program for making computer execute the processing method
    • 成像系统,成像系统的处理方法和程序,用于制作计算机执行处理方法
    • JP2007004313A
    • 2007-01-11
    • JP2005181320
    • 2005-06-21
    • Sony Corpソニー株式会社
    • OKADA MIYUKISUZUKI YOSHIHIRO
    • G06T7/00G06T1/00H04N5/232H04N101/00
    • H04N5/232G06K9/00228G06K9/3208H04N5/23245H04N5/23293
    • PROBLEM TO BE SOLVED: To provide an imaging system capable of effectively detecting a face section from image data at high speed.
      SOLUTION: In the imaging system, a monitoring mode search direction instruction section 330 gives search directions of the image data for face detection to an instruction selecting section 350, on the basis of the searching directions or the like, included in detected results of the face section in the image data of the former frame or a frame positioned in front of a few frames, which is stored in a face detection results RAM 110. A capture mode search direction instructing section 340 gives search directions of the image data to the instruction selecting section 350 for detection of a predetermined face. When signals, instructing recording of the image data, are output from a control section 111, the instruction selecting section 350 conveys the search directions, given from the capture mode searching direction instructing section 340 to a face detection control section 250; and when the signals are not outputted, it conveys the searching directions given from the monitoring mode search direction instruction section 330 to the face detection control section 250.
      COPYRIGHT: (C)2007,JPO&INPIT
    • 要解决的问题:提供一种能够高速地从图像数据有效地检测面部部分的成像系统。 解决方案:在成像系统中,监视模式搜索方向指令部分330根据检测结果中包含的搜索方向等,向面向指令选择部分350提供用于面部检测的图像数据的搜索方向 前面的帧的图像数据中的面部区域或位于几帧前方的帧,存储在面部检测结果RAM 110中。捕获模式搜索方向指示部分340将图像数据的搜索方向 用于检测预定面的指示选择部350。 当从控制部111输出指示图像数据的记录的信号时,指示选择部350将从捕捉模式搜索方向指示部340给出的搜索方向传送到面部检测控制部250; 并且当没有输出信号时,将从监视模式搜索方向指令部分330给出的搜索方向传送到面部检测控制部分250.(C)2007,JPO&INPIT