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
    • 画像処理装置及び画像処理方法
    • 图像处理装置和图像处理方法
    • JP2015033072A
    • 2015-02-16
    • JP2013163110
    • 2013-08-06
    • 株式会社モルフォMorpho Inc
    • KOBAYASHI MICHIHIROMIURA TAKESHIHIRAGA TADAMOTO
    • H04N5/225G03B15/00G03B19/07H04N5/232H04N5/335H04N5/367
    • 【課題】歩留まりの低下を防止しながら、レンズ及びイメージセンサからなるカメラを複数配列することにより高解像度の画像を取得する。【解決手段】画像処理装置1は、レンズ及びイメージセンサからなるカメラモジュールを複数含むカメラアレイ2と、カメラアレイ2の各カメラモジュールから出力される複数の画像を合成して合成画像を出力する出力部3とを備える。カメラアレイ2は、複数のカメラモジュールからなるモジュールブロック21を複数含む。一のモジュールブロックに含まれる複数のカメラモジュールのレンズは略同方向の光軸を有するので、それらのカメラモジュール22から出力される複数の画像に基づき、いわゆる超解像の画像を生成できる。各モジュールブロック21の光軸方向が互いに異なるので、モジュールブロック21ごとの超解像画像をスティッチング処理により合成して広範囲な画像を出力できる。【選択図】図1
    • 要解决的问题:通过排列由透镜和图像传感器形成的多个相机来获取高分辨率图像,同时防止产量降低。解决方案:图像处理装置1包括:相机阵列2,包括多个 每个由透镜和图像传感器形成的相机模块; 以及输出部分3,用于通过组合从相机阵列2的相机模块输出的多个图像来输出合成图像。相机阵列2包括由多个相机模块形成的多个模块21。 由于包括在一个模块中的多个相机模块的透镜具有基本上在相同方向上的光轴,所以可以基于从这些相机模块22输出的多个图像来产生所谓的超分辨率图像。由于 模块21的光轴方向彼此不同,通过缝合处理来合成各模块21的超分辨率图像,能够输出宽幅图像。
    • 2. 发明专利
    • Image synthesizing apparatus, image synthesizing method, image synthesizing program, and recording medium
    • 图像合成装置,图像合成方法,图像合成程序和记录介质
    • JP2013243780A
    • 2013-12-05
    • JP2013175399
    • 2013-08-27
    • Morpho Inc株式会社モルフォ
    • HIRAI YOSHITOMIURA TAKESHI
    • H04N5/235G06T3/00H04N5/225
    • PROBLEM TO BE SOLVED: To provide an image synthesizing apparatus, an image synthesizing method, and an image synthesizing program which are capable of generating an appropriate synthetic image even if a subject moves, and to provide a recording medium with the image synthesizing program stored thereon.SOLUTION: The apparatus generates a synthetic image using a first image and a second image different in exposure condition. The apparatus comprises an image input unit 10, a likelihood calculation unit 13, an exposure estimation unit 14, and a synthesizing unit 16. The image input unit 10 receives the first image and the second image. Before the estimation of an exposure transformation function for matching the exposure conditions of the first image and the second image, the likelihood calculation unit 13 calculates the likelihood of a moving subject on the basis of the difference between the first image and the second image. The exposure estimation unit 14 estimates the exposure transformation function on the basis of the likelihood of a moving subject. The synthesis unit 16 synthesizes the first image and the second image using the exposure transformation function.
    • 要解决的问题:提供一种图像合成装置,图像合成方法和图像合成程序,即使对象移动也能够产生合适的合成图像,并且提供其上存储有图像合成程序的记录介质 解决方案:该装置使用不同于曝光条件的第一图像和第二图像来生成合成图像。 该装置包括图像输入单元10,似然率计算单元13,曝光估计单元14和合成单元16.图像输入单元10接收第一图像和第二图像。 在估计用于匹配第一图像和第二图像的曝光条件的曝光变换功能之前,似然度计算单元13基于第一图像和第二图像之间的差来计算移动被摄体的可能性。 曝光估计单元14基于移动的被摄体的可能性来估计曝光变换功能。 合成单元16使用曝光变换功能合成第一图像和第二图像。
    • 3. 发明专利
    • Image similarity calculation device, image similarity calculation method, image similarity calculation program, and recording medium
    • 图像相似计算设备,图像相似性计算方法,图像相似度计算程序和记录介质
    • JP2013054529A
    • 2013-03-21
    • JP2011192048
    • 2011-09-02
    • Morpho Inc株式会社モルフォ
    • MIURA TAKESHI
    • G06T7/00
    • PROBLEM TO BE SOLVED: To provide an image similarity calculation device capable of determining that images under inversion relation are resembled, an image similarity calculation method, an image similarity calculation program, and a recording medium.SOLUTION: An image similarity calculation device 1 calculates similarity between an input image 30 and a reference image 31. This device includes a local feature amount extraction part 12, and a similarity calculation part 14. The local feature amount extraction part 12 acquires feature points of the input image 30 and the reference image 31, and describes feature amounts that are invariable with respect to rotation and inversion for every feature point of the input image 30 and the reference image 31. The similarity calculation part 14 calculates the similarity between the input image 30 and the reference image 31 on the basis of the feature amount for every feature point of the input image 30 and the reference image 31.
    • 要解决的问题:提供能够确定反转关系下的图像相似的图像相似度计算装置,图像相似度计算方法,图像相似度计算程序和记录介质。 图像相似度计算装置1计算输入图像30和参考图像31之间的相似度。该装置包括局部特征量提取部分12和相似度计算部分14.局部特征量提取部分12获取 输入图像30和参考图像31的特征点,并且描述对于输入图像30和参考图像31的每个特征点相对于旋转和反转不变的特征量。相似度计算部14计算 输入图像30和参考图像31,基于输入图像30的每个特征点的特征量和参考图像31.(C)2013,JPO和INPIT
    • 4. 发明专利
    • Image identification device, image identification method, image identification program and recording medium
    • 图像识别装置,图像识别方法,图像识别程序和记录介质
    • JP2012243197A
    • 2012-12-10
    • JP2011114665
    • 2011-05-23
    • Morpho Inc株式会社モルフォNtt Docomo Inc株式会社エヌ・ティ・ティ・ドコモ
    • TANASE YASUSHIMIURA TAKESHITODOROKI YASUHIROSHIINO HIROKIHABUKA KANESUKEHAMADA TETSUYAYASUDA YASUYO
    • G06T7/00H04N5/232H04N101/00
    • G06K9/00684G06F17/3025G06K9/4642
    • PROBLEM TO BE SOLVED: To provide an image identification device capable of improving accuracy in categorizing a block image.SOLUTION: An image identification device 1, which uses a separate plane to categorize a block image, comprises: a target image input unit 10 to which a target image is inputted; a block image generation unit 11 for generating a block image; a feature amount operation unit 12 for operating a feature amount of the block image; and a category determination unit 13 for determining whether or not the block image is categorized. The feature amount operation unit 12, by not only using a local feature amount of the block image and the whole feature amount of the whole target image but also using a coordinate position of a feature amount vector, which is formed by combining multiple local feature amounts in a second feature amount space with multiple features of the block image set as coordinate axes, and one or more arbitrary areas in the second feature amount space, includes the number of block images, which is obtained through area-by-area counting of the block images with the feature amount vector belonging to the area, in the whole feature amount.
    • 要解决的问题:提供能够提高对块图像进行分类的精度的图像识别装置。 解决方案:使用单独的平面对块图像进行分类的图像识别装置1包括:输入目标图像的目标图像输入单元10; 块图像生成单元11,用于生成块图像; 用于操作块图像的特征量的特征量操作单元12; 以及用于确定块图像是否被分类的类别确定单元13。 特征量操作单元12通过不仅使用块图像的局部特征量和整个目标图像的整体特征量,而且使用通过组合多个局部特征量形成的特征量向量的坐标位置 在具有设置为坐标轴的块图像的多个特征的第二特征量空间和第二特征量空间中的一个或多个任意区域中,包括通过逐区域计数获得的块图像的数量 在特征量的整个特征量中具有属于该区域的特征量矢量的图像。 版权所有(C)2013,JPO&INPIT
    • 5. 发明专利
    • Partial expansion method for compressed image and image processor
    • 压缩图像和图像处理器的部分扩展方法
    • JP2011188041A
    • 2011-09-22
    • JP2010048478
    • 2010-03-04
    • Morpho Inc株式会社モルフォ
    • HIRAGA TADAMOTONAKA KUNIHIRONISHIYAMA TAKAYUKIMIURA TAKESHINAKAYAMA KAZUHIRO
    • H04N1/41H04N19/00H04N19/44H04N19/59H04N19/625H04N19/91
    • G06F3/0482G06T1/0007G06T1/60G06T3/40G06T3/4092G06T9/00G06T2200/16G06T2200/24H04N19/17H04N19/176H04N19/46H04N19/59H04N19/60H04N19/70
    • PROBLEM TO BE SOLVED: To provide a partial expansion method for a compressed image, capable of suppressing the processing cost at a CPU for partial expansion, and quickly responding to a user operation to display a high-quality image on a screen when partial expansion processing and screen display are performed. SOLUTION: The partial expansion method for a compressed image comprises the step of: generating a reduced image according to the screen size of a display device while generating map data required for decompressing a compressed image in unit of macro block; associating the generated map data and the reduced image with the compressed image for storage; outputting the reduced image associated with the compressed image to the display device based on an image manipulation request; specifying a macro block to be decompressed within a display range of the reduced image; partially decompressing the specified macro block within the compressed image using the map data; and outputting an image within the display range to the display device among images thus decompressed partially. COPYRIGHT: (C)2011,JPO&INPIT
    • 要解决的问题:为了提供压缩图像的部分扩展方法,能够抑制CPU部分扩展的处理成本,并且能够快速响应用户操作以在屏幕上显示高质量图像, 进行部分扩展处理和画面显示。 解决方案:压缩图像的部分扩展方法包括以下步骤:根据显示设备的屏幕尺寸生成缩小图像,同时生成以宏块为单位解压缩压缩图像所需的地图数据; 将生成的地图数据和缩小图像与压缩图像相关联以进行存储; 基于图像操作请求将与压缩图像相关联的缩小图像输出到显示设备; 指定在缩小图像的显示范围内解压缩的宏块; 使用地图数据部分地解压缩压缩图像内的指定宏块; 并且将显示范围内的图像输出到显示装置,从而部分地解压缩。 版权所有(C)2011,JPO&INPIT
    • 6. 发明专利
    • Image processing method and image processor
    • 图像处理方法和图像处理器
    • JP2010157163A
    • 2010-07-15
    • JP2008335867
    • 2008-12-31
    • Morpho Inc株式会社モルフォ
    • HIRAGA TADAMOTOHABUKA KANESUKEMIURA TAKESHI
    • G06T5/20H04N1/409
    • G06T5/002G06T5/20G06T7/13G06T2207/20012G06T2207/20016G06T2207/20192
    • PROBLEM TO BE SOLVED: To remove low-frequency noise without imposing a load on a computer while holding edge information of a digital image. SOLUTION: This image processing method includes: a step of creating a shrunken image of a shrinking ratio rate r by averaging pixel values of an source image in each block of r pixels×r pixels (r: a natural number) with a filter target image as the source image; a step of obtaining a pixel value on the shrunken image corresponding to a focus pixel on the source image from a pixel on the shrunken image by linear interpolation; a step of determining a filter applied to a point corresponding to a focus pixel on the shrunken image from a reference pixel and the focus pixel on the shrunken image; and a step of determining a pixel value after correction of the focus pixel of the source image based on a pixel value obtained by applying the filter to the focus pixel of the source image, and a pixel value obtained by applying the filter to the focus pixel of the shrunken image. COPYRIGHT: (C)2010,JPO&INPIT
    • 要解决的问题:在保持数字图像的边缘信息的同时,不要在计算机上施加负载来移除低频噪声。 解决方案:该图像处理方法包括:通过对r个像素×r个像素(r:自然数)的每个块中的源图像的像素值进行平均来创建缩小比率r的缩小图像的步骤 过滤目标图像作为源图像; 通过线性插值从缩小图像上的像素获得与源图像上的聚焦像素对应的缩小图像上的像素值的步骤; 确定从参考像素和缩小图像上的焦点像素应用于与缩小图像上的焦点像素相对应的点的滤波器的步骤; 以及基于通过将滤波器应用于源图像的焦点像素而获得的像素值,以及通过将滤波器应用于聚焦像素而获得的像素值来确定源图像的聚焦像素的校正后的像素值的步骤 的缩影形象。 版权所有(C)2010,JPO&INPIT
    • 7. 发明专利
    • Image processing apparatus, image processing method, image processing program, and recording medium
    • 图像处理设备,图像处理方法,图像处理程序和记录介质
    • JP2014086097A
    • 2014-05-12
    • JP2014020497
    • 2014-02-05
    • Morpho Inc株式会社モルフォ
    • SAWAI SHOGOHIRAGA TADAMOTOMIURA TAKESHI
    • G06T3/00G06T7/60
    • PROBLEM TO BE SOLVED: To provide an image processing apparatus configured to prevent accumulation of errors to obtain a high-quality panoramic image even if an image captured from a different direction is included when input images are sequentially joined.SOLUTION: An image processing apparatus includes an input unit, a selection unit, a matching unit, an estimation unit, and a synthesis unit. The input unit sequentially inputs images. The selection unit selects a reference image from the input images. The matching unit calculates correspondence relation between a feature point of the reference image and a feature point of a target image. The estimation unit estimates a transformation for associating a coordinate system of the reference image with the coordinate system of the target image, by use of position information of a pair of feature points whose correspondence relation has been calculated by the matching unit, on the assumption that motion between the reference image and the target image is only rotation of an imaging element. The synthesis unit generates a synthetic image by combining the input images with the target image on the basis of the transformation.
    • 要解决的问题:提供一种图像处理装置,其被配置为即使当输入图像顺序连接时,包括从不同方向拍摄的图像时,也可以防止错误的积累以获得高质量的全景图像。解决方案:图像处理装置包括 输入单元,选择单元,匹配单元,估计单元和合成单元。 输入单元依次输入图像。 选择单元从输入图像中选择参考图像。 匹配单元计算参考图像的特征点与目标图像的特征点之间的对应关系。 估计单元通过使用由匹配单元计算其对应关系的一对特征点的位置信息来估计用于将参考图像的坐标系与目标图像的坐标系相关联的变换,假设 参考图像和目标图像之间的运动仅仅是成像元件的旋转。 合成单元通过基于变换将输入图像与目标图像组合来生成合成图像。
    • 8. 发明专利
    • Image processing apparatus, image processing method and image processing program
    • 图像处理设备,图像处理方法和图像处理程序
    • JP2013190947A
    • 2013-09-26
    • JP2012056154
    • 2012-03-13
    • Morpho Inc株式会社モルフォ
    • HIRAGA TADAMOTOMIURA TAKESHITAKADA KAZUKI
    • G06T7/20G06T19/00
    • PROBLEM TO BE SOLVED: To provide an image processing apparatus, an image processing method and an image processing program which are capable of appropriately computing a correspondence relationship between images.SOLUTION: An image processing apparatus includes a feature point acquiring section 111, a movement computing section 112, a movement acquiring section 113 and a reliability determining section 114. The feature point acquiring section 111 acquires a feature point of an image. The movement computing section 112 computes a degree of a feature point movement for each pixel position in a search range on the basis of a difference in pixel value between images. The movement acquiring section 113 acquires the minimum movement as the feature point movement. The reliability determining section 114 determines reliability of the feature point movement on the basis of whether or not a pixel position having the N-th (N is an integer of 2 or more) smallest movement and at least one pixel position among pixel positions having movement smaller than the N-th smallest movement are adjacent to each other.
    • 要解决的问题:提供能够适当地计算图像之间的对应关系的图像处理装置,图像处理方法和图像处理程序。解决方案:图像处理装置包括特征点获取部分111,移动计算 部分112,移动获取部分113和可靠性确定部分114.特征点获取部分111获取图像的特征点。 运动计算部112基于图像之间的像素值的差异,计算搜索范围内的每个像素位置的特征点移动的程度。 移动获取部113获取作为特征点移动的最小移动。 可靠性确定部分114基于具有第N个(N是2或更大的整数)的像素位置和运动的像素位置中的至少一个像素位置,确定特征点移动的可靠性 小于第N个最小的运动彼此相邻。
    • 9. 发明专利
    • Image synthesizer, image synthesizing method, image synthesis program, and recording medium
    • 图像合成器,图像合成方法,图像合成程序和记录介质
    • JP2013102554A
    • 2013-05-23
    • JP2013042040
    • 2013-03-04
    • Morpho Inc株式会社モルフォ
    • HIRAI YOSHITOMIURA TAKESHI
    • H04N5/235H04N5/232
    • PROBLEM TO BE SOLVED: To provide an image synthesizer for generating an appropriate synthesis image even if a subject moves, and to provide an image synthesizing method, an image synthesis program, and a recording medium storing the image synthesis program.SOLUTION: An image synthesizer generates a synthesis image by using a first image and a second image, which are different in an exposure condition. The synthesizer includes: an image input section 10; a likelihood calculation section 13; an exposure estimating section 14; and a synthesizing section 16. The image input section 10 inputs the first image and the second image. The likelihood calculation section 13 calculates moving subject likelihood for each pixel in response to a difference between the first image and the second image. The exposure estimating section 14 estimates an exposure conversion function for adjusting the exposure conditions of the first image and the second image in response to the moving subject likelihood. The synthesizing section 16 synthesizes the first image and the second image by using the exposure conversion function.
    • 要解决的问题:即使对象移动来提供用于生成合适的合成图像的图像合成器,并且提供图像合成方法,图像合成程序和存储图像合成程序的记录介质。 解决方案:图像合成器通过使用曝光条件不同的第一图像和第二图像来生成合成图像。 合成器包括:图像输入部分10; 似然度计算部13; 曝光估计部14; 和合成部分16.图像输入部分10输入第一图像和第二图像。 似然度计算部13响应于第一图像和第二图像之间的差异来计算每个像素的运动对象似然性。 曝光估计部分14估计用于响应于运动的被摄体可能性来调整第一图像和第二图像的曝光条件的曝光转换功能。 合成部分16通过使用曝光转换功能来合成第一图像和第二图像。 版权所有(C)2013,JPO&INPIT
    • 10. 发明专利
    • Image identification device, image identification method, image identification program and recording medium
    • 图像识别装置,图像识别方法,图像识别程序和记录介质
    • JP2012243196A
    • 2012-12-10
    • JP2011114660
    • 2011-05-23
    • Morpho Inc株式会社モルフォ
    • TANASE YASUSHIMIURA TAKESHITODOROKI YASUHIROSHIINO HIROKIHABUKA KANESUKE
    • G06T7/00H04N5/232H04N101/00
    • G06K9/4642G06K9/00684
    • PROBLEM TO BE SOLVED: To provide an image identification device capable of improving accuracy in classifying a block image that is obtained by dividing a target image.SOLUTION: An image identification device 1, which uses an already-learned separate plane to categorize a block image, according to each preset category, that is obtained by dividing a target image, comprises: a target image input unit 10 to which the target image is inputted; a block image generation unit 11 for dividing the target image into multiple blocks and generating multiple block images; a feature amount operation unit 12 for operating a feature amount of each block image; and a category determination unit 13 for using a coordinate position corresponding to a size of the feature amount of each block image in a feature amount space and the separate plane to determine whether or not each block image is categorized. The feature amount operation unit 12 uses a local feature amount calculated from image information for the block image and the whole feature amount calculated from the image information for the whole target image, as the feature amount of the block image.
    • 要解决的问题:提供能够提高通过划分目标图像而获得的块图像的分类精度的图像识别装置。 解决方案:根据通过划分目标图像获得的每个预设类别,使用已经学习的单独平面来对块图像进行分类的图像识别装置1包括:目标图像输入单元10,目标图像输入单元10 输入目标图像; 块图像生成单元11,用于将目标图像划分为多个块并生成多个块图像; 用于操作每个块图像的特征量的特征量操作单元12; 以及类别确定单元13,用于使用与特征量空间中的每个块图像的特征量的大小相对应的坐标位置和分离平面来确定每个块图像是否被分类。 特征量操作单元12使用从块图像的图像信息计算的局部特征量和从整个目标图像的图像信息计算的整体特征量作为块图像的特征量。 版权所有(C)2013,JPO&INPIT