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
    • 3. 发明授权
    • Determination of portrait against back light
    • 确定肖像对背光
    • US07929763B2
    • 2011-04-19
    • US12456405
    • 2009-06-15
    • Toshie Imai
    • Toshie Imai
    • G06K9/00
    • H04N1/6086G06T7/90G06T2207/30201
    • A CPU 200 compares a luminance distribution characteristic of image data with a reference luminance distribution characteristic, and then confirms that the image data GD is a backlit portrait image data if similarity degree Sv between the luminance distribution characteristic of image data and the reference luminance distribution characteristic is larger than reference similarity degree Svref. The CPU 200 determines whether an outer dark portion ratio Do is larger than a reference dark portion ratio Doref. If the CPU 200 determines that the outer dark portion ratio Do is larger than the reference dark portion ratio Doref, then it determines whether an outer bright portion ratio Bo is larger than a reference bright portion ratio Boref. If the CPU 200 determines that the outer bright portion ratio Bo is larger than a reference bright portion ratio Boref, then it determines that the image data GD is image data of backlit portrait image.
    • CPU200将图像数据的亮度分布特性与参考亮度分布特性进行比较,然后如果图像数据的亮度分布特性和参考亮度分布特性之间的相似度Sv相似,则确认图像数据GD是背光肖像图像数据 大于参考相似度Svref。 CPU 200确定外部暗部比例Do是否大于参考暗部比率Doref。 如果CPU 200确定外部暗部比例Do大于参考暗部比Doref,则判定外部亮部比率Bo是否大于基准亮部比率Boref。 如果CPU 200确定外部明亮部分比率Bo大于参考亮度部分比率Boref,则其确定图像数据GD是背光肖像图像的图像数据。
    • 4. 发明授权
    • Backlit image judgment
    • 背光图像判断
    • US07570836B2
    • 2009-08-04
    • US10909069
    • 2004-07-29
    • Toshie Imai
    • Toshie Imai
    • G06K9/40
    • G06T7/0002G06T2207/30168
    • A CPU 200 analyzes inner region pixels IP and outer region pixels OP independently; compares an inner luminance distribution characteristic i.e. a luminance distribution characteristic regarding the inner region pixels IP with a reference inner luminance distribution characteristic regarding image data of a backlit image that is previously stored in a HDD 202; and thereby calculates an inner similarity Si. Similarity, the CPU 200 compares an outer luminance distribution characteristic i.e. a luminance distribution characteristic regarding the outer region pixels OP with a reference outer luminance distribution characteristic, and thereby calculates an outer similarity So. The CPU 200 then calculates a total similarity St by multiplying the calculated inner similarity Si by the outer similarity So. If the total similarity St is greater than a criterion similarity Stref, the CPU 200 judges the shot image to be a backlit image.
    • CPU 200独立地分析内部区域像素IP和外部区域像素OP; 将内部亮度分布特性,即关于内部区域像素IP的亮度分布特性与关于先前存储在HDD 202中的背光图像的图像数据的参考内部亮度分布特性进行比较; 从而计算内部相似度Si。 相似度,CPU200将外部亮度分布特性即外部区域像素OP的亮度分布特性与基准外部亮度分布特性进行比较,从而计算外部相似度So。 然后,CPU200通过将计算的内部相似度Si乘以外部相似度S来计算总相似度St。 如果总相似度St大于标准相似度Stref,则CPU200判断拍摄图像为背光图像。
    • 6. 发明申请
    • Determination of main object on image and improvement of image quality according to main object
    • 主要对象主要对象的确定和图像质量的提高
    • US20050244072A1
    • 2005-11-03
    • US11075380
    • 2005-03-07
    • Toshie Imai
    • Toshie Imai
    • G06K9/00G06K9/40
    • G06K9/00664
    • A CPU 411 splits selected image data GD into a plurality of areas (pixel data groups), analyzing the image data GD in terms of area units, and determining the color range of the areas of the image data GD. The CPU 411 determines color range areas by associating adjacent areas of the same color range when determining the color range for the areas of the image data GD. The CPU 411 acquires position data for the color range areas that have been determined. The CPU 411 acquires position conditions (main object conditions) from ROM/HDD 413, and narrows the main object candidates to “sky, green, or people.” The CPU 411 finally determines the main object by comparing the position data of the color range color areas and the position conditions corresponding to the narrowed main object.
    • CPU 411将所选择的图像数据GD分割成多个区域(像素数据组),以面积单位分析图像数据GD,并确定图像数据GD的区域的颜色范围。 CPU 411在确定图像数据GD的区域的颜色范围时,通过将相同颜色范围的相邻区域相关联来确定颜色范围区域。 CPU 411获取已经确定的颜色范围区域的位置数据。 CPU 411从ROM / HDD 413获取位置条件(主要对象条件),并将主要对象候选变窄为“天空,绿色或人”。 CPU 411最终通过比较颜色范围颜色区域的位置数据和与缩小的主要对象相对应的位置条件来确定主要对象。
    • 8. 发明授权
    • Printing control device and printing control program
    • 打印控制装置和打印控制程序
    • US08474939B2
    • 2013-07-02
    • US13043978
    • 2011-03-09
    • Toshie Imai
    • Toshie Imai
    • B41J2/205
    • H04N1/54C09D11/322G06K15/1867H04N1/2338H04N1/2369
    • The information expressed by an original color image can be visually recognized even if the recording medium on which the color image has been recorded in dye ink is wetted with water. With a printing device equipped with pigment ink and dye ink, in the printing of a color image, the pigment ink corresponding to an image characteristic amount included in the color image is also injected along with the dye ink, so an image expressing the image characteristic amount included in the color image is recorded with the pigment ink, which has excellent water resistance, over the color image printed with the dye ink on the printing medium. Accordingly, in the event that the recording medium becomes wet and the dye ink bleed, the user can still make out the content of the information expressed by the original color image from the image printed in the pigment ink.
    • 即使将已经在染料墨中记录了彩色图像的记录介质用水润湿,也可以视觉识别由原始彩色图像表示的信息。 在配备有颜料墨水和染料墨水的印刷装置中,在彩色图像的印刷中,与彩色图像中包含的图像特征量对应的颜料墨水也与染料墨一起注入,从而形成表现图像特性的图像 通过在印刷介质上用染料墨打印的彩色图像上的颜料墨水记录着包含在彩色图像中的含量,其具有优异的耐水性。 因此,在记录介质变湿并且染料墨水渗漏的情况下,用户仍然可以从印刷在颜料墨中的图像中得出由原始彩色图像表示的信息的内容。
    • 9. 发明授权
    • Brightness correction for image
    • 图像亮度校正
    • US07932930B2
    • 2011-04-26
    • US12319946
    • 2009-01-13
    • Toshie Imai
    • Toshie Imai
    • H04N5/228
    • H04N1/628H04N1/00204H04N1/00278H04N1/6027
    • A CPU determines whether or not a picked up image that corresponds to image data is a backlit portrait image by analyzing the image data on a pixel-by-pixel basis, and if the picked up image that corresponds to the image data is determined to be a backlit portrait image, then executes a brightness correction for backlit portrait image. The CPU obtains a tone curve that may have an output value of a predetermined value FV as an output value in response to an input value of a flesh-colored pixel average luminance value PV ave, which is an average luminance value of flesh-colored pixels of all pixels that constitute the image data. The CPU applies the tone curve to the luminance of every pixel in the image data and thereby executes the brightness correction.
    • CPU通过逐像素地分析图像数据来确定与图像数据相对应的拾取图像是否为背光肖像图像,并且如果将与图像数据对应的拍摄图像确定为 背光的人像图像,然后执行背光肖像图像的亮度校正。 响应于作为肉色像素的平均亮度值的肉色像素平均亮度值PV ave的输入值,CPU获得可以具有作为输出值的预定值FV的输出值的色调曲线 构成图像数据的所有像素。 CPU将色调曲线应用于图像数据中的每个像素的亮度,从而执行亮度校正。