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. 发明授权
    • Image scanner having improved pixel convolution operation
    • 图像扫描器具有改进的像素卷积运算
    • US5272545A
    • 1993-12-21
    • US822231
    • 1992-01-17
    • Kikuo Mita
    • Kikuo Mita
    • G06K9/38G06T5/20H04N1/403H04N1/409H04N5/14
    • H04N1/403H04N1/409
    • An image scanner that can extract the information of interest from a document at high speed, using a relatively small-scale circuit arrangement that provides an image processing performance equal to that obtained by applying convolution to a larger number of pixels. Light reflecting from the document is converted to electrical image signals by a one-dimensional image sensor. After these image signals have been digitized by an A/D converter, they are input to an adder. A portion of the digitized signals is input to a rounding circuit in which the average intensity of a pixel unit, each comprised of a prescribed number of pixel groups, is calculated. These units are treated as pseudo pixels on which convolution is performed by a convolution integrator. A subtracter is then used to obtain the difference between signals input from the A/D converter and signals output by the convolution integrator. This is then used to obtain the difference between the intensity of the pixel of interest and the average intensity of the prescribed number of surrounding pixels to effectively distinguish alphanumeric characters and other such information, from the background.
    • 可以使用提供与通过对较大数量的像素应用卷积获得的图像处理性能相等的相对较小规模的电路布置来高速地从文档中提取感兴趣的信息的图像扫描器。 从文件反射的光被一维图像传感器转换成电子图像信号。 在这些图像信号被A / D转换器数字化之后,它们被输入到加法器。 数字化信号的一部分被输入到舍入电路,其中计算每个包括规定数量的像素组的像素单元的平均亮度。 这些单位被视为由卷积积分器执行卷积的伪像素。 然后使用减法器来获得从A / D转换器输入的信号与由卷积积分器输出的信号之间的差异。 然后将其用于获得感兴趣像素的强度与规定数量的周围像素的平均强度之间的差异,以有效地区分字母数字字符和其他此类信息与背景。
    • 8. 发明授权
    • Multi-resolution image scanner
    • 多分辨率图像扫描仪
    • US5267335A
    • 1993-11-30
    • US822452
    • 1992-01-17
    • Kikuo Mita
    • Kikuo Mita
    • G06K9/38G06K9/60H04N1/409G06K9/00H04N3/14
    • H04N1/4092G06K9/60H04N3/1581
    • An image scanner is provided that receives light reflected from a same position on a document by first, second, and third one-dimensional image sensors arranged in parallel. The second image sensor is a high-resolution image sensor comprising a plurality of photocells, which is disposed between and in a spaced-apart relationship with the first and third one-dimensional image sensors which are each low-resolution image sensors comprising photocells which are larger in size than the photocells of the second one-dimensional image sensor. Electrical image output signals from the first and third low-resolution image sensors are added, and any high-frequency components in the added signal are removed by a low-pass filter for producing signal data relating to the mean brightness of the region around a pixel of interest. The difference between the mean brightness and the brightness of the pixel of interest, as outputted by the second high-resolution image sensor, is then derived to produce an output signal in which points to where the brightness changes in the image are emphasized. Subsequent processing enables textual and other information of interest in the document to be extracted from background information.
    • 提供了一种图像扫描器,其接收由平行布置的第一,第二和第三一维图像传感器接收从文档上的相同位置反射的光。 第二图像传感器是包括多个光电管的高分辨率图像传感器,多个光电管被设置在与第一和第三一维图像传感器之间并且与第一和第三一维图像传感器间隔开的关系中,每个图像传感器是包括光电管的低分辨率图像传感器, 尺寸比第二一维图像传感器的光电池大。 添加来自第一和第三低分辨率图像传感器的电子图像输出信号,并且通过低通滤波器去除相加信号中的任何高频分量,以产生与像素周围的区域的平均亮度有关的信号数据 出于兴趣。 然后导出由第二高分辨率图像传感器输出的感兴趣像素的平均亮度和亮度之间的差异,以产生其中强调图像中亮度变化的点的输出信号。 随后的处理能够从背景信息中提取文档中感兴趣的文本和其他信息。