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 processing device
    • 图像处理装置
    • US06272249B1
    • 2001-08-07
    • US09019813
    • 1998-02-06
    • Setsuya KobayashiTakeshi Murakami
    • Setsuya KobayashiTakeshi Murakami
    • G06K962
    • H04N1/40062
    • The present invention is directed to an image processing device which is capable of discriminating the classification of a particular area of an image at improved accuracy. In an image processing device according to the present invention, an image input from an image signal input portion is processed in the following steps: a vertical and horizontal complexity calculating circuit determines absolute values Tx and Ty of differential densities between pixels neighboring to each other in vertical and horizontal directions, respectively, within a particular area of the image; a diagonal complexity calculating circuit determines absolute values Rx and Ry of differential densities of pixels neighboring to each other in main diagonal and sub diagonal directions, respectively, within the particular area; a comparator circuit compares sums of absolute values in respective directions and outputs a least sum as a complexity to an area discriminating portion; a difference-comparator portion determines a difference between a maximal value Ma and a least value Mi of densities of pixels of the image data and outputs it as a comparison difference value to the area discriminating portion; and the area discriminating portion discriminates the classification of the image area based on the above-mentioned complexity value and comparison difference value.
    • 本发明涉及一种图像处理装置,其能够以更高的精度区分图像的特定区域的分类。 在根据本发明的图像处理装置中,从图像信号输入部分输入的图像在以下步骤中被处理:垂直和水平复杂度计算电路确定彼此相邻的像素之间的差分密度的绝对值Tx和Ty 分别在图像的特定区域内的垂直和水平方向; 对角线复杂度计算电路分别确定特定区域内的主对角线和副对角线方向上彼此相邻的像素的差分密度的绝对值Rx和Ry; 比较器电路对各个方向的绝对值的和进行比较,并将最小值作为复杂度输出到区域识别部分; 差分比较部分确定图像数据的像素密度的最大值Ma和最小值Mi之间的差,并将其作为比较差值输出到区域识别部分; 并且区域识别部分基于上述复杂度值和比较差值来区分图像区域的分类。
    • 2. 发明授权
    • Image-region discriminating method and image-processing apparatus
    • 图像区鉴别方法和图像处理装置
    • US6052484A
    • 2000-04-18
    • US920434
    • 1997-08-29
    • Setsuya Kobayashi
    • Setsuya Kobayashi
    • H04N1/40G06K9/46G06K9/40G06K9/56G06T5/20
    • H04N1/40068
    • A degree of frequency and a comparison difference value are used as an amount of feature that is to be inputted to a discrimination circuit so as to discriminate the kind of regions. The degree of frequency is represented by the smaller of two sums, that is, the sum of absolute values of the density-level difference between pixels adjoining in the line direction of the pixels within the specific region and the sum of absolute values of the density-level difference between pixels adjoining in the direction orthogonal to the line of the pixels, which is obtained by a frequency-degree extracting circuit. Further, the comparison difference value is represented by the comparison difference between a maximum value and a minimum value in the density levels of all pixels within the specified region, which is obtained by the comparison difference circuit. Among a plurality of preset filters, one of the preset filters is selected based upon the amount of feature, and a filtering process is carried out by a filtering-process circuit by using the filter. With this arrangement, discrimination is made as to the kind of region, and a proper filtering process is carried out depending on which region, among the character region, photograph region and halftone-dot region, each focused pixel in an image that has been read belongs to.
    • 使用频率和比较差值作为要被输入到鉴别电路的特征量,以区分区域的种类。 频率的程度由两个和值中的较小者表示,即,在特定区域内的像素的行方向上相邻的像素之间的浓度级差的绝对值与密度的绝对值的和之和 在通过频率度提取电路获得的与像素线垂直的方向上邻接的像素之间的差异。 此外,比较差值由比较差电路获得的特定区域内的所有像素的浓度水平的最大值和最小值之间的比较差表示。 在多个预设滤波器中,基于特征量选择预设滤​​波器之一,并且通过使用滤波器由滤波处理电路执行滤波处理。 利用这种布置,区分区域的种类,并且根据字符区域,照片区域和半色调点区域中哪个区域,读取的图像中的每个聚焦像素进行适当的滤波处理 属于。
    • 3. 发明授权
    • Image processing circuit
    • 图像处理电路
    • US06163624A
    • 2000-12-19
    • US95373
    • 1998-06-10
    • Setsuya Kobayashi
    • Setsuya Kobayashi
    • H04N1/40G06K9/46
    • H04N1/40062
    • An image processing circuit of the present invention includes a succession calculating circuit. In the succession calculating circuit, an average value calculating circuit determines an average value of image data, inputted via line memories, in a specific region, and a multivalue-binary converting circuit converts, in accordance with the average value, the image data into binary data in which the entire image data in the specific region are separated into black pixels and white pixels. A succeeding black pixels calculating circuit calculates the number of succeeding black pixels each in a main scanning direction and in a sub scanning direction, and determines respective maximum values in the main scanning direction and in the sub scanning direction so as to output the respective maximum values as a main scanning direction maximum succession and a sub scanning direction maximum succession. The types of the specific region including the target pixel are discriminated in accordance with the succession, a complexity, and a compared subtracted value so as to carry out an image process in accordance with image types, thus improving discrimination accuracy of image features, used for selecting of an image process which should be carried out, without causing the size of the circuit to increase.
    • 本发明的图像处理电路包括一个连续计算电路。 在连续计算电路中,平均值计算电路确定在特定区域中通过行存储器输入的图像数据的平均值,并且多值二进制转换电路根据平均值将图像数据转换为二进制 将特定区域中的整个图像数据分成黑色像素和白色像素的数据。 随后的黑色像素计算电路计算主扫描方向和副扫描方向上的后续黑色像素的数量,并且确定主扫描方向和副扫描方向上的各个最大值,以输出各自的最大值 作为主扫描方向最大连续和副扫描方向最大连续。 根据继承,复杂度和比较的减去值来区分包括目标像素的特定区域的类型,以便根据图像类型执行图像处理,从而提高图像特征的辨别精度, 选择应该进行的图像处理,而不会导致电路的尺寸增加。
    • 4. 发明授权
    • Image-processing apparatus and image-processing method
    • 图像处理装置和图像处理方法
    • US06631210B1
    • 2003-10-07
    • US09414736
    • 1999-10-08
    • Takeshi MutohSetsuya KobayashiTakayuki AmagaiSeiji KohashikawaTakahiro Daido
    • Takeshi MutohSetsuya KobayashiTakayuki AmagaiSeiji KohashikawaTakahiro Daido
    • G06K934
    • H04N1/56H04N1/40062
    • An image-processing apparatus, as well as an image-processing method, is provided with a first inspection circuit which, with respect to density values of pixels within a specific area consisting of a target pixel and pixels in a vicinity thereof in image data for each color component, calculates an average density value, the sum of density differences, that is, the sum of absolute values of differences between the target pixel and the peripheral pixels, and the number the peripheral pixels having the same density value as the target pixel, so that a judgement is made as to whether the target pixel is a maximum value or a minimum value, and also calculates a run-length and the degree of busy from the pixel forming the maximum value or the minimum value. Moreover, based on the run-length and the degree of busy, the second inspection circuit extracts a pixel weight switching signal for each of the color components, and detects the periodicity of meshes of image data by counting pixels not less than the standard value or not more than the standard value based on the pixel weight switching signal within a predetermined counting area. With this arrangement, it becomes possible to carry out the discrimination between character areas and mesh areas as well as the discrimination between black character areas and white character ares with high precision.
    • 图像处理装置以及图像处理方法具有:第一检查电路,对于由图像数据的图像数据中的目标像素和其附近的像素构成的特定区域内的像素的浓度值, 每个颜色分量计算平均密度值,密度差的和,即目标像素和周边像素之间的差的绝对值之和以及与目标像素具有相同密度值的周边像素的数量 ,从而判断目标像素是最大值还是最小值,并且还从形成最大值或最小值的像素计算游程长度和繁忙程度。 另外,根据游程长度和忙碌程度,第二检查电路提取每个颜色分量的像素权重切换信号,并且通过对不小于标准值的像素进行计数来检测图像数据的网格周期,或者 不超过预定计数区域内的像素权重切换信号的标准值。 利用这种布置,可以高精度地执行字符区域和网格区域之间的区分以及黑色字符区域和白色字符区分。