-
公开(公告)号：US11431876B2
公开(公告)日：2022-08-30
申请号：US17006744
申请日：2020-08-28
申请人： Konica Minolta, Inc.
发明人： Yusuke Mimura , Makoto Oki , Hiroaki Kodaira
摘要： An image inspection device detects an abnormality of a formed image by comparing imaged data obtained by imaging the formed image with original image data of the formed image. The image inspection device includes a hardware processor that: adjusts the original image data to reduce sharpness of the original image data; and detects the abnormality by comparing the adjusted original image data with the obtained imaged data. The hardware processor partly restricts the reduction of the sharpness.
-
公开(公告)号：US20210274063A1
公开(公告)日：2021-09-02
申请号：US17256440
申请日：2018-09-13
发明人： Jesse O. Sutherland, III , Wesley R. Schalk , Benjamin Hoopes , Morgan T. Schramm , David M. Berfanger
摘要： An example computer-readable medium storing machine-readable instructions that, when executed by a processor, cause the processor to receive an image, identify a first color region in the image, the first color region having a color level below a color level threshold, and fortify the first color region.
-
公开(公告)号：US11017278B2
公开(公告)日：2021-05-25
申请号：US16833645
申请日：2020-03-29
发明人： Sung-Chu Lee , Pin-Hua Tien
摘要： A method of optimizing printing is applied to a printing apparatus and has following steps of retrieving an input image, executing a tagging process on the input image for tagging one of an edge tag, a fuzzy tag, and a photo tag on each sub-image of the input image, executing the different printing converting process on each sub-image according to its tag for obtaining a printable image, and printing according to the printable image. The present disclosed example can deepen the object edges in the image being printed, improving the image quality of non-edge regions, and improving the printing quality.
-
公开(公告)号：US20210127038A1
公开(公告)日：2021-04-29
申请号：US17075813
申请日：2020-10-21
发明人： Ryosuke Kato , Toshiaki Mutsuo
摘要： An image processing apparatus includes a filtering processing unit that executes a filtering process to suppress background noise of input image data; a threshold setting unit that sets a binarization threshold for the input image data; a background noise determination threshold setting unit that determines that a tone value at which the number of pixels of background noise of the input image data reaches a peak is a background peak tone value and that sets, as a background noise determination threshold, a tone value having a density higher than a density of the background peak tone value and having a number of pixels within a specific range of percentages, of the number of pixels at the peak; a background noise reduction processing unit that executes a background noise reduction process on the input image data and a binarization processing unit that executes a binarization process on the input image data.
-
公开(公告)号：US10798267B2
公开(公告)日：2020-10-06
申请号：US16679022
申请日：2019-11-08
发明人： Kenichirou Haruta
摘要： An image processing unit detects an edge portion of an input image and outputs first data for correcting the detected edge portion. The image processing unit also detects a thin line in the input image and outputs second data for correcting the detected thin line. In a case where a pixel of interest is subjected to both correction processes using the first data and the second data, a greater correction amount is selected and the correction is made using the selected correction amount, and a result corrected image is output as an output image.
-
公开(公告)号：US10748261B2
公开(公告)日：2020-08-18
申请号：US16185066
申请日：2018-11-09
发明人： Tsung-Hsuan Li , Shang-Lun Chan , Shih-Tse Chen
摘要： The present invention discloses a false color removal method comprising: receiving a current pixel including a first color value, a second color value and a third color value, in which the three color values are composed of a maximum value, a medium value and a minimum value; performing permutation to the maximum value, the medium value and the minimum value to obtain six permutation results; calculating six weighting values, in which a kth weighting value is calculated according to at least a kth permutation result of the six permutation results and the three color values, and the k stands for an integer-variable between one and six; calculating six products, in which a kth product is obtained by multiplying the kth weighting value by the kth permutation result; and using the sum of the six products to update the first, second and third color values.
-
公开(公告)号：US10582086B2
公开(公告)日：2020-03-03
申请号：US16073000
申请日：2016-04-21
申请人： HP INDIGO B.V.
发明人： Ran Waidman , Tal Frank , Nir Guttman
摘要： Measures for use in calibrating a printing device. Historical dot gain linearization lookup table data for the printing device is processed. On the basis of the processed historical dot gain linearization lookup table data, a plurality of input points for a current dot gain linearization lookup table are dynamically determined. The printing device is calibrated according to the dynamically determined current dot gain linearization lookup table.
-
8.发明授权公开(公告)号：US10572751B2
公开(公告)日：2020-02-25
申请号：US15446136
申请日：2017-03-01
申请人： Adobe Inc.
发明人： Vijay Kumar Sharma , Sourabh Gupta , Ajay Bedi
摘要： Techniques for converting mechanical markings on hardcopy textual content into digital annotations in a digital document file. In accordance with some embodiments, the techniques include identifying at least one block of text in a digital (scanned) image of a hardcopy document, and identifying at least one mechanical marking in the digital image of the hardcopy document. The mechanical marking, such as an underline, strike-through, highlight or circle, covers or lies adjacent to the corresponding block of text. An annotated digital document file is generated from the digital image of the hardcopy document. The annotated digital document file includes computer-executable instructions representing the original text of the hardcopy document and at least one annotation corresponding to the mechanical marking in the hardcopy document.
-
公开(公告)号：US10554857B2
公开(公告)日：2020-02-04
申请号：US15842813
申请日：2017-12-14
申请人： Google LLC
发明人： Nils Kokemohr
摘要： A method for applying filters to digital images with minimal amplification of image noise, comprising filtering the digital image with an EPDR edge-preserving detail-reducing filter, determining a matrix from the filtered image as a result of one or more structure adaptive functions, and modifying the digital image using the filter, adjusted by the matrix values, to produce an enhanced digital image. The order of processing may be inverted, by first determining the matrix and then filtering the matrix with the edge-preserving detail-reducing filter.
-
公开(公告)号：US10526750B2
公开(公告)日：2020-01-07
申请号：US16079650
申请日：2016-06-30
发明人： Shinoj Bhaskaran
摘要： Examples to process print media (105) are defined herein. At least one marked cell from a plurality of cells (305) extending throughout a processed image of the print media (105) is detected. The processed image of the print media (105) may include marked portions (110) and unmarked portions (115). Further, the marked cell overlays a marked portion of the processed image. Once the marked cell is detected, the marked portions (110) of the print media (105) corresponding to the marked portions (110) of the processed image may be determined and separated from the print media (105) to provide a processed media (130) comprising the unmarked portions (115).
-
-
-
-
-
-
-
-
-
搜索结果
791 条记录 (耗时 0.017 秒)