-
公开(公告)号：US20180005478A1
公开(公告)日：2018-01-04
申请号：US15541705
申请日：2015-06-29
发明人： Jian CHEN , Shanling CUI , Qianwen WANG , Jing XU
CPC分类号： G07D7/205 , G06T7/90 , G07D7/1205 , G07D7/20 , G07D7/2008 , G07D7/2091
摘要： A method and a device for banknote classification and recognition based on a Lab color space are provided for improving the denomination recognition rate. The method includes obtaining an RGB image of a banknote to be detected; calculating gray values Gray R, Gray G and Gray B of the RGB image in red (R), green (G) and blue (B) wavebands; converting the gray values Gray R, Gray G and Gray B into gray values Gray a and Gray b in the Lab color space; and substituting a product of Gray a and Gray b and a difference between the absolute value of Gray a and the absolute value of Gray b into preset formulas to determine a category of the banknote to be detected.
-
公开(公告)号：US20160314563A1
公开(公告)日：2016-10-27
申请号：US15104334
申请日：2014-10-13
发明人： Qianwen WANG , Jing YOU , Jing XU , Dehao XIE
CPC分类号： G06T5/006 , G06T3/0093 , G06T7/12
摘要： The present invention relates to a method for correcting a fragmentary or deformed quadrangular image. The method comprises five steps, i.e. detection of an edge point, elimination of an abnormal edge point, straight-line fitting, vertex calculation and image correction. The method for correcting a fragmentary or deformed quadrangular image is applied to a recognition method and a recognition system for papers, such as valuable documents, bills, identity cards, etc., and can rapidly conduct edge detection and tilt correction on images of valuable documents, bills or papers which are fragmentary or deformed.
摘要翻译： 本发明涉及一种用于校正碎片或变形的四边形图像的方法。 该方法包括五个步骤，即检测边缘点，消除异常边缘点，直线拟合，顶点计算和图像校正。 用于校正零碎或变形的四边形图像的方法被应用于诸如有价值的文件，纸币，身份证等的纸张的识别方法和识别系统，并且可以快速地对有价值的文档的图像进行边缘检测和倾斜校正 ，碎片或变形的纸币或纸张。
-
公开(公告)号：US20170228956A1
公开(公告)日：2017-08-10
申请号：US15518584
申请日：2015-08-07
发明人： Jing YOU , Qianwen WANG , Jing XU
摘要： A method for detecting overlapped bank notes is provided. The method includes: step 10, collecting original image data of bank notes; step 20, performing security thread positioning detection on the original image data of the bank notes, to obtain security thread detection data; step 40, determining whether the security thread detection data meets a preset security thread reference condition, going to step 60 if the security thread detection data meets the preset security thread reference condition, and going to step 70 if the security thread detection data does not meet the preset security thread reference condition; step 60, obtaining a determination result that the bank notes are not overlapped, and ending the method; and step 70, obtaining a determining result that the bank notes are overlapped, and ending the method.
-
公开(公告)号：US20160198066A1
公开(公告)日：2016-07-07
申请号：US14917238
申请日：2014-11-21
发明人： Qianwen WANG , Tiancai LIANG , Mengtao LIU , Yifei ZHANG
CPC分类号： H04N1/409 , H04N1/00045 , H04N1/401 , H04N1/4076 , H04N5/235
摘要： An image calibration method and device. A deviation compensation coefficient of each pixel is calculated according to image data generated by strong and weak lighting parameters, and the deviation compensation coefficient is used to calibrate data of each image pixel collected and output by an image sensing unit. Therefore, the influence of inconsistency of each photosensitive element of the image sensing unit on the image greyscale can be eliminated, so that the effect of document medium image recognition is increased. The method in the embodiments of the present invention comprises: S1, acquiring a strong lighting parameter of each photosensitive element within a long exposure time and a weak lighting parameter thereof within a short exposure time; S2, acquiring image data of a sheet medium; and S3, according to the strong lighting parameter, the weak lighting parameter and the image data, calculating the calibrated image data of the sheet medium.
摘要翻译： 一种图像校准方法和装置。 根据强光照明参数产生的图像数据计算出各像素的偏差补偿系数，偏差补偿系数用于校正由图像感测部收集并输出的各图像像素的数据。 因此，可以消除图像感测单元的每个感光元件的不一致对图像灰度的影响，从而增加了文档媒体图像识别的效果。 本发明的实施例中的方法包括：S1，在短曝光时间内获取长曝光时间内的每个光敏元件的强光照参数和弱照明参数; S2，获取片材介质的图像数据; 和S3，根据强照明参数，弱照明参数和图像数据，计算片材介质的校准图像数据。
-
-
-
搜索结果
4 条记录 (耗时 0.014 秒)
