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
    • 21. 发明专利
    • СПОСОБ ПРОВЕРКИ
    • RU2768553C1
    • 2022-03-24
    • RU2020142769
    • 2018-06-07
    • WILCO AG
    • STIRNIMANN CHRISTIAN
    • B07C5/342G06V10/20
    • Изобретениеотноситсяк способудляоценкиконтейнераи системепроверкидляосуществленияданногоспособа. Техническимрезультатомявляетсяповышениеэффективностипроведенияпроверкидляоценкиконтейнеров. Способзаключаетсяв том, чтопослепроверкипоменьшеймереодногоконтейнеранадефектыприсваиваютданныепроверкипоменьшеймереодномуконтейнеру, первуюоценкупоменьшеймереодномуконтейнерунаоснованиирезультатапроверки, сохраняютидентификационныйпризнакпоменьшеймереодногоконтейнеравместес даннымипроверкии первойоценкойв хранилищеисходныхданныхв видепакетаданных; сортируютпоменьшеймереодинконтейнернаоснованиипервойоценки; еслиперваяоценкапредставляетсобой «повторноетестирование», топредоставляютхранилищеобработанныхданныхс пакетомобработанныхданныхи присваиваютвторуюоценкупространствуданныхпакетаобработанныхданных; сортируютпоменьшеймереодинконтейнернаоснованиивторойоценки. 2 н. и 7 з.п. ф-лы, 3 ил.
    • 23. 发明专利
    • METHOD TO GENERATE A SLAP/FINGERS FOREGROUND MASK
    • CA3145443A1
    • 2021-01-07
    • CA3145443
    • 2020-06-29
    • THALES DIS FRANCE SAS
    • DING YIWANG ANNE JINSONG
    • G06V40/12G06T7/194G06V10/20G06V10/25G06V40/13
    • The present invention relates to a method to generate a slap/fingers foreground mask to be used for subsequent image processing of fingerprints on an image acquired using a contactless fingerprint reader having at least a flash light, said method comprising the following steps: acquisition of two images of the slap/fingers in a contactless position in vicinity of the reader, one image taken with flash light on and one image taken without flash light, calculation of a difference map between the image acquired with flash light and the image acquired without flash light, calculation of an adaptive binarization threshold for each pixel of the image, the threshold for each pixel being the corresponding value in the difference map, to which is subtracted this corresponding value multiplied by a corresponding flashlight compensation factor value determined in a flashlight compensation factor map using an image of a non-reflective blank target acquired with flash light and to which is added this corresponding value multiplied by a corresponding background enhancement factor value determined in a background enhancement factor map using the image acquired without flash light, binarization of the difference map by attributing a first value to pixels where the adaptive binarization threshold value is higher than the corresponding value in the difference map and a second value to pixels where the adaptive binarization threshold value is lower than the corresponding value in the difference map, the binarized image being the slap/fingers foreground mask.
    • 30. 发明专利
    • Hierarchical image decomposition for defect detection
    • GB2602880A
    • 2022-07-20
    • GB202116711
    • 2021-11-19
    • IBM
    • FLORIN MICHAEL SCHEIDEGGERADELMO CHRISTIANO INNOCENZA MALOSSI
    • G06V10/72G06T7/00G06V10/20G06V10/50G06V10/82
    • Method of recognising an object, defect or artefact in a high-resolution image 202 (i.e. an image with resolution much bigger than a working resolution 204 of an image recognition algorithm) comprising: down sampling the high-resolution image into a series of reduced resolution layers 206-210; tiling each down sampled image, each tile having the same resolution as that of the image recognition algorithm; applying the image recognition algorithm to each tile of each layer 212-216; and aggregating the results of the application of the image recognition algorithm to each tile. Overlapping tiles in which an object is detected may be merged (Fig.5). Aggregating the results may comprise: extracting polygons of a shape of a recognized object for each layer; and mapping local polygon coordinates to global coordinates in the image having the highest resolution, thereby allowing comparison between layers of differing resolution. Aggregating the results may comprise: comparing each adjacent layer through the use of a logical “AND” (e.g. 408-410, Fig.4); and combining the comparison of each neighbouring layer through a logical “OR” (418, Fig.4). The baseline algorithm may be a pre-trained neural network model, such as a mask R-CNN (Region Based Convolutional Neural Network) or fast R-CNN.