Dual stage neural network pipeline systems and methods

    公开(公告)号:US10558894B2

    公开(公告)日:2020-02-11

    申请号:US16281971

    申请日:2019-02-21

    摘要: A method of identifying and recognizing characters using a dual-stage neural network pipeline, the method including: receiving, by a computing device, image data; providing the image data to a first convolutional layer of a convolutional neural network (CNN); applying, using the CNN, pattern recognition to the image data to identify a region of the image data containing text; providing sub-image data comprising the identified region of the image data to a convolutional recurrent neural network (CRNN); and recognizing, using the CRNN, the characters within the sub-image data.

    DUAL STAGE NEURAL NETWORK PIPELINE SYSTEMS AND METHODS

    公开(公告)号:US20190266445A1

    公开(公告)日:2019-08-29

    申请号:US16281971

    申请日:2019-02-21

    摘要: A method of identifying and recognizing characters using a dual-stage neural network pipeline, the method including: receiving, by a computing device, image data; providing the image data to a first convolutional layer of a convolutional neural network (CNN); applying, using the CNN, pattern recognition to the image data to identify a region of the image data containing text; providing sub-image data comprising the identified region of the image data to a convolutional recurrent neural network (CRNN); and recognizing, using the CRNN, the characters within the sub-image data.

    Dual stage neural network pipeline systems and methods

    公开(公告)号:US11126892B2

    公开(公告)日:2021-09-21

    申请号:US16705604

    申请日:2019-12-06

    摘要: A method of identifying and recognizing characters using a dual-stage neural network pipeline, the method including: receiving, by a computing device, image data; providing the image data to a first convolutional layer of a convolutional neural network (CNN); applying, using the CNN, pattern recognition to the image data to identify a region of the image data containing text; providing sub-image data comprising the identified region of the image data to a convolutional recurrent neural network (CRNN); and recognizing, using the CRNN, the characters within the sub-image data.

    DUAL STAGE NEURAL NETWORK PIPELINE SYSTEMS AND METHODS

    公开(公告)号:US20210365737A1

    公开(公告)日:2021-11-25

    申请号:US17394594

    申请日:2021-08-05

    摘要: A method of identifying and recognizing characters using a dual-stage neural network pipeline, the method including: receiving, by a computing device, image data; providing the image data to a first convolutional layer of a convolutional neural network (CNN); applying, using the CNN, pattern recognition to the image data to identify a region of the image data containing text; providing sub-image data comprising the identified region of the image data to a convolutional recurrent neural network (CRNN); and recognizing, using the CRNN, the characters within the sub-image data.

    Dual stage neural network pipeline systems and methods

    公开(公告)号:US10262235B1

    公开(公告)日:2019-04-16

    申请号:US15904964

    申请日:2018-02-26

    摘要: A method of identifying and recognizing characters using a dual-stage neural network pipeline, the method including: receiving, by a computing device, image data; providing the image data to a first convolutional layer of a convolutional neural network (CNN); applying, using the CNN, pattern recognition to the image data to identify a region of the image data containing text; providing sub-image data comprising the identified region of the image data to a convolutional recurrent neural network (CRNN); and recognizing, using the CRNN, the characters within the sub-image data.