-
1.发明申请公开(公告)号：US20190294910A1
公开(公告)日：2019-09-26
申请号：US15926966
申请日：2018-03-20
Applicant: KONICA MINOLTA LABORATORY U.S.A., INC.
Inventor： Saman Sarraf
Abstract: In an intelligent character recognition (ICR) method for recognizing hand-written text images using a long-short term memory (LSTM) recurrent neural network (RNN), text images are segmented into text line images, and the text lines images are pre-processed to normalize the line height and to equalize the word spacings in each text line. Both training images used to train the RNN network and test images containing text to be recognized by the trained RNN network are pre-processed to have identical heights and identical word spacings between words. This method improves character recognition accuracy.
-
公开(公告)号：US10025976B1
公开(公告)日：2018-07-17
申请号：US15393056
申请日：2016-12-28
Applicant: KONICA MINOLTA LABORATORY U.S.A., INC.
Inventor： Saman Sarraf , Duanduan Yang
Abstract: Disclosed herein is a method of optimizing data normalization by selecting the best height normalization setting from training RNN (Recurrent Neural Network) with one or more datasets comprising multiple sample images of handwriting data, which comprises estimating a few top place ratios for normalization by minimizing a cost function for any given sample image in the training dataset, and further, determining the best ratio from the top place ratios by validating the recognition results of sample images with each top place ratio.
-
公开(公告)号：US20180181804A1
公开(公告)日：2018-06-28
申请号：US15393056
申请日：2016-12-28
Applicant: KONICA MINOLTA LABORATORY U.S.A., INC.
Inventor： Saman Sarraf , Duanduan Yang
CPC classification number: G06K9/00409 , G06K9/42 , G06K9/4642 , G06K9/6256 , G06K9/6262 , G06T5/002 , G06T5/20
Abstract: Disclosed herein is a method of optimizing data normalization by selecting the best height normalization setting from training RNN (Recurrent Neural Network) with one or more datasets comprising multiple sample images of handwriting data, which comprises estimating a few top place ratios for normalization by minimizing a cost function for any given sample image in the training dataset, and further, determining the best ratio from the top place ratios by validating the recognition results of sample images with each top place ratio.
-
公开(公告)号：US10423852B1
公开(公告)日：2019-09-24
申请号：US15926966
申请日：2018-03-20
Applicant: KONICA MINOLTA LABORATORY U.S.A., INC.
Inventor： Saman Sarraf
Abstract: In an intelligent character recognition (ICR) method for recognizing hand-written text images using a long-short term memory (LSTM) recurrent neural network (RNN), text images are segmented into text line images, and the text lines images are pre-processed to normalize the line height and to equalize the word spacings in each text line. Both training images used to train the RNN network and test images containing text to be recognized by the trained RNN network are pre-processed to have identical heights and identical word spacings between words. This method improves character recognition accuracy.
-
-
-
Search Results
4
records
(took 0.013 seconds)
