-
1.发明申请SYSTEM AND METHOD OF CHARACTER RECOGNITION USING FULLY CONVOLUTIONAL NEURAL NETWORKS WITH ATTENTION 审中-公开使用完全卷积神经网络进行字符识别的系统和方法
公开(公告)号：WO2018090013A1
公开(公告)日：2018-05-17
申请号：PCT/US2017/061562
申请日：2017-11-14
Applicant: KODAK ALARIS INC.
Inventor： SUCH, Felipe Petroski , PTUCHA, Raymond , BROCKLER, Frank , HUTKOWSKI, Paul
Abstract: Embodiments of the present disclosure include a method that obtains a digital image. The method includes extracting a word block from the digital image. The method includes processing the word block by evaluating a value of the word block against a dictionary. The method includes outputting a prediction equal to a common word in the dictionary when a confidence factor is greater than a predetermined threshold. The method includes processing the word block and assigning a descriptor to the word block corresponding to a property of the word block. The method includes processing the word block using the descriptor to prioritize evaluation of the word block. The method includes concatenating a first output and a second output. The method includes predicting a value of the word block.
Abstract translation: 本公开的实施例包括获得数字图像的方法。 该方法包括从数字图像提取文字块。 该方法包括通过针对字典评估字块的值来处理字块。 该方法包括当置信因子大于预定阈值时输出等于字典中的常见单词的预测。 该方法包括处理字块并将描述符分配给与字块的属性对应的字块。 该方法包括使用描述符处理字块以优先评估字块。 该方法包括级联第一输出和第二输出。 该方法包括预测字块的值。
-
2.发明申请SYSTEM AND METHOD OF CHARACTER RECOGNITION USING FULLY CONVOLUTIONAL NEURAL NETWORKS 审中-公开使用完全卷积神经网络的字符识别系统和方法
公开(公告)号：WO2018090011A1
公开(公告)日：2018-05-17
申请号：PCT/US2017/061556
申请日：2017-11-14
Applicant: KODAK ALARIS INC.
Inventor： SUCH, Felipe Petroski , PTUCHA, Raymond , BROCKLER, Frank , HUTKOWSKI, Paul , SINGH, Vatsala
Abstract: Embodiments of the present disclosure include a method for extracting symbols from a digitized object. The method includes processing the word block against a dictionary. The method includes comparing the word block against a word in the dictionary, the comparison providing a confidence factor. The method includes outputting a prediction equal to the word when the confidence factor is greater than a predetermined threshold. The method includes evaluating properties of the word block when the confidence factor is less than the predetermined threshold. The method includes predicting a value of the word block based on the properties of the word block. The method further includes determining an error rate for the predicted value of the word block. The method includes outputting a value for the word block, the output equal to a calculated value corresponding to a value of the word block having the lowest error rate.
Abstract translation: 本公开的实施例包括用于从数字化对象中提取符号的方法。 该方法包括针对字典处理单词块。 该方法包括将单词块与字典中的单词进行比较，该比较提供置信因子。 该方法包括当置信因子大于预定阈值时输出等于该词的预测。 该方法包括当置信因子小于预定阈值时评估字块的属性。 该方法包括基于字块的属性来预测字块的值。 该方法还包括确定字块的预测值的错误率。 该方法包括输出字块的值，输出等于对应于具有最低错误率的字块的值的计算值。
-
Search Results
2
records
(took 0.013 seconds)
