白丝美女被狂躁免费视频网站,500av导航大全精品,yw.193.cnc爆乳尤物未满,97se亚洲综合色区,аⅴ天堂中文在线网官网

System for character recognition in a digital image processing environment

專利號(hào)
US11176362B1
公開日期
2021-11-16
申請(qǐng)人
Bank of America Corporation(US NC Charlotte)
發(fā)明人
Madhusudhanan Krishnamoorthy; Nityashree Pannerselvam
IPC分類
G06K9/00; G06T5/10; G06T5/00; G06K9/26
技術(shù)領(lǐng)域
or,resolution,more,in,query,system,image,images,may,ibe
地域: NC NC Charlotte

摘要

Systems, computer program products, and methods are described herein for character recognition in a digital image processing environment. The present invention is configured to electronically retrieve one or more documents from a document repository, wherein the one or more documents are in an image format; initiate one or more image super resolution algorithms on the one or more documents; generate, based on at least the one or more image super resolution algorithms, one or more high-resolution images associated with each of the one or more documents; initiate one or more image bottleneck ensembles (IBE) algorithms on the one or more high-resolution images; extract, using the one or more IBE algorithms, one or more features associated with the one or more high resolution images; and store the one or more features extracted from the one or more high resolution images in a feature repository.

說(shuō)明書

Next, as shown in block 408, the process flow includes determining one or more matches between the one or more features associated with the one or more images of the query and the one or more features associated with the one or more high resolution images. In some embodiments, the system may be configured to determine the one or more matches between the one or more images of the query and at least the portion of the one or more features associated with the one or more high resolution images identified within the scale at each of the one or more predetermined incremental steps. Following the previous example, a match is determined when a significant portion of the features in the image of the query matches a significant portion of the high resolution document with a sufficiently high similarity index. In some embodiments, the system may be configured to determine the similarity index between the one or more features associated with the image of the query and the one or more features associated with the one or more high resolution images associated with the one or more documents based on at least a distance analysis. In one aspect, the distance analysis may be based on one or more distance measures, such as, Euclidean distance, Manhattan distance, Pearson Correlation distance, cosine distance, Spearman correlation distance, and/or the like. Accordingly, the system may be configured to compare the similarity index of the matching between the features of the image of the query with the features of the high resolution image to a predetermined similarity threshold. In one aspect, the predetermined similarity threshold may be a threshold distance measure. A lower threshold distance indicates that the features are closer to each other and are thus have a higher similarity index. On the other hand, a higher threshold distance indicates that the features are farther away from each other and thus have a lower similarity index. In addition, the system may be configured to compare the number of features of the image of the query that match the features of the high resolution image with a threshold number to determine whether the query is identified in the document. If both the number of features and the similarity index meet their respective predetermined thresholds, then the system may be configured to determine a match.

權(quán)利要求

1
微信群二維碼
意見反饋