公开(公告)号：US20240404268A1

公开(公告)日：2024-12-05

申请号：US18699701

申请日：2021-10-14

Applicant: Hewlett-Packard Development Company, L.P.

Inventor： Qian Lin ,  Augusto Valente ,  Otavio Gomes

IPC: G06V10/82 ,  G06V10/774 ,  G06V10/776

Abstract: In some examples, a computing device can include a processing resource and a memory resource storing instructions to cause the processing resource to cause a convolutional neural network (CNN) model to be trained with an initial training data set to detect an object included in annotated images included in the initial training data set, cause the trained CNN model to perform inferencing on unannotated images included in an inference data set to detect the object in the unannotated images, determine an error rate of the trained CNN model, and cause the trained CNN model to be further trained based on the error rate.

公开(公告)号：US20230343119A1

公开(公告)日：2023-10-26

申请号：US17273416

申请日：2021-02-26

Applicant: Hewlett-Packard Development Company, L.P.

Inventor： Lucas Nedel Kirsten ,  Guilherme Megeto ,  Augusto Valente ,  Karina Bogdan ,  Rovilson Junior

IPC: G06V30/12 ,  G06V30/18 ,  G06V10/82

CPC classification number: G06V30/133 ,  G06V30/18124 ,  G06V10/82 ,  G06V30/14

Abstract: A contextual feature matrix that aggregates contextual information within a captured image of a document at multiple scales is generated using a multiscale aggregator machine learning model. Pixel-wise enhancement curves for the captured image are estimated based on the contextual feature matrix using an enhancement curve prediction machine learning model. The pixel-wise enhancement curves are iteratively applied to the captured image to enhance the document within the captured image.