公开(公告)号：US20180307897A1

公开(公告)日：2018-10-25

申请号：US16024823

申请日：2018-06-30

Applicant: Samsung Electronics Co., Ltd.

Inventor： Mostafa EL-KHAMY ,  Arvind YEDLA ,  Marcel NASSAR ,  Jungwon LEE

IPC: G06K9/00

CPC classification number: G06K9/00268 ,  G06K9/00228 ,  G06T7/70 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30201

Abstract: A system to recognize objects in an image includes an object detection network outputs a first hierarchical-calculated feature for a detected object. A face alignment regression network determines a regression loss for alignment parameters based on the first hierarchical-calculated feature. A detection box regression network determines a regression loss for detected boxes based on the first hierarchical-calculated feature. The object detection network further includes a weighted loss generator to generate a weighted loss for the first hierarchical-calculated feature, the regression loss for the alignment parameters and the regression loss of the detected boxes. A backpropagator backpropagates the generated weighted loss. A grouping network forms, based on the first hierarchical-calculated feature, the regression loss for the alignment parameters and the bounding box regression loss, at least one of a box grouping, an alignment parameter grouping, and a non-maximum suppression of the alignment parameters and the detected boxes.

公开(公告)号：US20170344808A1

公开(公告)日：2017-11-30

申请号：US15224487

申请日：2016-07-29

Applicant: Samsung Electronics Co., Ltd.

Inventor： Mostafa EL-KHAMY ,  Arvind YEDLA ,  Marcel NASSAR ,  Jungwon LEE

IPC: G06K9/00

CPC classification number: G06K9/00268 ,  G06K9/00228 ,  G06T7/70 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30201

Abstract: A system to recognize objects in an image includes an object detection network outputs a first hierarchical-calculated feature for a detected object. A face alignment regression network determines a regression loss for alignment parameters based on the first hierarchical-calculated feature. A detection box regression network determines a regression loss for detected boxes based on the first hierarchical-calculated feature. The object detection network further includes a weighted loss generator to generate a weighted loss for the first hierarchical-calculated feature, the regression loss for the alignment parameters and the regression loss of the detected boxes. A backpropagator backpropagates the generated weighted loss. A grouping network forms, based on the first hierarchical-calculated feature, the regression loss for the alignment parameters and the bounding box regression loss, at least one of a box grouping, an alignment parameter grouping, and a non-maximum suppression of the alignment parameters and the detected boxes.

公开(公告)号：US20180158189A1

公开(公告)日：2018-06-07

申请号：US15478947

申请日：2017-04-04

Applicant: Samsung Electronics Co., Ltd.

Inventor： Arvind YEDLA ,  Marcel NASSAR ,  Mostafa EL-KHAMY ,  Jungwon LEE

IPC: G06T7/11

CPC classification number: G06T7/11 ,  G06K9/00369 ,  G06K9/3241 ,  G06K9/4628 ,  G06K9/627 ,  G06N3/0454 ,  G06N3/0472 ,  G06N3/08 ,  G06T7/194

Abstract: Apparatuses and methods of manufacturing same, systems, and methods for object detection using a region-based deep learning model are described. In one aspect, a method is provided, in which a region proposal network (RPN) is used to identify regions of interest (RoI) in an image by assigning a confidence levels, the assigned confidence levels of the RoIs are used to boost the background score assigned by the downstream classifier to each RoI, and the background scores are used in a softmax function to calculate the final class probabilities for each object class.