IP Library Granted Patent US 11,429,985
Granted Patent B2
US 11,429,985 · App. 15/695,641 · Granted Aug 30, 2022

Information processing device calculating statistical information

Inventors: Tomoyuki Shibata (Kawasaki, JP); Yuto Yamaji (Kawasaki, JP); Hideo Umeki (Yokohama, JP)
Assignee: KABUSHIKI KAISHA TOSHIBA
G06Q30/02G06Q10/06393G06V20/80
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,429,985
App. No.
15/695,641
Granted
Aug 30, 2022
Kind
B2
Abstract

According to one embodiment, an information processing device includes a processor and a memory. The processor determines whether an object included in an image belongs to a first group or not. The processor calculates at least one of first statistical information of an object determined to belong to the first group or second statistical information of an object determined not to belong to the first group. The processor stores at least one of the first statistical or the second statistical information in the memory. The processor executes display processing for at least one of the first statistical information or the second statistical information stored in the memory.

Claims (27)

1. An information processing system comprising:

an imaging sensor; and

an information processing device, wherein the imaging sensor is configured to capture a plurality of frames of image data and transmit the image data to the information processing device wirelessly in real time,

the information processing device includes:

a processor circuit;

a display device; and

a storage unit which is connected to the processor circuit and is configured to store the image data and feature explanation information associating type information of feature quantities with explanatory information explaining the type information of the feature quantities,

the processor circuit is configured to:

execute metric learning using semi-supervised learning algorithm using teaching information instructed from a user by an operation accepting device and unteaching information to improve classification performance of the metric learning,

extract person image targets from the image data stored in the storage unit by executing image processing based upon the image data,

execute determining whether each of the person image targets included in the image data belongs to a first group or not based upon the feature quantities of each of the person image targets and a result of the metric learning, and storing, in the storage unit, determination result data obtained by the determining,

calculate, by executing a statistical processing, at least one of first statistical information of person image targets determined to belong to the first group or second statistical information of person image targets determined not to belong to the first group,

execute selecting at least one of the feature quantities which contributed to the determining whether the person image targets belong to the first group or not,

select explanation information associated with the at least one of the feature quantities from the storage unit based upon the feature explanation information stored in the storage unit, and

display, on the display device:

at least one of the calculated first statistical information and the calculated second statistical information, and

the selected explanation information, and

the selecting includes selecting the at least one of the feature quantities having an inverse correlation between the first group and a second group which is not the first group.

2. The information processing system of claim 1 , wherein the processor circuit is further configured to display, on the display device, an image of one of the person image targets determined to belong to the first group and an image of one of the person image targets determined not to belong to the first group.

3. The information processing system of claim 2 , wherein the processor circuit is further configured to acquire the teaching information indicating whether a specific person image target displayed belongs to the first group or not.

4. The information processing system of claim 3 , wherein the processor circuit is further configured to determine whether the specific person image target belongs to the first group or not based on the teaching information.

5. The information processing system of claim 2 , wherein the processor circuit is further configured to display person image target belonging to a boundary area between the first group and the second group which is not the first group.

6. The information processing system of claim 5 , wherein the boundary area is an area based on likelihood information calculated by the processor circuit.

7. The information processing system of claim 1 , wherein the first statistical information includes a result of the statistical processing for the person image targets determined to belong to the first group, the second statistical information includes a result of the statistical processing for the person image targets determined not to belong to the first group, and the feature quantities include a numerical amount value used by analyzing the image data.

8. The information processing system of claim 1 , wherein the first group is a group of specific person image targets, and the second group is a group of unspecific person image targets.

9. The information processing system of claim 8 , wherein the specific person image targets are salesclerk image targets, and the unspecific person image targets are customer image targets.

10. The information processing system of claim 1 , wherein the processor circuit is further configured to select the at least one of the feature quantities which contributed to the determining whether the image objects belong to the first group or not by executing a principal component analysis.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 6, 2017
From: SHIBATA, TOMOYUKI; YAMAJI, YUTO; UMEKI, HIDEO
To: KABUSHIKI KAISHA TOSHIBA
Reel/Frame 044311/0591 →
Priority Claims (1)
JP JP2017-054986 · Mar 21, 2017 · national
Continuity (1)
Related Publication 20180276471A1 · Sep 27, 2018