# US 10,373,014 B2 · Object detection method and image search system

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 10,373,014 B2
- Document ID: US10373014B2
- Status: Granted
- Kind: B2
- Application number: 15/552,823
- Filed: 2016-04-05
- Published: 2018-02-01
- Granted: 2019-08-06
- Earliest claimed: 2015-04-20
- Assignees: Hitachi, Ltd.
- Applicants: Hitachi, Ltd.
- Inventors: Atsushi Hiroike; Yuki Watanabe
- Web page: https://patentgrep.com/patent/US10373014B2

## CPC

- G06F 16/5854: {using shape and object relationship}
- G06F 16/00: Information retrieval; Database structures therefor; File system structures therefor
- G06F 16/50: of still image data
- G06F 16/53: Querying
- G06T 7/68: of symmetry
- G06V 10/42: Global feature extraction by analysis of the whole pattern, e.g. using frequency domain transformations or autocorrelation
- G06V 10/758: {Involving statistics of pixels or of feature values, e.g. histogram matching}
- G06V 40/169: {Holistic features and representations, i.e. based on the facial image taken as a whole}
- G06V 40/171: {Local features and components; Facial parts (eye characteristics G06V40/18); Occluding parts, e.g. glasses; Geometrical relationships}
- G06V 40/172: {Classification, e.g. identification}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

It is provided an object detection method to be performed by an image analysis device configured with a computer including a processor and a memory, the object detection method comprising: a first step of receiving, by the processor, input of an image and storing the image to the memory; a second step of extracting, by the processor, a partial area which is a part of the input image and storing the partial area to the memory; a third step of evaluating, by the processor, symmetry of the partial area using features extracted from the partial area and reflected features obtained by applying reflection to the features; and a fourth step of determining, by the processor, that the partial area is an object area including an object to be detected in a case where the symmetry of the partial area is evaluated as higher than a predetermined threshold.

## Claims

### Claim 1

An object detection method to be performed by an image analysis device configured with a computer including a processor and a memory, the object detection method comprising:
a first step of receiving, by the processor, input of an image and storing the image to the memory;
a second step of extracting, by the processor, a partial area which is a part of the input image and storing the partial area to the memory;
a third step of evaluating, by the processor, symmetry of the partial area using features extracted from the partial area and reflected features obtained by applying one or more transformation matrices to corresponding one or more image feature vectors obtained from the features; and
a fourth step of determining, by the processor, that the partial area is an object area including an object to be detected in a case where the symmetry of the partial area is evaluated as higher than a predetermined threshold,
wherein the third step includes:
a step of distributing the orientations of intensity gradient vectors extracted as the features to a range from 0 to 180 degrees to process in a case where the input image is a binary image; and
a step of distributing the orientations of intensity gradient vectors extracted as the features to a range from 0 to 360 degrees to process in a case where the input image is not a binary image.

### Claim 2 (depends on 1)

The object detection method according to claim 1, wherein the third step includes a step of evaluating symmetry of the partial area using features extracted from the partial area, reflected features obtained by applying one or more transformation matrices to corresponding one or more image feature vectors obtained from the features, and an average magnitude of the features.

### Claim 3 (depends on 1)

The object detection method according to claim 1, wherein the third step includes a step of dividing the partial area into rectangular blocks having a predetermined size and extracting features from each block.

### Claim 4 (depends on 1)

The object detection method according to claim 1, wherein the third step includes steps of creating an area by changing at least one of position and size of the partial area, evaluating symmetry of features of the partial area and symmetry of features of the created area, and determining that an area evaluated to have symmetry higher than a predetermined threshold is an object area including an object to be detected.

### Claim 5 (depends on 1)

The object detection method according to claim 1, wherein the second step includes a step of transforming the input image to have a specified aspect ratio and extracting a partial area from the image transformed in aspect ratio.

### Claim 6 (depends on 1)

An image search system configured to:
for each of input images for registration, store features of an object area determined by the method according to claim 1 to a database; and
compare features extracted from an input query image with features of the registered images to retrieve a registered image similar to the query image.