# US 2021/0241025 A1 · Object recognition method and apparatus, and storage medium

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

- Number: US 2021/0241025 A1
- Document ID: US20210241025A1
- Status: Published application
- Kind: A1
- Application number: 17/238,215
- Filed: 2021-04-23
- Published: 2021-08-05
- Earliest claimed: 2020-10-28
- Assignees: Beijing More Health Technology Group Co. Ltd.
- Applicants: Beijing More Health Technology Group Co. Ltd.
- Inventors: Jin ZHAO; Fei KONG; Hai WANG; Bangchang LIU; Shufeng GU; Hongwen ZHAO; Xiaobin LUO; Dejie CHANG; Chaozhen LIU; Yikun ZHANG; Yunzhao WU; Boran ZHUANG; Xiaofei YUAN
- Web page: https://patentgrep.com/patent/US20210241025A1

## CPC

- G06V 10/40: Extraction of image or video features
- G06F 18/22: Matching criteria, e.g. proximity measures
- G06F 18/2413: based on distances to training or reference patterns
- G06F 18/2431: Multiple classes
- G06F 18/253: {of extracted features}
- G06V 10/74: Image or video pattern matching; Proximity measures in feature spaces
- G06V 10/751: {Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching}
- G06V 10/761: {Proximity, similarity or dissimilarity measures}
- G06V 10/764: using classification, e.g. of video objects
- G06V 10/806: {of extracted features}
- G06V 20/68: Food, e.g. fruit or vegetables
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

This application provides an object recognition method and apparatus, and a storage medium, and relates to the technical field of image recognition. The object recognition method includes: receiving an image of an object to be recognized; inputting the image of the object to be recognized into a pre-trained image feature extractor to obtain a first feature vector of the image of the object to be recognized; and determining category information of the object to be recognized according to the first feature vector of the image of the object to be recognized as well as image feature vectors in an image database, wherein the image database includes image information of a plurality of objects.

## Claims

### Claim 1

An object recognition method, comprising:
receiving an image of an object to be recognized;
inputting the image of the object to be recognized into a pre-trained image feature extractor to obtain a first feature vector of the image of the object to be recognized; and
determining category information of the object to be recognized according to the first feature vector of the image of the object to be recognized and image feature vectors in an image database, wherein the image database contains image information of a plurality of objects, wherein the image information of each of the plurality of objects at least comprises the category information of the object and the first feature vector of the image, wherein the first feature vector is a feature vector in the form of floating-point number;
wherein determining the category information of the object to be recognized according to the first feature vector of the image of the object to be recognized as well as image feature vectors in the image database comprises:
inputting the first feature vector of the image of the object to be recognized into a pre-trained feature quantizer to obtain a second feature vector of the image of the object to be recognized, and the second feature vector being a binary feature vector; and
determining the category information of the object to be recognized according to the first feature vector and the second feature vector of the image of the object to be recognized as well as image feature vectors in an image database.

### Claim 2 (depends on 1)

The object recognition method according to claim 1, wherein the image information of each of the plurality of objects in the image database further comprises the second feature vector of the image, wherein
determining the category information of the object to be recognized according to the first feature vector and the second feature vector of the image of the object to be recognized and image feature vectors in an image database comprises:
comparing the second feature vector of the image of the object to be recognized with the second feature vector of each image information in the image database, and selecting a set of candidate image information from the image database according to a comparison result; and
comparing the first feature vector of the object to be recognized with the first feature vector of each image information in the set of candidate image information, and determining the category information of the object to be recognized according to the comparison result.

### Claim 3 (depends on 2)

The object recognition method according to claim 2, wherein comparing the second feature vector of the image of the object to be recognized with the second feature vector of each image information in the image database, and selecting the set of candidate image information from the image database according to the comparison result comprises:
performing an exclusive-OR operation on the second feature vector of the image of the object to be recognized and the second feature vector of each image information in the image database to obtain the comparison result being used for labeling a degree of dissimilarity between the image of the object to be recognized and each image information in the image database; and
adding each image information in the image database corresponding to the degree of dissimilarity smaller than a first preset threshold into the set of candidate image information.

### Claim 4 (depends on 2)

The object recognition method according to claim 2, wherein comparing the first feature vector of the object to be recognized with the first feature vector of each image information in the set of the candidate image information, and determining the category information of the object to be recognized according to the comparison result comprises:
determining an Euclidean distance between the first feature vector of the image of the object to be recognized and each first feature vector in the set of the candidate image information to obtain a degree of dissimilarity between the first feature vector of the image of the object to be recognized and each first feature vector in the set of the candidate image information; and
determining the category information of the object to be recognized according to the degree of dissimilarity between the first feature vector of the image of the object to be recognized and each first feature vector in the set of the candidate image information.

### Claim 5 (depends on 4)

The object recognition method according to claim 4, wherein determining category information of the object to be recognized according to the degree of dissimilarity between the first feature vector of the image of the object to be recognized and each first feature vector in the set of the candidate image information comprises:
taking the category information of the object with which the image information in the set of the candidate image information corresponding to the minimum degree of dissimilarity is labeled as the category of the object to be recognized.

### Claim 6 (depends on 1)

The object recognition method according to claim 1, wherein determining the category information of the object to be recognized according to the first feature vector of the image of the object to be recognized as well as image feature vectors in the image database comprises:
comparing the first feature vector of the image of the object to be recognized with the first feature vector of each image information in the image database, and determining the category information of the object to be recognized according to a comparison result.

### Claim 7

An object recognition apparatus, comprising:
a receiving unit, an input unit, and a determination unit; wherein
the receiving unit is configured to receive an image of the object to be recognized;
the input unit is configured to input the image of the object to be recognized into a pre-trained image feature extractor to obtain a first feature vector of the image of the object to be recognized; and
the determination unit is configured to determine category information of the object to be recognized according to the first feature vector of the image of the object to be recognized as well as image feature vectors in an image database, wherein the image database comprises image information of a plurality of objects, wherein the image information of each of the plurality of objects at least comprises the category information of the object, and the first feature vector of the image, wherein the first feature vector is a feature vector in the form of floating-point number;
the determination unit is configured to input the first feature vector of the image of the object to be recognized into a pre-trained feature quantizer to obtain a second feature vector of the image of the object to be recognized, and the second feature vector being a binary feature vector; and
determining category information of the object to be recognized according to the first feature vector and the second feature vector of the image of the object to be recognized and image feature vectors in an image database.

### Claim 8 (depends on 1)

An electronic device, comprising a processor, a storage medium, and a bus, wherein the storage medium stores machine-readable instructions executable by the processor, and when the electronic device is in operation, the processor communicates with the storage medium over the bus, and executes the machine-readable instructions to perform the object recognition method of claim 1.
