Object recognition API

1. Overview of object recognition

Input to identify the photo, and then output will identify the names of the objects (including Chinese and English), identify the precision of the object, identified the location of the object in the original image (by returning the pixel parameters)

2. Object recognition API


Fetching result of object recognition;

HTTP request mode:

The body of put is the recognition image;

Request URL:


Request parameters has two options: MUST and OPTIONAL

Request parameters:
Name Type Option Comment
token string Must Token
Name Type Comment
rc int Error code
result json Identified result
reason string Error Description:
When rc is not equal to 0, it is an error;
When rc is equal to 0, this field is not returned;
Result array element:
Name Type Comment
cate string Identified name (English)
alias string Alias string Identified name (Chinese)
pro double Identified result
left int Pixel distance from the left edge of the picture
right int Pixel distance from the right edge of the picture
top int Pixel distance from the top edge of the picture
bot int Pixel distance from the bottom edge of the picture
Error Code Description (rc code):
rc Description
0 Success
-1 Internal server error
-2 Length of token exceed limitation:
maximum size fortoken is 40 bytes.
-3 Parameter error (token not passed; picture content is not passed)
-4 Invalid token
Request Example:

Curl request demo Click to download