智能抠图
描述
本接口用于云端进行显著性检测的请求,能够自动识别图像中的显著性目标区域。支持人像、商品、图形三种类型的显著性检测,并可返回检测结果图或 mask 图,支持边缘细节优化等高级功能。
版本
1.0
图片要求
- 图片格式JPG、PNG、HEIC
- 图片像素尺寸最小 224×224 像素,最大 3000×3000 像素
- 图片文件大小建议控制在3M 内
调用 URL
正式环境:https://openapi.meitu.com
任务提交接口:https://openapi.meitu.com/api/v1/sdk/sync/push
任务名称(task):/v1/photo_scissors/sod
任务类型(task_type):mtlab调用方法
POST
Content-Type: application/json
权限
请求参数
| 是否必选 | 参数名 | 类型 | 参数说明 |
|---|---|---|---|
| 必选 | params | string | 算法参数(JSON 字符串) |
| 必选 | init_images | object[] | 多媒体文件列表 |
| 必选 | task | string | 固定 /v1/photo_scissors/sod |
| 必选 | task_type | string | 固定 mtlab |
| 可选 | sync_timeout | int | 默认 30,同步超时时间 |
init_images 多媒体文件参数,结构说明如下
| 是否必选 | 参数名 | 类型 | 参数说明 |
|---|---|---|---|
| 必选 | url | string | 多媒体的 url 地址,或者 base64 |
| 必选 | profile | object | 属性信息描述 |
profile 属性信息描述
| 是否必选 | 参数名 | 类型 | 参数说明 |
|---|---|---|---|
| 必选 | media_profiles | object | 媒体属性信息 |
| 必选 | version | string | 版本信息,固定 v1 |
media_profiles 媒体属性信息
| 是否必选 | 参数名 | 类型 | 参数说明 |
|---|---|---|---|
| 必选 | media_data_type | string | 媒体数据类型,"url": 表示 url,"jpg": 表示 base64 |
params 推理参数是 JSON 字符串,其结构说明如下
| 是否必选 | 字段 | 类型 | 说明 |
|---|---|---|---|
| 可选 | rsp_media_type | string | 默认 url;jpg 表示 base64 |
| 必选 | parameter | object | 算法核心参数对象 |
parameter 算法参数详情
| 是否必选 | 参数名 | 类型 | 说明 |
|---|---|---|---|
| 可选 | nMask | bool | 是否返回 mask 图,True 只返回 mask 图,False 返回结果图 |
| 可选 | model_type | int | 选择要使用的抠图模型 0:人像抠图 1:商品抠图 2:图形抠图 若不传,模型内部会自动判断选择使用哪个模型 |
| 可选 | userboxes | string | 图标类型可以添加用户交互框参数,坐标应当使用相对坐标,务必按照左上角开始顺时针的顺序传入四个点的坐标(即左上、右上、右下、左下)。示例:[[[0.01, 0.814], [0.12, 0.814], [0.12, 0.96], [0.01, 0.96]]] |
| 可选 | blackwhite | bool | 是否返回黑白图,True 只返回黑白 mask 图,False 返回四通道 Mask 图,默认为 False |
| 可选 | nbox | bool | 是否返回目标位置,True 返回目标位置 top_x, top_y, bottom_x, bottom_y,默认为 False |
| 可选 | post_matting | bool | 仅针对商品类别,是否使用边缘后处理算法,默认为 False。若设置为 True,会得到更精细的边缘细节,但是耗时会增加 0.2s~1s |
| 可选 | use_fe_rgba | bool | 控制是否使用前景估计,默认为 False。如果图像抠图结果边缘存在白边或黑边等问题,则设置为 True,使用前景估计 |
输入值示例
{
"task": "/v1/photo_scissors/sod",
"task_type": "mtlab",
"init_images": [
{
"url": "https://example.com/image.jpg",
"profile": {
"media_profiles": {
"media_data_type": "url"
},
"version": "v1"
}
}
],
"params": "{\"rsp_media_type\":\"url\",\"parameter\":{\"nMask\":false,\"model_type\":0}}",
"sync_timeout": 30
}返回值说明
注意,生成的结果,会定期清理,请及时下载保存| 字段 | 类型 | 说明 |
|---|---|---|
| request_id | string | 请求标识 |
| trace_id | string | 链路追踪标识 |
| code | int | 业务状态码,0 表示请求受理成功 |
| error_code | int | 错误码,成功时为 0 |
| message | string | 业务信息 |
| tips | any | 补充提示,可为 null |
| data | object | 任务状态和算法结果 |
data 中单个元素的字段说明
| 字段 | 类型 | 说明 |
|---|---|---|
| status | int | 状态码:-1 未找到任务;0 创建成功;1 执行中;2 失败;9 超时,使用查询接口查询;10 成功 |
| result | object | 算法结果 |
| progress | number | 任务进度 |
| predict_elapsed | int | 预计耗时,毫秒 |
| create_time | int64 | 创建时间戳,毫秒 |
| task_id | string | 任务 ID |
| custom_task_id | string | 客户自定义任务 ID |
| trace_id | string | 链路追踪标识 |
| client_info | string | 客户端信息 |
| init_images | object[]/null | 输入媒体回显 |
result 中单个元素的字段说明
| 字段 | 类型 | 说明 |
|---|---|---|
| parameter | object | 算法参数信息 |
| media_info_list | array | 媒体文件列表 |
| msg | string | 状态消息 |
| msg_id | string | 消息ID |
| code | int | 算法状态码 |
| error_code | int | 错误代码 |
| error_msg | string | 错误信息 |
| data | object | 算法返回数据 |
返回值示例
请求成功返回示例
Response Status:200
content-type 为 application/json; charset=utf-8
{
"request_id": "req_123456789",
"trace_id": "trace_987654321",
"code": 0,
"error_code": 0,
"message": "success",
"tips": null,
"data": {
"status": 10,
"result": {
"parameter": {
"version": "1.0",
"exist_salient": true,
"Kind": 0
},
"media_info_list": [
{
"media_data": "https://example.com/result.jpg",
"media_profiles": {
"media_data_type": "url"
}
}
],
"msg": "success",
"msg_id": "msg_123456",
"code": 0,
"error_code": 0,
"error_msg": ""
},
"progress": 100,
"predict_elapsed": 5000,
"create_time": 1640995200000,
"task_id": "task_1234567890",
"custom_task_id": "",
"trace_id": "trace_987654321",
"client_info": "",
"init_images": null
}
}需要查询返回示例
使用 查询接口 接口查询
Response Status:200
content-type 为 application/json; charset=utf-8
{
"request_id": "",
"trace_id": "",
"code": 0,
"error_code": 0,
"message": "success",
"tips": null,
"data": {
"status": 9,
"result": {
"id": "t_mt1a3i5n7b3da6d589-46b5-4f66-a0bb-8dd22f2a172e"
},
"progress": 0,
"predict_elapsed": 10000,
"create_time": 1759202368761,
"task_id": "t_mt1a3i5n7b3da6d589-46b5-4f66-a0bb-8dd22f2a172e",
"custom_task_id": "",
"trace_id": "9129a3a2-99c4-46ce-8731-0e100e2fbee7",
"client_info": "",
"init_images": null
}
}请求失败返回示例
Response Status:400
content-type 为 application/json; charset=utf-8
{
"request_id": "req_error_123456",
"trace_id": "trace_error_789012",
"code": 20003,
"error_code": 20003,
"message": "ALGO_ERROR",
"tips": null,
"data": {
"status": 2,
"result": {
"id": "t_mt1a3i5n7be8d575cc-2ffb-4e0c-85a8-1824110e31b8",
"code": 20003,
"data": {
"duration": {
"alg_process_time": 0,
"created_timestamp": 1759201989,
"pull_timestamp": 1759201989,
"repost_time": 0,
"upload_time": 0,
"waiting_time": 0
},
"error_code": 20003,
"error_msg": "DETECT_NOT_FACE",
"extra": {},
"media_info_list": [],
"msg_id": "c1b09cb2-6e05-4d21-55ab-r007b1f21bec",
"parameter": null
},
"msg": "DETECT_NOT_FACE",
"msg_id": "c1b09cb2-6e05-4d21-55ab-r007b1f21bec"
},
"progress": 1,
"predict_elapsed": 10000,
"create_time": 1759201989444,
"task_id": "t_mt1a3i5n7be8d575cc-2ffb-4e0c-85a8-1824110e31b8",
"custom_task_id": "",
"trace_id": "",
"client_info": "",
"init_images": null
}
}通用的错误代码与信息
详见 API 错误码
SDK 调用示例
Python
import requests
import json
from sign_sdk import sign
def api_call_example():
key = "your_api_key"
secret = "your_api_secret"
url = "https://openapi.meitu.com/api/v1/sdk/sync/push"
method = "POST"
headers = {
"Content-Type": "application/json",
sign.HeaderHost: "openapi.meitu.com",
}
inner_params = {
"rsp_media_type": "url",
"parameter": {
"nMask": False,
"model_type": 0,
},
}
payload_dict = {
"task": "/v1/photo_scissors/sod",
"task_type": "mtlab",
"init_images": [{
"url": "https://example.com/image.jpg",
"profile": {
"media_profiles": {"media_data_type":"url"},
"version": "v1"
}
}],
"params": json.dumps(inner_params, ensure_ascii=False),
"sync_timeout": 30,
}
body = json.dumps(payload_dict, ensure_ascii=False)
try:
signer = sign.Signer(key, secret)
signed_request = signer.sign(url, method, headers, body)
session = requests.Session()
response = session.send(signed_request)
print(f"Status: {response.status_code}")
print(f"Response: {response.text}")
except Exception as e:
print(f"Error: {str(e)}")
if __name__ == "__main__":
api_call_example()Go
package main
import (
"fmt"
"io"
"net/http"
"github.com/mtlab/api/signer"
)
func main() {
key := "your_api_key"
secret := "your_api_secret"
signObj := signer.NewSigner(key, secret)
url := "https://openapi.meitu.com/api/v1/sdk/sync/push"
method := "POST"
headers := make(http.Header)
headers.Set(signer.HeaderHost, "openapi.meitu.com")
headers.Set("Content-Type", "application/json")
body := `{
"task": "/v1/photo_scissors/sod",
"task_type": "mtlab",
"init_images": [{
"url": "https://example.com/image.jpg",
"profile": {
"media_profiles": {"media_data_type":"url"},
"version": "v1"
}
}],
"params": "{\"rsp_media_type\":\"url\",\"parameter\":{\"nMask\":false,\"model_type\":0}}",
"sync_timeout": 30
}`
req, err := signObj.Sign(url, method, headers, body)
if err != nil {
fmt.Println("Failed to sign request:", err)
return
}
client := http.DefaultClient
resp, err := client.Do(req)
if err != nil {
fmt.Println("Failed to send request:", err)
return
}
defer resp.Body.Close()
bodyBytes, err := io.ReadAll(resp.Body)
if err != nil {
fmt.Println("Read response failed:", err)
return
}
fmt.Println("Response:", resp.StatusCode, string(bodyBytes))
}PHP
<?php
require 'signer.php';
$key = 'your_api_key';
$secret = 'your_api_secret';
$signer = new Signer($key, $secret);
$url = 'https://openapi.meitu.com/api/v1/sdk/sync/push';
$method = 'POST';
$headers = [
'Content-Type' => 'application/json'
];
$innerParams = json_encode([
"rsp_media_type" => "url",
"parameter" => [
"nMask" => false,
"model_type" => 0
]
]);
$body = json_encode([
"task" => "/v1/photo_scissors/sod",
"task_type" => "mtlab",
"init_images" => [
[
"url" => "https://example.com/image.jpg",
"profile" => [
"media_profiles" => ["media_data_type" => "url"],
"version" => "v1"
]
]
],
"params" => $innerParams,
"sync_timeout" => 30
]);
$curl = $signer->sign($url, $method, $headers, $body);
$response = curl_exec($curl);
$status = curl_getinfo($curl, CURLINFO_HTTP_CODE);
if ($status == 0) {
echo "Error: " . curl_error($curl);
} else {
echo "Status: " . $status . "\n";
echo "Response: " . $response;
}
curl_close($curl);
?>Java
package com.meitu.openai.common;
import java.io.BufferedReader;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.net.HttpURLConnection;
import java.net.MalformedURLException;
import java.net.URL;
import java.nio.charset.StandardCharsets;
import java.util.HashMap;
import java.util.Map;
import com.meitu.openai.common.Signer;
public class Main {
public static void main(String[] args) throws Exception {
Signer signer = new Signer("your_api_key", "your_api_secret");
String url = "https://openapi.meitu.com/api/v1/sdk/sync/push";
String method = "POST";
Map<String, String> headers = new HashMap<>();
headers.put("Content-Type", "application/json");
headers.put(Signer.HeaderHost, "openapi.meitu.com");
String body = "{\n" +
" \"task\": \"/v1/photo_scissors/sod\",\n" +
" \"task_type\": \"mtlab\",\n" +
" \"init_images\": [\n" +
" {\n" +
" \"url\": \"https://example.com/image.jpg\",\n" +
" \"profile\": {\n" +
" \"media_profiles\": {\n" +
" \"media_data_type\": \"url\"\n" +
" },\n" +
" \"version\": \"v1\"\n" +
" }\n" +
" }\n" +
" ],\n" +
" \"params\": \"{\\\"rsp_media_type\\\":\\\"url\\\",\\\"parameter\\\":{\\\"nMask\\\":false,\\\"model_type\\\":0}}\",\n" +
" \"sync_timeout\": 30\n" +
"}";
Map<String,String> signedHeaders = signer.sign(url, method, headers, body);
System.out.println("signedHeader: "+signedHeaders);
try {
HttpURLConnection connection = (HttpURLConnection) new URL(url).openConnection();
connection.setRequestMethod(method);
for (Map.Entry<String,String> entry : signedHeaders.entrySet()) {
connection.setRequestProperty(entry.getKey(), entry.getValue());
}
connection.setDoOutput(true);
if (body!=null){
connection.getOutputStream().write(body.getBytes(StandardCharsets.UTF_8));
}
int status = connection.getResponseCode();
System.out.println(status);
InputStream inputStream;
if (status >= 400) {
inputStream = connection.getErrorStream();
} else {
inputStream = connection.getInputStream();
}
BufferedReader in = new BufferedReader(new InputStreamReader(inputStream));
String inputLine;
StringBuilder response = new StringBuilder();
while ((inputLine = in.readLine()) != null) {
response.append(inputLine);
}
in.close();
System.out.println("======");
System.out.println(response.toString());
System.out.println("======");
} catch (MalformedURLException e) {
e.printStackTrace();
}
}
}