API参考
对于服务提供的所有操作：
- 响应体以及POST请求的请求体均为JSON数据（JSON对象）。
- 当请求处理成功时，响应状态码为
200，响应体的属性如下：
| 名称 |
类型 |
含义 |
errorCode |
integer |
错误码。固定为0。 |
errorMsg |
string |
错误说明。固定为"Success"。 |
响应体还可能有result属性，类型为object，其中存储操作结果信息。
| 名称 |
类型 |
含义 |
errorCode |
integer |
错误码。与响应状态码相同。 |
errorMsg |
string |
错误说明。 |
服务提供的操作如下：
获取图像OCR结果。
POST /ocr
| 名称 |
类型 |
含义 |
是否必填 |
image |
string |
服务可访问的图像文件的URL或图像文件内容的Base64编码结果。 |
是 |
inferenceParams |
object |
推理参数。 |
否 |
inferenceParams的属性如下：
| 名称 |
类型 |
含义 |
是否必填 |
maxLongSide |
integer |
推理时，若文本检测模型的输入图像较长边的长度大于maxLongSide，则将对图像进行缩放，使其较长边的长度等于maxLongSide。 |
否 |
- 请求处理成功时，响应体的
result具有如下属性：
| 名称 |
类型 |
含义 |
texts |
array |
文本位置、内容和得分。 |
image |
string |
OCR结果图，其中标注检测到的文本位置。图像为JPEG格式，使用Base64编码。 |
texts中的每个元素为一个object，具有如下属性：
| 名称 |
类型 |
含义 |
poly |
array |
文本位置。数组中元素依次为包围文本的多边形的顶点坐标。 |
text |
string |
文本内容。 |
score |
number |
文本识别得分。 |
result示例如下：
{
"texts": [
{
"poly": [
[
444,
244
],
[
705,
244
],
[
705,
311
],
[
444,
311
]
],
"text": "北京南站",
"score": 0.9
},
{
"poly": [
[
992,
248
],
[
1263,
251
],
[
1263,
318
],
[
992,
315
]
],
"text": "天津站",
"score": 0.5
}
],
"image": "xxxxxx"
}
多语言调用服务示例
Python
import base64
import requests
API_URL = "http://localhost:8080/ocr" # 服务URL
image_path = "./demo.jpg"
output_image_path = "./out.jpg"
# 对本地图像进行Base64编码
with open(image_path, "rb") as file:
image_bytes = file.read()
image_data = base64.b64encode(image_bytes).decode("ascii")
payload = {"image": image_data} # Base64编码的文件内容或者图像URL
# 调用API
response = requests.post(API_URL, json=payload)
# 处理接口返回数据
assert response.status_code == 200
result = response.json()["result"]
with open(output_image_path, "wb") as file:
file.write(base64.b64decode(result["image"]))
print(f"Output image saved at {output_image_path}")
print("\nDetected texts:")
print(result["texts"])
C++
#include <iostream>
#include "cpp-httplib/httplib.h" // https://github.com/Huiyicc/cpp-httplib
#include "nlohmann/json.hpp" // https://github.com/nlohmann/json
#include "base64.hpp" // https://github.com/tobiaslocker/base64
int main() {
httplib::Client client("localhost:8080");
const std::string imagePath = "./demo.jpg";
const std::string outputImagePath = "./out.jpg";
httplib::Headers headers = {
{"Content-Type", "application/json"}
};
// 对本地图像进行Base64编码
std::ifstream file(imagePath, std::ios::binary | std::ios::ate);
std::streamsize size = file.tellg();
file.seekg(0, std::ios::beg);
std::vector<char> buffer(size);
if (!file.read(buffer.data(), size)) {
std::cerr << "Error reading file." << std::endl;
return 1;
}
std::string bufferStr(reinterpret_cast<const char*>(buffer.data()), buffer.size());
std::string encodedImage = base64::to_base64(bufferStr);
nlohmann::json jsonObj;
jsonObj["image"] = encodedImage;
std::string body = jsonObj.dump();
// 调用API
auto response = client.Post("/ocr", headers, body, "application/json");
// 处理接口返回数据
if (response && response->status == 200) {
nlohmann::json jsonResponse = nlohmann::json::parse(response->body);
auto result = jsonResponse["result"];
encodedImage = result["image"];
std::string decodedString = base64::from_base64(encodedImage);
std::vector<unsigned char> decodedImage(decodedString.begin(), decodedString.end());
std::ofstream outputImage(outPutImagePath, std::ios::binary | std::ios::out);
if (outputImage.is_open()) {
outputImage.write(reinterpret_cast<char*>(decodedImage.data()), decodedImage.size());
outputImage.close();
std::cout << "Output image saved at " << outPutImagePath << std::endl;
} else {
std::cerr << "Unable to open file for writing: " << outPutImagePath << std::endl;
}
auto texts = result["texts"];
std::cout << "\nDetected texts:" << std::endl;
for (const auto& text : texts) {
std::cout << text << std::endl;
}
} else {
std::cout << "Failed to send HTTP request." << std::endl;
return 1;
}
return 0;
}
Java
import okhttp3.*;
import com.fasterxml.jackson.databind.ObjectMapper;
import com.fasterxml.jackson.databind.JsonNode;
import com.fasterxml.jackson.databind.node.ObjectNode;
import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;
import java.util.Base64;
public class Main {
public static void main(String[] args) throws IOException {
String API_URL = "http://localhost:8080/ocr"; // 服务URL
String imagePath = "./demo.jpg"; // 本地图像
String outputImagePath = "./out.jpg"; // 输出图像
// 对本地图像进行Base64编码
File file = new File(imagePath);
byte[] fileContent = java.nio.file.Files.readAllBytes(file.toPath());
String imageData = Base64.getEncoder().encodeToString(fileContent);
ObjectMapper objectMapper = new ObjectMapper();
ObjectNode params = objectMapper.createObjectNode();
params.put("image", imageData); // Base64编码的文件内容或者图像URL
// 创建 OkHttpClient 实例
OkHttpClient client = new OkHttpClient();
MediaType JSON = MediaType.Companion.get("application/json; charset=utf-8");
RequestBody body = RequestBody.Companion.create(params.toString(), JSON);
Request request = new Request.Builder()
.url(API_URL)
.post(body)
.build();
// 调用API并处理接口返回数据
try (Response response = client.newCall(request).execute()) {
if (response.isSuccessful()) {
String responseBody = response.body().string();
JsonNode resultNode = objectMapper.readTree(responseBody);
JsonNode result = resultNode.get("result");
String base64Image = result.get("image").asText();
JsonNode texts = result.get("texts");
byte[] imageBytes = Base64.getDecoder().decode(base64Image);
try (FileOutputStream fos = new FileOutputStream(outputImagePath)) {
fos.write(imageBytes);
}
System.out.println("Output image saved at " + outputImagePath);
System.out.println("\nDetected texts: " + texts.toString());
} else {
System.err.println("Request failed with code: " + response.code());
}
}
}
}
Go
package main
import (
"bytes"
"encoding/base64"
"encoding/json"
"fmt"
"io/ioutil"
"net/http"
)
func main() {
API_URL := "http://localhost:8080/ocr"
imagePath := "./demo.jpg"
outputImagePath := "./out.jpg"
// 对本地图像进行Base64编码
imageBytes, err := ioutil.ReadFile(imagePath)
if err != nil {
fmt.Println("Error reading image file:", err)
return
}
imageData := base64.StdEncoding.EncodeToString(imageBytes)
payload := map[string]string{"image": imageData} // Base64编码的文件内容或者图像URL
payloadBytes, err := json.Marshal(payload)
if err != nil {
fmt.Println("Error marshaling payload:", err)
return
}
// 调用API
client := &http.Client{}
req, err := http.NewRequest("POST", API_URL, bytes.NewBuffer(payloadBytes))
if err != nil {
fmt.Println("Error creating request:", err)
return
}
res, err := client.Do(req)
if err != nil {
fmt.Println("Error sending request:", err)
return
}
defer res.Body.Close()
// 处理接口返回数据
body, err := ioutil.ReadAll(res.Body)
if err != nil {
fmt.Println("Error reading response body:", err)
return
}
type Response struct {
Result struct {
Image string `json:"image"`
Texts []map[string]interface{} `json:"texts"`
} `json:"result"`
}
var respData Response
err = json.Unmarshal([]byte(string(body)), &respData)
if err != nil {
fmt.Println("Error unmarshaling response body:", err)
return
}
outputImageData, err := base64.StdEncoding.DecodeString(respData.Result.Image)
if err != nil {
fmt.Println("Error decoding base64 image data:", err)
return
}
err = ioutil.WriteFile(outputImagePath, outputImageData, 0644)
if err != nil {
fmt.Println("Error writing image to file:", err)
return
}
fmt.Printf("Image saved at %s.jpg\n", outputImagePath)
fmt.Println("\nDetected texts:")
for _, text := range respData.Result.Texts {
fmt.Println(text)
}
}
C#
using System;
using System.IO;
using System.Net.Http;
using System.Net.Http.Headers;
using System.Text;
using System.Threading.Tasks;
using Newtonsoft.Json.Linq;
class Program
{
static readonly string API_URL = "http://localhost:8080/ocr";
static readonly string imagePath = "./demo.jpg";
static readonly string outputImagePath = "./out.jpg";
static async Task Main(string[] args)
{
var httpClient = new HttpClient();
// 对本地图像进行Base64编码
byte[] imageBytes = File.ReadAllBytes(imagePath);
string image_data = Convert.ToBase64String(imageBytes);
var payload = new JObject{ { "image", image_data } }; // Base64编码的文件内容或者图像URL
var content = new StringContent(payload.ToString(), Encoding.UTF8, "application/json");
// 调用API
HttpResponseMessage response = await httpClient.PostAsync(API_URL, content);
response.EnsureSuccessStatusCode();
// 处理接口返回数据
string responseBody = await response.Content.ReadAsStringAsync();
JObject jsonResponse = JObject.Parse(responseBody);
string base64Image = jsonResponse["result"]["image"].ToString();
byte[] outputImageBytes = Convert.FromBase64String(base64Image);
File.WriteAllBytes(outputImagePath, outputImageBytes);
Console.WriteLine($"Output image saved at {outputImagePath}");
Console.WriteLine("\nDetected texts:");
Console.WriteLine(jsonResponse["result"]["texts"].ToString());
}
}
Node.js
const axios = require('axios');
const fs = require('fs');
const API_URL = 'http://localhost:8080/ocr'
const imagePath = './demo.jpg'
const outputImagePath = "./out.jpg";
let config = {
method: 'POST',
maxBodyLength: Infinity,
url: API_URL,
data: JSON.stringify({
'image': encodeImageToBase64(imagePath) // Base64编码的文件内容或者图像URL
})
};
// 对本地图像进行Base64编码
function encodeImageToBase64(filePath) {
const bitmap = fs.readFileSync(filePath);
return Buffer.from(bitmap).toString('base64');
}
// 调用API
axios.request(config)
.then((response) => {
// 处理接口返回数据
const result = response.data["result"];
const imageBuffer = Buffer.from(result["image"], 'base64');
fs.writeFile(outputImagePath, imageBuffer, (err) => {
if (err) throw err;
console.log(`Output image saved at ${outputImagePath}`);
});
console.log("\nDetected texts:");
console.log(result["texts"]);
})
.catch((error) => {
console.log(error);
});
PHP
<?php
$API_URL = "http://localhost:8080/ocr"; // 服务URL
$image_path = "./demo.jpg";
$output_image_path = "./out.jpg";
// 对本地图像进行Base64编码
$image_data = base64_encode(file_get_contents($image_path));
$payload = array("image" => $image_data); // Base64编码的文件内容或者图像URL
// 调用API
$ch = curl_init($API_URL);
curl_setopt($ch, CURLOPT_POST, true);
curl_setopt($ch, CURLOPT_POSTFIELDS, json_encode($payload));
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
$response = curl_exec($ch);
curl_close($ch);
// 处理接口返回数据
$result = json_decode($response, true)["result"];
file_put_contents($output_image_path, base64_decode($result["image"]));
echo "Output image saved at " . $output_image_path . "\n";
echo "\nDetected texts:\n";
print_r($result["texts"]);
?>
通用图像识别产线中包含了主体检测模块和图像特征模块，有若干模型可供选择，您可以根据下边的 benchmark 数据来选择使用的模型。如您更考虑模型精度，请选择精度较高的模型，如您更考虑模型推理速度，请选择推理速度较快的模型，如您更考虑模型存储大小，请选择存储大小较小的模型。
