Azure AI 视觉图像分析 Java SDK

azure-ai-vision-imageanalysis-java
分类编程
作者Agentic Awesome Skills 社区
许可MIT
评分4.80/5
使用14.3K

Azure AI Vision Image Analysis Java SDK

使用 Azure AI Vision Image Analysis Java SDK 构建图像分析应用程序。

安装

xml
<dependency>
    <groupId>com.azure</groupId>
    <artifactId>azure-ai-vision-imageanalysis</artifactId>
    <version>1.1.0-beta.1</version>
</dependency>

客户端创建

使用 API 密钥

java
import com.azure.ai.vision.imageanalysis.ImageAnalysisClient;
import com.azure.ai.vision.imageanalysis.ImageAnalysisClientBuilder;
import com.azure.core.credential.KeyCredential;

String endpoint = System.getenv("VISION_ENDPOINT");
String key = System.getenv("VISION_KEY");


ImageAnalysisClient client = new ImageAnalysisClientBuilder()
    .endpoint(endpoint)
    .credential(new KeyCredential(key))
    .buildClient();

异步客户端

java
import com.azure.ai.vision.imageanalysis.ImageAnalysisAsyncClient;

ImageAnalysisAsyncClient asyncClient = new ImageAnalysisClientBuilder()
    .endpoint(endpoint)
    .credential(new KeyCredential(key))
    .buildAsyncClient();

使用 DefaultAzureCredential

java
import com.azure.identity.DefaultAzureCredentialBuilder;

ImageAnalysisClient client = new ImageAnalysisClientBuilder()
    .endpoint(endpoint)
    .credential(new DefaultAzureCredentialBuilder().build())
    .buildClient();

视觉功能

| 功能 | 描述 |
|---------|-------------|
| CAPTION | 生成人类可读的图像描述 |
| DENSE_CAPTIONS | 为最多 10 个区域生成描述 |
| READ | OCR - 从图像中提取文本 |
| TAGS | 为对象、场景、动作提供内容标签 |
| OBJECTS | 检测对象并提供边界框 |
| SMART_CROPS | 智能缩略图区域 |
| PEOPLE | 检测人物及其位置 |

核心模式

生成描述

java
import com.azure.ai.vision.imageanalysis.models.*;
import com.azure.core.util.BinaryData;
import java.io.File;
import java.util.Arrays;

// 从文件读取
BinaryData imageData = BinaryData.fromFile(new File("image.jpg").toPath());


ImageAnalysisResult result = client.analyze(
    imageData,
    Arrays.asList(VisualFeatures.CAPTION),
    new ImageAnalysisOptions().setGenderNeutralCaption(true));


System.out.printf("Caption: \"%s\" (confidence: %.4f)%n",
    result.getCaption().getText(),
    result.getCaption().getConfidence());

从 URL 生成描述

java
ImageAnalysisResult result = client.analyzeFromUrl(
    "https://example.com/image.jpg",
    Arrays.asList(VisualFeatures.CAPTION),
    new ImageAnalysisOptions().setGenderNeutralCaption(true));

System.out.printf("Caption: \"%s\"%n", result.getCaption().getText());

提取文本 (OCR)

java
ImageAnalysisResult result = client.analyze(
    BinaryData.fromFile(new File("document.jpg").toPath()),
    Arrays.asList(VisualFeatures.READ),
    null);

for (DetectedTextBlock block : result.getRead().getBlocks()) {
    for (DetectedTextLine line : block.getLines()) {
        System.out.printf("Line: '%s'%n", line.getText());
        System.out.printf("  Bounding polygon: %s%n", line.getBoundingPolygon());
        
        for (DetectedTextWord word : line.getWords()) {
            System.out.printf("  Word: '%s' (confid");

ence: %.4f)%n",
word.getText(),
word.getConfidence());
}
}
}
code
### 检测对象
java
ImageAnalysisResult result = client.analyzeFromUrl(
imageUrl,
Arrays.asList(VisualFeatures.OBJECTS),
null);

for (DetectedObject obj : result.getObjects()) {
System.out.printf("Object: %s (confidence: %.4f)%n",
obj.getTags().get(0).getName(),
obj.getTags().get(0).getConfidence());

ImageBoundingBox box = obj.getBoundingBox();
System.out.printf(" Location: x=%d, y=%d, w=%d, h=%d%n",
box.getX(), box.getY(), box.getWidth(), box.getHeight());
}

code
### 获取标签
java
ImageAnalysisResult result = client.analyzeFromUrl(
imageUrl,
Arrays.asList(VisualFeatures.TAGS),
null);

for (DetectedTag tag : result.getTags()) {
System.out.printf("Tag: %s (confidence: %.4f)%n",
tag.getName(),
tag.getConfidence());
}

code
### 检测人物
java
ImageAnalysisResult result = client.analyzeFromUrl(
imageUrl,
Arrays.asList(VisualFeatures.PEOPLE),
null);

for (DetectedPerson person : result.getPeople()) {
ImageBoundingBox box = person.getBoundingBox();
System.out.printf("Person at x=%d, y=%d (confidence: %.4f)%n",
box.getX(), box.getY(), person.getConfidence());
}

code
### 智能裁剪
java
ImageAnalysisResult result = client.analyzeFromUrl(
imageUrl,
Arrays.asList(VisualFeatures.SMART_CROPS),
new ImageAnalysisOptions().setSmartCropsAspectRatios(Arrays.asList(1.0, 1.5)));

for (CropRegion crop : result.getSmartCrops()) {
System.out.printf("Crop region: aspect=%.2f, x=%d, y=%d, w=%d, h=%d%n",
crop.getAspectRatio(),
crop.getBoundingBox().getX(),
crop.getBoundingBox().getY(),
crop.getBoundingBox().getWidth(),
crop.getBoundingBox().getHeight());
}

code
### 密集描述
java
ImageAnalysisResult result = client.analyzeFromUrl(
imageUrl,
Arrays.asList(VisualFeatures.DENSE_CAPTIONS),
new ImageAnalysisOptions().setGenderNeutralCaption(true));

for (DenseCaption caption : result.getDenseCaptions()) {
System.out.printf("Caption: \"%s\" (confidence: %.4f)%n",
caption.getText(),
caption.getConfidence());
System.out.printf(" Region: x=%d, y=%d, w=%d, h=%d%n",
caption.getBoundingBox().getX(),
caption.getBoundingBox().getY(),
caption.getBoundingBox().getWidth(),
caption.getBoundingBox().getHeight());
}

code
### 多项功能
java
ImageAnalysisResult result = client.analyzeFromUrl(
imageUrl,
Arrays.asList(
VisualFeatures.CAPTION,
VisualFeatures.TAGS,
VisualFeatures.OBJECTS,
VisualFeatures.READ),
new ImageAnalysisOptions()
.setGenderNeutralCaption(true)
.setLanguage("en"));

// 访问所有结果
System.out.println("Caption: " + result.getCaption().getText());
System.out.println("Tags: " + result.getTags().size());
System.out.println("Objects: " + result.getObjects().size());
System.out.println("Text blocks: " + result.getRead().getBlocks().size());

code
### 异步分析
java
asyncClient.analyzeFromUrl(
imageUrl,
Arrays.asList(VisualFeatures.CAPTION),
null)
.subscribe(
result -> System.out.println("Caption: " + result.getCaption().getText()),
error -> System.err.println("Error: " + error.getMessage()),
() -> System.out.println("Complete")
);
code
## 错误处理
java
im
java
import com.azure.core.exception.HttpResponseException;


try {
    client.analyzeFromUrl(imageUrl, Arrays.asList(VisualFeatures.CAPTION), null);
} catch (HttpResponseException e) {
    System.out.println("Status: " + e.getResponse().getStatusCode());
    System.out.println("Error: " + e.getMessage());
}

环境变量

bash
VISION_ENDPOINT=https://<resource>.cognitiveservices.azure.com/
VISION_KEY=<your-api-key>

图像要求

  • 格式：JPEG, PNG, GIF, BMP, WEBP, ICO, TIFF, MPO
  • 大小：< 20 MB
  • 分辨率：50x50 至 16000x16000 像素

区域可用性

Caption 和 Dense Captions 需要 GPU 支持的区域。部署前请检查 支持的区域。

触发词

  • "image analysis Java"
  • "Azure Vision SDK"
  • "image captioning"
  • "OCR image text extraction"
  • "object detection image"
  • "smart crop thumbnail"
  • "detect people image"

使用场景

本技能适用于执行概览中所描述的工作流或操作。

局限性

  • 仅在任务与上述范围明确匹配时使用此技能。
  • 不要将输出结果视为特定环境验证、测试或专家评审的替代方案。
  • 如果缺少必要的输入、权限、安全边界或成功标准，请停止操作并请求澄清。