我创建了一个简单的类来测试Google视觉OCR API。我正在传递一个包含5个字母的简单图像，该图像应该返回其中包含“ CRAIG”的字符串。尽管此API调用返回了很多额外的信息：
{
"property": {
"detectedLanguages": [
{
"languageCode": "en"
}
]
},
"boundingBox": {
"vertices": [
{
"x": 183,
"y": 105
},
{
"x": 674,
"y": 105
},
{
"x": 674,
"y": 253
},
{
"x": 183,
"y": 253
}
]
},
"symbols": [
{
"property": {
"detectedLanguages": [
{
"languageCode": "en"
}
]
},
"boundingBox": {
"vertices": [
{
"x": 183,
"y": 105
},
{
"x": 257,
"y": 105
},
{
"x": 257,
"y": 253
},
{
"x": 183,
"y": 253
}
]
},
"text": "C",
"confidence": 0.99
},
{
"property": {
"detectedLanguages": [
{
"languageCode": "en"
}
]
},
"boundingBox": {
"vertices": [
{
"x": 249,
"y": 105
},
{
"x": 371,
"y": 105
},
{
"x": 371,
"y": 253
},
{
"x": 249,
"y": 253
}
]
},
"text": "R",
"confidence": 0.99
},
{
"property": {
"detectedLanguages": [
{
"languageCode": "en"
}
]
},
"boundingBox": {
"vertices": [
{
"x": 459,
"y": 105
},
{
"x": 581,
"y": 105
},
{
"x": 581,
"y": 253
},
{
"x": 459,
"y": 253
}
]
},
"text": "A",
"confidence": 0.99
},
{
"property": {
"detectedLanguages": [
{
"languageCode": "en"
}
]
},
"boundingBox": {
"vertices": [
{
"x": 582,
"y": 105
},
{
"x": 638,
"y": 105
},
{
"x": 638,
"y": 253
},
{
"x": 582,
"y": 253
}
]
},
"text": "I",
"confidence": 0.98
},
{
"property": {
"detectedLanguages": [
{
"languageCode": "en"
}
],
"detectedBreak": {
"type": "LINE_BREAK"
}
},
"boundingBox": {
"vertices": [
{
"x": 636,
"y": 105
},
{
"x": 674,
"y": 105
},
{
"x": 674,
"y": 253
},
{
"x": 636,
"y": 253
}
]
},
"text": "G",
"confidence": 0.99
}
],
"confidence": 0.98
}
我如何只取回信件？
class：
public static void Main(string[] args)
{
string credential_path = @"C:\Users\35385\nodal.json";
System.Environment.SetEnvironmentVariable("GOOGLE_APPLICATION_CREDENTIALS", credential_path);
// Instantiates a client
var client = ImageAnnotatorClient.Create();
// Load the image file into memory
var image = Image.FromFile("vision.jpg");
// Performs label detection on the image file
var response = client.DetectDocumentText(image);
foreach (var page in response.Pages)
{
foreach (var block in page.Blocks)
{
foreach (var paragraph in block.Paragraphs)
{
Console.WriteLine(string.Join("\n", paragraph.Words));
}
}
}
}
我传递的图像是我用油漆画出的一个简单单词：
<< img src =“ https://image.soinside.com/eyJ1cmwiOiAiaHR0cHM6Ly9pLmliYi5jby85SGo3cWI1L3Zpc2lvbi5qcGcifQ==” alt =“忙碌的猫”>
经过一番研究，以下内容为我提供了这个词，并且输出的内容也更加简洁：
Block Text at (183, 105) - (674, 105) - (674, 253) - (183, 253)
Paragraph at (183, 105) - (674, 105) - (674, 253) - (183, 253)
Word: CRAIG
方法：
foreach (var page in response.Pages)
{
foreach (var block in page.Blocks)
{
string box = string.Join(" - ", block.BoundingBox.Vertices.Select(v => $"({v.X}, {v.Y})"));
Console.WriteLine($"Block {block.BlockType} at {box}");
foreach (var paragraph in block.Paragraphs)
{
box = string.Join(" - ", paragraph.BoundingBox.Vertices.Select(v => $"({v.X}, {v.Y})"));
Console.WriteLine($" Paragraph at {box}");
foreach (var word in paragraph.Words)
{
Console.WriteLine($" Word: {string.Join("", word.Symbols.Select(s => s.Text))}");
}
}
}
}
尝试更改..
var response = client.DetectDocumentText(image);
收件人
var response = client.DetectText(image);
说明
以下是GOOGLE CLOUD VISION API文档中的一些信息
Vision API可以检测并提取图像中的文本。有两个支持光学字符识别（OCR）的注释功能：
TEXT_DETECTION从任何图像检测并提取文本。例如，一张照片可能包含路牌或交通标志。 JSON包括整个提取的字符串，单个单词及其边界框。
DOCUMENT_TEXT_DETECTION也从图像中提取文本，但针对密集文本和文档优化了响应。 JSON包括页面，块，段落，单词和中断信息。