javascript - Azure 计算机视觉 : Recognize Printed Text

Question

我正在使用 Azure 计算机视觉和 Nodejs，我想提取图像上的文本，它按预期工作，但我面临一些挑战:代码:

'use strict';



const request = require('request');




const subscriptionKey = 'key';

const endpoint = 'endpoint'



var uriBase = endpoint + 'vision/v3.1/ocr';



const imageUrl = 'https://livesimply.me/wp-content/uploads/2015/09/foods-to-avoid-real-food-3036-2-1024x683.jpg';



// Request parameters.

const params = {

'language': 'unk',

'detectOrientation': 'true',

};



const options = {

uri: uriBase,

qs: params,

body: '{"url": ' + '"' + imageUrl + '"}',

headers: {

    'Content-Type': 'application/json',

    'Ocp-Apim-Subscription-Key' : subscriptionKey

}

};



request.post(options, (error, response, body) => {

if (error) {

console.log('Error: ', error);

return;

}

let jsonResponse = JSON.stringify(JSON.parse(body), null, '  ');

console.log('JSON Response\n');

console.log(jsonResponse);

});

输出:

"regions": [

{

  "boundingBox": "0,191,277,281",

  "lines": [

    {

      "boundingBox": "53,191,23,49",

      "words": [

        {

          "boundingBox": "53,191,23,49",

          "text": "in"

        }

      ]

    },

    {

      "boundingBox": "0,285,277,82",

      "words": [

        {

          "boundingBox": "0,285,150,82",

          "text": ")arb.0g"

        },

        {

          "boundingBox": "214,288,63,63",

          "text": "0%"

        }

      ]

    },

    {

      "boundingBox": "14,393,45,79",

      "words": [

        {

          "boundingBox": "14,393,45,79",

          "text": "Og"

        }

      ]

    },

    {

      "boundingBox": "213,394,63,63",

      "words": [

        {

          "boundingBox": "213,394,63,63",

          "text": "00/0"

        }

      ]

    }

  ]

},

{

  "boundingBox": "322,184,352,457",

  "lines": [

    {

      "boundingBox": "326,184,348,54",

      "words": [

        {

          "boundingBox": "326,184,239,52",

          "text": "INGREDIENTS:"

        },

        {

          "boundingBox": "588,188,86,50",

          "text": "WHITE"

        }

      ]

    },

    {

      "boundingBox": "325,248,281,59",

      "words": [

        {

          "boundingBox": "325,248,83,56",

          "text": "TUNA,"

        },

        {

          "boundingBox": "417,250,127,51",

          "text": "SOYBEAN"

        },

        {

          "boundingBox": "555,252,51,55",

          "text": "OIL,"

        }

      ]

    },

    {

      "boundingBox": "324,313,341,60",

      "words": [

        {

          "boundingBox": "324,313,155,52",

          "text": "VEGETABLE"

        },

        {

          "boundingBox": "489,316,101,56",

          "text": "BROTH,"

        },

        {

          "boundingBox": "598,317,67,56",

          "text": "SALT,"

        }

      ]

    },

    {

      "boundingBox": "324,378,334,53",

      "words": [

        {

          "boundingBox": "324,378,235,52",

          "text": "PYROPHOSPHATE"

        },

        {

          "boundingBox": "566,381,92,50",

          "text": "ADDED"

        }

      ]

    },

    {

      "boundingBox": "323,519,248,52",

      "words": [

        {

          "boundingBox": "323,519,193,51",

          "text": "DISTRIBUTED"

        },

        {

          "boundingBox": "528,521,43,50",

          "text": "BY:"

        }

      ]

    },

    {

      "boundingBox": "322,584,298,57",

      "words": [

        {

          "boundingBox": "322,584,124,50",

          "text": "BUMBLE"

        },

        {

          "boundingBox": "457,585,52,50",

          "text": "BEE"

        },

        {

          "boundingBox": "519,585,101,56",

          "text": "FOODS,"

        }

      ]

    }

  ]

},

{

  "boundingBox": "791,400,198,117",

  "lines": [

    {

      "boundingBox": "921,400,68,45",

      "words": [

        {

          "boundingBox": "921,400,68,45",

          "text": ",11."

        }

      ]

    },

    {

      "boundingBox": "791,464,128,53",

      "words": [

        {

          "boundingBox": "791,464,75,53",

          "text": "PRC:"

        },

        {

          "boundingBox": "874,467,45,48",

          "text": "x"

        }

      ]

    }

  ]

}

  ]

  }

但是我在使用这段代码时遇到了一些挑战:

1. 我希望输出为字符串而不是 JSON 树。
2. 我想只提取成分，而不是所有文本。
3. 在某些情况下，图像可能包含成分但未指定成分关键字，在这种情况下如何提取成分？

图片:

感谢各位专家的帮助。

Answer 1

我们使用计算机视觉 REST API 通过光学字符识别 (OCR) 从图像中提取打印文本。成功的响应会以 JSON 格式返回。您无法从此 Azure 认知服务获取直接字符串输出。

对于问题-

I want the output as a string and not JSON tree.

我们无法像图中所示的字符串一样直接打印成分。要提取内容并以特定格式显示它，在获取 JSON 字符串后，将其解析为 JSON 对象并运行循环以从中提取数据。之后使用 split 函数将数据存储到数组中。如下面的代码片段所示。

function(error, response, body){
    if(error) {
        console.log(error);
    } else {
        //parsing the JSON string
        var jsonObj = JSON.parse(body);

        var ob = jsonObj;
        //running loop to extract the text values
            for(i=0;i<....){
                for(j=0;j<....){
                    for(k=0;k<....){
                         var str = str + " "+ob.....text;
                    }
                    str = str + "\n";
                }
            }
          var arr = str.split("\n");

根据您获得的 JSON 结构放置您的逻辑。

对于你的第二个问题和第三个问题 -

I would like to extract just the ingredients and not the all text.

In some cases the images may have ingredients without specifying the ingredient key-word, how can I extract the ingredients in this case ?

计算机视觉将从图像中提取所有打印文本并将其作为 JSON 提供给您，您无法提取特定文本。使用与上述相同的方法，仅提取成分即可达到所需的结果。

我建议阅读这篇文章 Extract printed text (OCR) using the Computer Vision REST API and Node.js GitHub 文档以获取更多信息。