Image OCR

General OCR

package main

import (
    "encoding/json"
    "fmt"
    "os"
    "strconv"

    "github.com/aliyun/alibaba-cloud-sdk-go/services/green"
)

func main() {
    // Reuse the client across calls to avoid repeated connection overhead.
    client, _err := green.NewClientWithAccessKey(
        "cn-shanghai",
        os.Getenv("ALIBABA_CLOUD_ACCESS_KEY_ID"),
        os.Getenv("ALIBABA_CLOUD_ACCESS_KEY_SECRET"),
    )
    if _err != nil {
        fmt.Println(_err.Error())
        return
    }

    task := map[string]interface{}{
        "dataId": "<your-data-id>",   // Unique ID for tracking this request
        "url":    "<your-image-url>",
    }

    content, _ := json.Marshal(map[string]interface{}{
        "tasks":   task,
        "scenes":  [...]string{"ocr"},
        "bizType": "<your-business-scenario>",
    })

    request := green.CreateImageSyncScanRequest()
    request.SetContent(content)

    response, _err := client.ImageSyncScan(request)
    if _err != nil {
        fmt.Println(_err.Error())
        return
    }
    if response.GetHttpStatus() != 200 {
        fmt.Println("response not success. status:" + strconv.Itoa(response.GetHttpStatus()))
        return
    }
    fmt.Println(response.GetHttpContentString())
}

Replace the following placeholders before running:

Structured card OCR

To extract text from a structured card, add the extras field with the card parameter. The following example detects the front of an ID card.

// Recognize the front of an ID card.
cardExtras := map[string]interface{}{"card": "id-card-front"}

// To recognize the back of an ID card instead, use:
// cardExtras := map[string]interface{}{"card": "id-card-back"}

content, _ := json.Marshal(map[string]interface{}{
    "tasks":   task,
    "scenes":  [...]string{"ocr"},
    "bizType": "<your-business-scenario>",
    "extras":  cardExtras,
})

The card parameter accepts the following values: