Handwritten Text OCR
Function
Handwriting OCR recognizes the handwritten and printed text and returns structured information in JSON format. For details about the constraints on using this API, see Constraints. For details about how to use this API, see Introduction to OCR.
Prerequisites
Before using Handwritten Text OCR, you need to apply for the service and complete authentication. For details, see Subscribing to OCR and Authentication.
URI
POST https://{endpoint}/v2/{project_id}/ocr/handwriting
| Parameter | Mandatory | Description |
|---|---|---|
| endpoint | Yes | Domain name or IP address of the server bearing the REST service endpoint. The endpoint varies depending on services in different regions. For more details, see Endpoints. For example, the endpoint of OCR in the CN North-Beijing4 region is ocr.cn-north-4.myhuaweicloud.com. |
| project_id | Yes | Project ID, which can be obtained from Obtaining a Project ID. |
Request Parameters
| Parameter | Mandatory | Type | Description |
|---|---|---|---|
| X-Auth-Token | Yes | String | User token During API authentication using a token, the token is added to requests to obtain permissions for calling the API. The value of X-Subject-Token in the response header is the obtained token. |
| Content-Type | Yes | String | MIME type of the request body. The value is application/json. |
| Parameter | Mandatory | Type | Description |
|---|---|---|---|
| image | No. Set either this parameter or url. | String | Base64 character string converted from the image. The size cannot exceed 10 MB. The narrow edge contains at least 8 pixels and the wide edge contains at most 8,192 pixels. The JPEG, JPG, PNG, BMP, and TIFF formats are supported. |
| url | No. Set either this parameter or image. | String | Image URL. Currently, the following URLs are supported:
NOTE:
|
| quick_mode | No | Boolean | If the quick mode is enabled, a single-line text image (containing only one line of text and the text area occupies more than 50% of the total text area) can be quickly recognized. Possible values are as follows:
If this parameter is not specified, the default value false is used, indicating that the quick mode is disabled. |
| char_set | No | String | Character set. You can specify the range of the output character set as required. Possible values are as follows:
If this parameter is not specified, general is used by default. |
| detect_direction | No | Boolean | Whether to enable the function of aligning tilted images. The options are as follows:
An image tilted at any angle can be aligned. If this parameter is not specified, the default value false is used. |
Response Parameters
Response parameters and status codes vary in different recognition results. They are described as below.
Status code: 200
| Parameter | Type | Description |
|---|---|---|
| result | HandwritingResult object | Calling result of a successful API call This parameter is not included when the API fails to be called. |
| Parameter | Type | Description |
|---|---|---|
| words_block_count | Integer | Number of detected text blocks |
| words_block_list | Array of HandwritingItemsResponse objects | List of text blocks to be recognized. The output sequence is from left to right and from top to bottom. |
| Parameter | Type | Description |
|---|---|---|
| words | String | Recognition result of a text block |
| type | String | Type of the recognition result. The return value is text. |
| confidence | Number | Confidence information of a related field. The value ranges from 0 to 1. A higher confidence level indicates a higher reliability and accuracy of the corresponding field identified. The confidence is not equal to the accuracy, and is calculated through related algorithms. |
| location | Array of integers | List of location information about a words block, including the coordinates (x, y) of vertexes of the text block, where the coordinate origin is the upper-left vertex of the image. The x-axis is horizontal, and the y-axis is vertical. |
Status code: 400
| Parameter | Type | Description |
|---|---|---|
| error_code | String | Error code of a failed API call. For details, see Error Codes. If error code ModelArts.4204 is displayed, refer to Why Is a Message Stating "ModelArts.4204" Displayed When the OCR API Is Called? This parameter is not included when the API is successfully called. |
| error_msg | String | Error message returned when the API fails to be called This parameter is not included when the API is successfully called. |
Request Example
- The endpoint is the request URL for calling an API. Endpoints vary depending on services and regions. For details, see Endpoints.
For example, Handwritten Text OCR is deployed in the CN North-Beijing4 region. The endpoint is ocr.cn-north-4.myhuaweicloud.com. The request URL is https://ocr.cn-north-4.myhuaweicloud.com/v2/{project_id}/ocr/handwriting. project_id is the project ID. For details about how to obtain the project ID, see Obtaining a Project ID.
- For details about how to obtain a token, see Making an API Request.
- Request example (Method 1: Use the image Base64 string.)
POST https://{endpoint}/v2/{project_id}/ocr/handwriting Request Header: Content-Type: application/json X-Auth-Token: MIINRwYJKoZIhvcNAQcCoIINODCCDTQCAQExDTALBglghkgBZQMEAgEwgguVBgkqhkiG... Request Body: { "image": "/9j/4AAQSkZJRgABAgEASABIAAD/4RFZRXhpZgAATU0AKgAAAA...", "quick_mode": false, "char_set": "general", "detect_direction": false }
- Request example (Method 2: Use the image URL.)
POST https://{endpoint}/v2/{project_id}/ocr/handwriting Request Header: Content-Type: application/json X-Auth-Token: MIINRwYJKoZIhvcNAQcCoIINODCCDTQCAQExDTALBglghkgBZQMEAgEwgguVBgkqhkiG... Request Body: { "url":"https://BucketName.obs.xxxx.com/ObjectName", "quick_mode ":false, "char_set": "general", "detect_direction": false }
- Sample code for a Python 3 request (For codes in other languages, refer to the following sample or use OCR SDK.)
# encoding:utf-8 import requests import base64 url = "https://{endpoint}/v2/{project_id}/ocr/handwriting" token = "Actual token value obtained by the user" headers = {'Content-Type': 'application/json', 'X-Auth-Token': token} imagepath = r'./data/handwriting-demo.png' with open(imagepath, "rb") as bin_data: image_data = bin_data.read() image_base64 = base64.b64encode(image_data).decode("utf-8") # Base64 encoding of images. payload = {"image": image_base64} # url or image. response = requests.post(url, headers=headers, json=payload) print(response.text)
Example Response
Status code: 200
Successful response example
{
"result": {
"words_block_count": 2,
"words_block_list": [
{
"words": "Words recognized from the image",
"type": "text",
"confidence": 0.98,
"location": [
[282, 45],
[461, 47],
[460, 77],
[280, 76]
]
},
{
"words": "Words recognized from the image",
"type": "text",
"confidence": 0.99,
"location": [
[949, 52],
[1095, 53],
[1100, 87],
[953, 86]
]
}
]
}
} Status code: 400
Failure response example
{
"error_code": "AIS.0103",
"error_msg": "The image size does not meet the requirements."
} Status Codes
| Status Code | Description |
|---|---|
| 200 | Success response |
| 400 | Failure response |
For details about status codes, see Status Codes.
Error Codes
For details about error codes, see Error Codes.
Last Article: Auto Classification OCR
Next Article: ID Card OCR
Did this article solve your problem?
Thank you for your score！Your feedback would help us improve the website.