هذه الصفحة غير متوفرة حاليًا بلغتك المحلية. نحن نعمل جاهدين على إضافة المزيد من اللغات. شاكرين تفهمك ودعمك المستمر لنا.
- What's New
- Function Overview
- Product Bulletin
- Service Overview
-
Billing
- Billing Overview
- Billing Modes
- Billing Items
- Billing Examples
- Billing Mode Changes
- Renewing Subscriptions
- Bills
- Arrears
- Billing Termination
- Cost Management
-
Billing FAQ
- Why Do I Get Additional Charges or Arrears After Purchasing a Package?
- Why Can I Still Call the Service and Incur Arrears When My Account Balance Is Zero?
- Why Do I Get Additional Charges or Arrears After Unsubscribing from an OCR Service?
- Can I Refund a Package After I Buy It?
- How Is Billing Handled When a Package Is Used Up? And How Can I Check the Remaining Quota and Receive Alerts for My Package?
- How Does a Member Account Use a Package Purchased by an Enterprise Master Account?
- What Is Fee Deduction Order for Multiple Packages?
- What are Grace Period and Retention Period?
- What Is Considered Valid Billing for OCR?
- Can Different API Packages Be Shared?
- Can OCR Be Charged by Project?
- Getting Started
- User Guide
- SDK Reference
- API Reference
-
FAQs
- Subscription
-
Token-based Authentication
- What Are the Username, Domain Name, and Project Name in the Token Message Body?
- Why Is the Error Message "The account is locked." Displayed?
- Why Is the Error Message "The username or password is wrong." Displayed?
- Why Does the Token Retrieval Process Return a 401 Status Code?
- Why Does the Token Fail to Be Obtained When I Use Postman to Call an ORC API?
- Why Don't I Have Programming Access Permissions?
- Why Does the Header Overflow When I Use Postman to Call an OCR API?
-
API
- How Do I View the API Usage?
- Why Is the Actual Number of API Calls Inconsistent with the Record Displayed on the Management Console?
- Does OCR Support Batch Processing?
- Can the OCR Results Be Converted into Word, TXT, or PDF Files?
- How Do I Obtain the Base64 Code of an Image?
- What Is the Number of Concurrent OCR API Calls?
- How Do I Use OCR APIs?
- Can the Region Where OCR Is Called Be Different from the Region Where OBS Resources Are Located?
- Can the Input Data of OCR Be Stored Locally?
- How Do I Improve the Recognition Speed?
- How Do I Convert a PDF to an Image?
- Can OCR Read Images from Non-Huawei Cloud Storage?
-
SDK
- Do OCR SDKs Need to Be Purchased?
- Do OCR SDKs Need Maven to Manage Dependency Packages?
- How Do I Change the Response Type in Returned Results?
- How Can I Fix an SSL Configuration Error?
- How Can I Fix a "connect timed out" Error?
- Why Does the Project ID Fail to Be Obtained?
- What Should I Do if I Forget My AK and SK?
-
Error Code
- Why Do I Fail to Call an OCR API?
- How Do I Handle the Error APIG.0301?
- How Do I Handle the Error APIG.0201?
- How Do I Handle the Error APIG.0101?
- How Do I Handle the Error APIG.0106?
- How Do I Handle the Error APIG.0308?
- How Do I Handle the Error ModelArts.0212?
- How Do I Handle the Error ModelArts.4603 or ModelArts.4704?
- How Do I Handle the Error ModelArts.4204?
- Permissions
- Data Security and Privacy
- Regions and AZs
- General Consulting
- Videos
- Glossary
- More Documents
- General Reference
Show all
Copied.
How Do I Improve the Recognition Speed?
The speed of the OCR API depends on the image size, which affects the time needed for network transmission and Base64 decoding. Therefore, you are advised to compress the images before using OCR to process them while ensuring the required level of resolution. This will accelerate image processing by the OCR API. The JPG image format is recommended.
Based on empirical data, it is recommended to keep small images (such as ID cards with sparse text) under 1 MB, and large images (such as dense documents of the A4 paper size) under 2 MB.
For details about how to compress an image, see the following code:
import cv2 def resize_image(image, max_size): """ This code is used to expand or downsize an image proportionally. It compares the long side of the image with the input parameter max_size. If the long side of the image exceeds max_size, the image is downsized proportionally. Otherwise, the original image is returned. :param max_size: maximum length of the long side of an image. (Set this parameter based on site requirements. You are advised to set this parameter to a value as small as possible as long as the resolution requirement is met.) :return: returns the downsized image or the original image. """ height, width = image.shape[:2] max_side = max(height, width) if max_side > max_size: scale = max_size / max_side image = cv2.resize(image, None, fx=scale, fy=scale) return image image = cv2.imread('test.png') image = resize_image(image, max_size=1024)
Feedback
Was this page helpful?
Provide feedbackThank you very much for your feedback. We will continue working to improve the documentation.See the reply and handling status in My Cloud VOC.
For any further questions, feel free to contact us through the chatbot.
Chatbot