Processing Image Files
Private AI supports scanning images for PII and creating de-identified or redacted copies. Private AI’s supported entity types function across each file type, with localized variants of different PII (Personally Identifiable Information) entities, PHI (Protected Health Information) entities, and PCI (Payment Card Industry) entities being detected. Our Supported Languages and Supported Entity Types page provides a more detailed look.
info
If you'd like to try it yourself, please visit our free interactive web demo. No code or account is necessary.
How Images Are Processed
Image files are processed as follows:
- Non-text PII such as faces and license plates are detected and de-identified via blurring or black box redaction.
- The resulting image is run an OCR system to detect any text present.
- The output of the OCR system is passed to a PII detection module.
- Any PII found in the previous step is de-identified via blurring or black box redaction.
info
You can configure the OCR System by setting it as an Environment Variable or sending it in the request object. Check out our OCR Guide to further understand the OCR modes and their usage.
Constraints
- There is limited support for 8-bit PNG images.
Supported File Types
File Type | Extension | Content Type | Added In |
---|---|---|---|
JPEG image | .jpg , .jpeg |
image/jpg , image/jpeg |
3.0.0 |
TIFF image | .tif , .tiff |
image/tif , image/tiff |
3.0.0 |
PNG image | .png |
image/png |
3.4.0 |
BMP image | .bmp |
image/bmp , image/x-ms-bmp |
3.4.0 |
Support Matrix
CPU Container | GPU Container | Community API | Professional API | PrivateGPT UI | |
---|---|---|---|---|---|
Supported? | Yes | Yes | Yes | Yes | No |
Sample Request
info
Please sign up for a free API key to run this code.
{
"file": {
"data": file_content_base64,
"content_type": "image/jpeg",
},
"entity_detection": {
"return_entity": True
}
}
echo '{
"file": {"data": "'$(base64 -w 0 sample.jpeg)'",
"content_type": "image/jpeg"},
"entity_detection": {"return_entity": "True"}
}' \
| curl --request POST --url 'https://api.private-ai.com/community/v4/process/files/base64' \
-H 'Content-Type: application/json' \
-H 'x-api-key: <YOUR KEY HERE>' \
-d @- \
| jq -r .processed_file \
| base64 -d > 'sample.redacted.jpeg'
import requests
import base64
file_url = "https://paidocumentation.blob.core.windows.net/$web/sample.jpeg"
filename_out = "/path/to/output/sample.redacted.jpeg"
file_content = requests.get(file_url).content
file_content_base64 = base64.b64encode(file_content).decode()
url = "https://api.private-ai.com/community/v4/process/files/base64"
headers = {"Content-Type": "application/json", "x-api-key": "<INSERT API KEY>"}
payload = {
"file":{
"data": file_content_base64,
"content_type": "image/jpeg",
},
"entity_detection": {
"return_entity": True
}
}
response = requests.post(url, json=payload, headers=headers)
with open(filename_out, "wb") as f:
f.write(base64.b64decode(response.json()["processed_file"]))
from privateai_client import PAIClient
from privateai_client.objects import request_objects
import base64
filename_in = "sample.jpeg"
filename_out = "sample.redacted.jpeg"
file_type= "image/jpeg"
client = PAIClient(url="https://api.private-ai.com/community/v4/", api_key="<YOUR API KEY>")
with open(filename_in, "rb") as b64_file:
file_data = base64.b64encode(b64_file.read())
file_data = file_data.decode("ascii")
file_obj = request_objects.file_obj(data=file_data, content_type=file_type)
request_obj = request_objects.file_base64_obj(file=file_obj)
resp = client.process_files_base64(request_object=request_obj)
with open(filename_out, 'wb') as redacted_file:
processed_file = resp.processed_file.encode("ascii")
processed_file = base64.b64decode(processed_file, validate=True)
redacted_file.write(processed_file)
Sample Response
"processed_file": "Base64 Encoded File Content of the Redacted File",
"processed_text":"string",
"entities":"List[Entity]",
"entities_present":true,
"languages_detected":{"lang_1":0.67, "lang_2": 0.74}