Safe Search model update
We will be updating the SAFE_SEARCH_DETECTION feature model to improve quality.
We'll support both the current model and the new model for the next 90 days. After 90 days, the new model will become the default. The current model can still be accessed by specifying "builtin/legacy" for an additional 90 days before it's deprecated.
To use the new model, specify "builtin/latest" in the model field of a Feature object.
New label detection model
An improved model is now available for Label Detection. Along with the improved model, the topicality field is now populated correctly.
Specify "builtin/latest" in the model field of a Feature object to use the new model.
We'll support both the current model and the new model the next 90 days. After 90 days, the new models will become the default. The current models can still be accessed by specifying "builtin/legacy" for an additional 90 days before they are deprecated.
Updated feature models
Improved models are now available for the following features:
Specify "builtin/latest" in the model field of a Feature object to use the new models.
We'll support both the current model and the new model the next 90 days. After 90 days, the new models will become the default. The current models can still be accessed by specifying "builtin/legacy" for an additional 90 days before they are deprecated.
Change in OCR model behavior when detecting line break hyphens
Soft hyphens are used for the purpose of breaking words across lines. The previous ("builtin/legacy") version used the BreakType HYPHEN to represent a soft hyphen. The new stable ("builtin/latest") version represents it as a new symbol with literal text "-" and BreakType EOL_SURE_SPACE.
Consider the following example text and OCR model output:
Sample text
"Mr. White has had considerable experience as a Veteri-
nary surgeon, and will attend practice in that line."
Output ("builtin/legacy" model):
[...]
{
"property": {
"detectedBreak": {
"type": "HYPHEN"
}
},
"boundingBox": {
"vertices": [
[...]
]
},
"text": "i"
}
[...]
Output ("builtin/latest" model):
{
"boundingBox": {
"vertices": [
[...]
]
},
"text": "i"
},
{
"property": {
"detectedBreak": {
"type": "EOL_SURE_SPACE"
}
},
"boundingBox": {
"vertices": [
[...]
]
},
"text": "-"
}
Product Search legacy category migration
The legacy categories "apparel", "homegoods", and "toys" have been upgraded. See the December 5, 2022 release note for more information.
Landmark Detection Upgrade
Specify "builtin/latest" in the model field of a Feature object to use the new model.
We'll support both the current model and the new model the next 90 days. After 90 days the current model will be deprecated and only the new model will be used for all landmark detection requests.
Face Detection Upgrade
Specify "builtin/latest" in the model field of a Feature object to use the new model.
We'll support both the current model and the new model the next 90 days. After 90 days the latest model will become the default model. The old model will be available for another 90 days by specifying "builtin/legacy".
Product Search legacy category migration
In 90 days, the legacy categories "apparel", "homegoods", and "toys" will be upgraded. You will still be able to use these categories. However, when running searches, they will perform similar to the "apparel-v2", "homegoods-v2", and "toys-v2" categories.
OCR model migration
The TEXT_DETECTION and DOCUMENT_TEXT_DETECTION models have been upgraded to newer versions. The API interface and client library will be the same as the previous version. The API follows the same Service Level Agreement.
The legacy models can still be accessed until August 20 2022. Specify "builtin/legacy" in the model field of a Feature object to get the old model results. After August 20, 2022 the legacy models will no longer be offered.
]]>OCR model migration reverted
We have switched the "builtin/stable" model back to the original version temporarily while we fix a bug resulting from this migration. The week of May 16th, we will update the "builtin/stable" model used for OCR again with the model from "builtin/latest" and create a new release note.
You will be able to use the original model as "builtin/legacy" for 90 more days after we upgrade "builtin/stable".
]]>OCR model migration
The TEXT_DETECTION and DOCUMENT_TEXT_DETECTION models have been upgraded to newer versions. The API interface and client library will be the same as the previous version. The API follows the same Service Level Agreement.
The legacy models can still be accessed until August 02 2022. Specify "builtin/legacy" in the model field of a Feature object to get the old model results. After August 02, 2022 the legacy models will no longer be offered.
]]>OCR model update
We have updated the "builtin/latest" OCR model with quality improvements. Consequently, customers can continue to test this model for 90 additional days.
Please note that you have 90 days from today to test the new model by specifying "builtin/latest" in the model field of the Feature object. At the end of that period, it will be promoted to the default model accessible as "builtin/stable". After that event, the original models will still be available for another 90 days using "builtin/legacy". If you encounter problems with this upgrade, please contact Vision API engineering team by submitting a ticket in the private issue tracker.
For the original announcement of this change, see the October 1, 2021 release note.
Region forwarding from the global to the regional endpoint has been deprecated. For more information, see the October 1, 2021 release note.
]]>OCR Model Update
An improved model is now available for Text Detection (OCR). The new model can be used with TEXT_DETECTION and DOCUMENT_TEXT_DETECTION features. The same model is used for requests sent to both features.
With the new model, the distribution of confidence scores of responses will change. For more information, see Service announcements.
Please note that you have 90 days from today to test the new model by specifying "builtin/latest" in the model field of the Feature object. At the end of that period, it will be promoted to the default model accessible as "builtin/stable". After that event, the original models will still be available for another 90 days using "builtin/legacy". If you encounter problems with this upgrade, please contact Vision API engineering team by submitting a ticket in the private issue tracker.
Deprecate region forwarding In 90 days, specifying the location "us" or "eu" in the request to the global endpoint vision.googleapis.com will no longer be supported. Instead you should directly call the "us" or "eu" region endpoints (us-vision.googleapis.com or eu-vision.googleapis.com). You can find more information in the Multi-regional support section of the feature pages.
New multi-regional support for features
The Vision API now offers multi-regional support (us and eu) for the LABEL_DETECTION and SAFE_SEARCH features.
EXIF rotation featured fixed
EXIF rotation is now disabled.
For more information, see the March 8, 2021 release note.
]]>EXIF rotation feature fix
This fix will disable EXIF rotation, a feature activated by the model update mentioned in the November 11, 2020 release note. This feature affects the DOCUMENT_TEXT_DETECTION and TEXT_DETECTION features.
EXIF rotation will be turned down on March 22, 2021. If your usage relies on this specific behavior, please file a feature request to us.
]]>OCR On-Prem General Availability (GA) release
OCR On-Prem is now generally available for approved customers. OCR On-Prem enables easy integration of Google image text recognition technologies into your on-premises solution.
For more information, refer to the product documentation. Approved customers can also view the marketplace entry .
]]>Confidence score field addition for TEXT_DETECTION
You can now provide the flag TextDetectionParams.enable_text_detection_confidence_score to a TEXT_DETECTION request to get a confidence score for response information.
LABEL_DETECTION model upgrade
The latest LABEL_DETECTION model announced on October 16, 2020 has been promoted to the default model. The original model will still be available for another 60 days using "builtin/legacy".
OCR legacy model access discontinued
Extended support of the legacy TEXT_DETECTION and DOCUMENT_TEXT_DETECTION models ("builtin/legacy_20190601") is now discontinued.
See the June 11, 2020 release note for more information.
]]>LABEL_DETECTION model upgrade
The LABEL_DETECTION model will undergo an upgrade over the next 90 days to a newer version. The API interface and client library will be the same as with the previous version. The API follows the same Service Level Agreement.
Please note that you have 30 days from today to test the new model by specifying "builtin/latest" in the model field of the Feature object while requesting image annotation. At the end of that period, it will be promoted to the default model accessible as "builtin/stable". After that event, the original model will still be available for another 60 days using "builtin/legacy".
If you encounter problems with this upgrade, please contact Vision API engineering team by submitting a ticket in the private issue tracker.
]]>OCR legacy model access extension
Based on customer feedback, we have decided to extend support of the legacy TEXT_DETECTION and DOCUMENT_TEXT_DETECTION models. These legacy models are accessed by specifying "builtin/legacy_20190601" in the model of a Feature object.
These models will now be accessible until November 15, 2020 (6 months from launch date) to give customers more time to adapt and migrate to the new model.
See the May 15, 2020 release note for the original update announcement.
]]>Access Transparency GA
Access Transparency logging is now Generally Available. If you want to enable Access Transparency logs, see Enabling Access Transparency.
]]>OCR model upgrades
Note: As per the June 11, 2020 release note, the legacy models are accessible through November 15, 2020.
The TEXT_DETECTION and DOCUMENT_TEXT_DETECTION models have been upgraded to newer versions. The API interface and client library will be the same as previous version. The API follows the same Service Level Agreement.
The legacy models can still be accessed until June 30, 2020. Specify
"builtin/legacy_20190601" in the model field of a
Feature object to get the old model results. After June 30, 2020 the old models will not longer be offered.
For more information, see the product documentation.
]]>CMEK compliance
Vision API is now compliant with customer-managed encryption keys (CMEK). To learn more, vist the CMEK compliance page. Please note that Product Search is not CMEK compliant at this time.
]]>SafeSearch Detection update
The SafeSearch model has been upgraded to a newer version. The API interface and client library will be the same as previous version. The API follows the same Service Level Agreement.
For more information, see the product documentation.
]]>Cloud Vision API will not return gendered labels such as 'man' and 'woman' after February 19, 2020
Detecting labels in an image containing humans will result in non-gendered label such as 'person' being returned. Our prior approach was to return gendered terms, like 'man' or 'woman'.
Given that a person's gender cannot be inferred by appearance, we have decided to remove these labels in order to align with the Artificial Intelligence Principles at Google, specifically Principle #2: Avoid creating or reinforcing unfair bias.
]]>Regional endpoints available for OCR
The Vision API now offers multi-regional support (us and eu) for the OCR feature.
Using a multi-region endpoint enables you to configure the Vision API to store and perform machine learning (OCR) on your data in the United States or European Union.
]]>Beta feature
The following beta features are available in API version v1p4beta1:
Packaged goods and general vertical:
The following product categories have been updated or added for General Availability:
packagedgoods-v1 (updated)general-v1 (added)Batch deletion
Batch deletion is now offered for the following product types:
See the "Deleting resources" topic for more information.
Model update: The Object Localizer model has been updated.
Responses to images:annotate requests now include an objectAnnotation field with a label for the object defined by the bounding box indicated. See the "Searching for products" topic for more information.
VPC Service Controls
Vision Product Search VPC Service Controls provide additional security for your pipeline's resources and services. To learn more about VPC Service Controls, see the VPC Service Controls overview.
To learn about the limitations of using Vision Product Search with VPC Service Controls, see the supported products and limitations.
]]>OCR regional support
You can now specify a continent-level region for data processing of OCR requests. For more infomation, see the OCR how-to pages:
]]>Improved detection models are now default for the following features:
The legacy model can still be accessed for 90 days by specifying
"builtin/legacy" in the model field of a
Feature object.
Spring framework integration
If you write your applications in Java with the Spring Framework, we now provide a guide to help you add Spring Cloud Vision API to your application. Spring Cloud Vision can make it easier and more efficient to work with Cloud Vision.
]]>