watson_developer_cloud.visual_recognition_v3 module

The IBM Watson™ Visual Recognition service uses deep learning algorithms to identify scenes, objects, and faces in images you upload to the service. You can create and train a custom classifier to identify subjects that suit your needs.

class VisualRecognitionV3(version, url='https://gateway.watsonplatform.net/visual-recognition/api', api_key=None, iam_api_key=None, iam_access_token=None, iam_url=None)[source]

Bases: watson_developer_cloud.watson_service.WatsonService

The Visual Recognition V3 service.

default_url = 'https://gateway.watsonplatform.net/visual-recognition/api'
classify(images_file=None, parameters=None, accept_language=None, images_file_content_type=None, images_filename=None, url=None, threshold=None, owners=None, classifier_ids=None, **kwargs)[source]

Classify images.

Classify images with built-in or custom classifiers.

Parameters:
  • images_file (file) – An image file (.jpg, .png) or .zip file with images. Maximum image size is 10 MB. Include no more than 20 images and limit the .zip file to 100 MB. Encode the image and .zip file names in UTF-8 if they contain non-ASCII characters. The service assumes UTF-8 encoding if it encounters non-ASCII characters. You can also include images with the url property in the parameters object.
  • parameters (str) – (Deprecated) A JSON object that specifies additional request options. The parameter can be sent as a string or a file, and can include these inputs: - url: A string with the image URL to analyze. Must be in .jpg, or .png format. The minimum recommended pixel density is 32X32 pixels per inch, and the maximum image size is 10 MB. You can also include images in the images_file parameter. - threshold: A floating point value that specifies the minimum score a class must have to be displayed in the response. The default threshold for returning scores from a classifier is 0.5. Set the threshold to 0.0 to ignore the classification score and return all values. - owners: An array of the categories of classifiers to apply. Use IBM to classify against the default general classifier, and use me to classify against your custom classifiers. To analyze the image against both classifier categories, set the value to both IBM and me. The built-in default classifier is used if both classifier_ids and owners parameters are empty. The classifier_ids parameter overrides owners, so make sure that classifier_ids is empty. - classifier_ids: Specifies which classifiers to apply and overrides the owners parameter. You can specify both custom and built-in classifiers. The built-in default classifier is used if both classifier_ids and owners parameters are empty. The following built-in classifier IDs require no training: - default: Returns classes from thousands of general tags. - food: (Beta) Enhances specificity and accuracy for images of food items. - explicit: (Beta) Evaluates whether the image might be pornographic. Example: {“classifier_ids”:[“CarsvsTrucks_1479118188”,”explicit”],”threshold”:0.6}.
  • accept_language (str) – Specifies the language of the output class names. Can be en (English), ar (Arabic), de (German), es (Spanish), it (Italian), ja (Japanese), or ko (Korean). Classes for which no translation is available are omitted. The response might not be in the specified language under these conditions: - English is returned when the requested language is not supported. - Classes are not returned when there is no translation for them. - Custom classifiers returned with this method return tags in the language of the custom classifier.
  • images_file_content_type (str) – The content type of images_file.
  • images_filename (str) – The filename for images_file.
  • url (str) – A string with the image URL to analyze. Must be in .jpg, or .png format. The minimum recommended pixel density is 32X32 pixels per inch, and the maximum image size is 10 MB. You can also include images in the images_file parameter.
  • threshold (float) – A floating point value that specifies the minimum score a class must have to be displayed in the response. The default threshold for returning scores from a classifier is 0.5. Set the threshold to 0.0 to ignore the classification score and return all values.
  • owners (list[str]) – An array of the categories of classifiers to apply. Use IBM to classify against the default general classifier, and use me to classify against your custom classifiers. To analyze the image against both classifier categories, set the value to both IBM and me. The built-in default classifier is used if both classifier_ids and owners parameters are empty. The classifier_ids parameter overrides owners, so make sure that classifier_ids is empty.
  • classifier_ids (list[str]) – The classifier_ids parameter overrides owners, so make sure that classifier_ids is empty. - classifier_ids: Specifies which classifiers to apply and overrides the owners parameter. You can specify both custom and built-in classifiers. The built-in default classifier is used if both classifier_ids and owners parameters are empty. The following built-in classifier IDs require no training: - default: Returns classes from thousands of general tags. - food: (Beta) Enhances specificity and accuracy for images of food items. - explicit: (Beta) Evaluates whether the image might be pornographic. Example: “classifier_ids=”CarsvsTrucks_1479118188”,”explicit”.
  • headers (dict) – A dict containing the request headers
Returns:

A dict containing the ClassifiedImages response.
Return type:

dict
detect_faces(images_file=None, parameters=None, images_file_content_type=None, images_filename=None, url=None, **kwargs)[source]

Detect faces in images.

Analyze and get data about faces in images. Responses can include estimated age and gender, and the service can identify celebrities. This feature uses a built-in classifier, so you do not train it on custom classifiers. The Detect faces method does not support general biometric facial recognition.

Parameters:
  • images_file (file) – An image file (.jpg, .png) or .zip file with images. Include no more than 15 images. You can also include images with the url property in the parameters object. All faces are detected, but if there are more than 10 faces in an image, age and gender confidence scores might return scores of 0.
  • parameters (str) – (Deprecated) A JSON object that specifies a single image (.jpg, .png) to analyze by URL. The parameter can be sent as a string or a file. Example: {“url”:”http://www.example.com/images/myimage.jpg”}.
  • images_file_content_type (str) – The content type of images_file.
  • images_filename (str) – The filename for images_file.
  • url (str) – The URL of an image to analyze. Must be in .gif, .jpg, .png, or .tif format. The minimum recommended pixel density is 32X32 pixels per inch, and the maximum image size is 10 MB. Redirects are followed, so you can use a shortened URL. You can also include images with the images_file parameter.
  • headers (dict) – A dict containing the request headers
Returns:

A dict containing the DetectedFaces response.
Return type:

dict
create_classifier(name, **kwargs)[source]

Create a classifier. :param str name: The name of the new classifier. Encode special characters in UTF-8. :param file <NAME>_positive_examples: A compressed (.zip) file of images that depict the visual subject for a class within the new classifier. Include at least 10 images in .jpg or .png format. The minimum recommended image resolution is 32X32 pixels. The maximum number of images is 10,000 images or 100 MB per .zip file. Encode special characters in the file name in UTF-8. :param file negative_examples: A compressed (.zip) file of images that do not depict the visual subject of any of the classes of the new classifier. Must contain a minimum of 10 images. Encode special characters in the file name in UTF-8. :param dict headers: A dict containing the request headers :return: A dict containing the Classifier response. :rtype: dict

delete_classifier(classifier_id, **kwargs)[source]

Delete a classifier.

Parameters:
  • classifier_id (str) – The ID of the classifier.
  • headers (dict) – A dict containing the request headers
Return type:

None
get_classifier(classifier_id, **kwargs)[source]

Retrieve classifier details.

Retrieve information about a custom classifier.

Parameters:
  • classifier_id (str) – The ID of the classifier.
  • headers (dict) – A dict containing the request headers
Returns:

A dict containing the Classifier response.
Return type:

dict
list_classifiers(verbose=None, **kwargs)[source]

Retrieve a list of classifiers.

Parameters:verbose (bool) – Specify true to return details about the classifiers. Omit

this parameter to return a brief list of classifiers. :param dict headers: A dict containing the request headers :return: A dict containing the Classifiers response. :rtype: dict

update_classifier(classifier_id, **kwargs)[source]

Update a classifier. :param str classifier_id: The ID of the classifier. :param file <NAME>_positive_examples: A .zip file of images that depict the visual subject of a class in the classifier. The positive examples create or update classes in the classifier. You can include more than one positive example file in a call. Include at least 10 images in .jpg or .png format. The minimum recommended image resolution is 32X32 pixels. The maximum number of images is 10,000 images or 100 MB per .zip file. Encode special characters in the file name in UTF-8. :param file negative_examples: A .zip file of images that do not depict the visual subject of any of the classes of the new classifier. Must contain a minimum of 10 images. Encode special characters in the file name in UTF-8. :param dict headers: A dict containing the request headers :return: A dict containing the Classifier response. :rtype: dict

get_core_ml_model(classifier_id, **kwargs)[source]

Retrieve a Core ML model of a classifier.

Download a Core ML model file (.mlmodel) of a custom classifier that returns <tt>”core_ml_enabled”: true</tt> in the classifier details.

Parameters:
  • classifier_id (str) – The ID of the classifier.
  • headers (dict) – A dict containing the request headers
Returns:

A Response <Response> object representing the response.
Return type:

requests.models.Response
delete_user_data(customer_id, **kwargs)[source]

Delete labeled data.

Deletes all data associated with a specified customer ID. The method has no effect if no data is associated with the customer ID. You associate a customer ID with data by passing the X-Watson-Metadata header with a request that passes data. For more information about personal data and customer IDs, see [Information security](https://console.bluemix.net/docs/services/visual-recognition/information-security.html).

Parameters:
  • customer_id (str) – The customer ID for which all data is to be deleted.
  • headers (dict) – A dict containing the request headers
Return type:

None
class Class(class_name)[source]

Bases: object

A category within a classifier.

Attr str class_name:
 The name of the class.
class ClassResult(class_name, score=None, type_hierarchy=None)[source]

Bases: object

Result of a class within a classifier.

Attr str class_name:
 Name of the class.
Attr float score:
 (optional) Confidence score for the property in the range of 0 to

1. A higher score indicates greater likelihood that the class is depicted in the image. The default threshold for returning scores from a classifier is 0.5. :attr str type_hierarchy: (optional) Knowledge graph of the property. For example, /fruit/pome/apple/eating apple/Granny Smith. Included only if identified.

class ClassifiedImage(classifiers, source_url=None, resolved_url=None, image=None, error=None)[source]

Bases: object

Results for one image.

Attr str source_url:
 (optional) Source of the image before any redirects. Not

returned when the image is uploaded. :attr str resolved_url: (optional) Fully resolved URL of the image after redirects are followed. Not returned when the image is uploaded. :attr str image: (optional) Relative path of the image file if uploaded directly. Not returned when the image is passed by URL. :attr ErrorInfo error: (optional) Information about what might have caused a failure, such as an image that is too large. Not returned when there is no error. :attr list[ClassifierResult] classifiers: The classifiers.

class ClassifiedImages(images, custom_classes=None, images_processed=None, warnings=None)[source]

Bases: object

Results for all images.

Attr int custom_classes:
 (optional) Number of custom classes identified in the

images. :attr int images_processed: (optional) Number of images processed for the API call. :attr list[ClassifiedImage] images: Classified images. :attr list[WarningInfo] warnings: (optional) Information about what might cause less than optimal output. For example, a request sent with a corrupt .zip file and a list of image URLs will still complete, but does not return the expected output. Not returned when there is no warning.

class Classifier(classifier_id, name, core_ml_enabled, owner=None, status=None, explanation=None, created=None, classes=None, retrained=None, updated=None)[source]

Bases: object

Information about a classifier.

Attr str classifier_id:
 ID of a classifier identified in the image.
Attr str name:Name of the classifier.
Attr str owner:(optional) Unique ID of the account who owns the classifier. Returned

when verbose=`true`. Might not be returned by some requests. :attr str status: (optional) Training status of classifier. :attr bool core_ml_enabled: Whether the classifier can be downloaded as a Core ML model after the training status is ready. :attr str explanation: (optional) If classifier training has failed, this field may explain why. :attr datetime created: (optional) Date and time in Coordinated Universal Time (UTC) that the classifier was created. :attr list[Class] classes: (optional) Classes that define a classifier. :attr datetime retrained: (optional) Date and time in Coordinated Universal Time (UTC) that the classifier was updated. Returned when verbose=`true`. Might not be returned by some requests. Identical to updated and retained for backward compatibility. :attr datetime updated: (optional) Date and time in Coordinated Universal Time (UTC) that the classifier was most recently updated. The field matches either retrained or created. Returned when verbose=`true`. Might not be returned by some requests.

class ClassifierResult(name, classifier_id, classes)[source]

Bases: object

Classifier and score combination.

Attr str name:Name of the classifier.
Attr str classifier_id:
 ID of a classifier identified in the image.
Attr list[ClassResult] classes:
 Classes within the classifier.
class Classifiers(classifiers)[source]

Bases: object

A container for the list of classifiers.

Attr list[Classifier] classifiers:
 List of classifiers.
class DetectedFaces(images, images_processed=None, warnings=None)[source]

Bases: object

Results for all faces.

Attr int images_processed:
 (optional) Number of images processed for the API call.
Attr list[ImageWithFaces] images:
 The images.
Attr list[WarningInfo] warnings:
 (optional) Information about what might cause less

than optimal output. For example, a request sent with a corrupt .zip file and a list of image URLs will still complete, but does not return the expected output. Not returned when there is no warning.

class ErrorInfo(code, description, error_id)[source]

Bases: object

Information about what might have caused a failure, such as an image that is too large. Not returned when there is no error.

Attr int code:HTTP status code.
Attr str description:
 Human-readable error description. For example, `File size limit

exceeded`. :attr str error_id: Codified error string. For example, limit_exceeded.

class Face(age=None, gender=None, face_location=None)[source]

Bases: object

Information about the face.

Attr FaceAge age:
 (optional) Age information about a face.
Attr FaceGender gender:
 (optional) Information about the gender of the face.
Attr FaceLocation face_location:
 (optional) The location of the bounding box around

the face.

class FaceAge(min=None, max=None, score=None)[source]

Bases: object

Age information about a face.

Attr int min:(optional) Estimated minimum age.
Attr int max:(optional) Estimated maximum age.
Attr float score:
 (optional) Confidence score in the range of 0 to 1. A higher score

indicates greater confidence in the estimated value for the property.

class FaceGender(gender, score=None)[source]

Bases: object

Information about the gender of the face.

Attr str gender:
 Gender identified by the face. For example, MALE or FEMALE.
Attr float score:
 (optional) Confidence score in the range of 0 to 1. A higher score

indicates greater confidence in the estimated value for the property.

class FaceLocation(width, height, left, top)[source]

Bases: object

The location of the bounding box around the face.

Attr float width:
 Width in pixels of face region.
Attr float height:
 Height in pixels of face region.
Attr float left:
 X-position of top-left pixel of face region.
Attr float top:Y-position of top-left pixel of face region.
class ImageWithFaces(faces, image=None, source_url=None, resolved_url=None, error=None)[source]

Bases: object

Information about faces in the image.

Attr list[Face] faces:
 Faces detected in the images.
Attr str image:(optional) Relative path of the image file if uploaded directly. Not

returned when the image is passed by URL. :attr str source_url: (optional) Source of the image before any redirects. Not returned when the image is uploaded. :attr str resolved_url: (optional) Fully resolved URL of the image after redirects are followed. Not returned when the image is uploaded. :attr ErrorInfo error: (optional) Information about what might have caused a failure, such as an image that is too large. Not returned when there is no error.

class WarningInfo(warning_id, description)[source]

Bases: object

Information about something that went wrong.

Attr str warning_id:
 Codified warning string, such as limit_reached.
Attr str description:
 Information about the error.