com.ibm.watson.developer_cloud.alchemy.v1

Class AlchemyVision

java.lang.Object

com.ibm.watson.developer_cloud.service.WatsonService

com.ibm.watson.developer_cloud.service.AlchemyService

com.ibm.watson.developer_cloud.alchemy.v1.AlchemyVision

public class AlchemyVision
extends AlchemyService

The Alchemy Vision service uses deep learning innovations to understand a picture’s content and context. It sees complex visual scenes in their entirety —without needing any textual clues— leveraging a holistic approach to understanding the multiple objects and surroundings.

Version:

v1

See Also:

Alchemy Vision

Field Summary

Fields inherited from class com.ibm.watson.developer_cloud.service.AlchemyService

ENDPOINT, JSONP, OUTPUT_MODE

Fields inherited from class com.ibm.watson.developer_cloud.service.WatsonService

MESSAGE_CODE, MESSAGE_ERROR, VERSION

Constructor Summary

Constructors

Constructor and Description
AlchemyVision()

Method Summary

Modifier and Type	Method and Description
ServiceCall<ImageKeywords>	getImageKeywords(File image, Boolean forceShowAll, Boolean knowledgeGraph) Extracts keywords from an image.
ServiceCall<ImageKeywords>	getImageKeywords(URL url, Boolean forceShowAll, Boolean knowledgeGraph) Extracts keywords from a URL.
ServiceCall<ImageLink>	getImageLink(String html) Extracts the main image link from a HTML page.
ServiceCall<ImageLink>	getImageLink(URL url) Extracts main image link from a URL.
ServiceCall<ImageSceneText>	getImageSceneText(File image) Identifies text in an image.
ServiceCall<ImageSceneText>	getImageSceneText(URL url) Identifies text in an image specified by URL or in the primary image in a web page specified by URL.
ServiceCall<ImageFaces>	recognizeFaces(File image, Boolean knowledgeGraph) Recognizes faces from an image. For each face detected returns: Bounding box Gender Approximate age Name (if celebrity is detected) Here is an example of how to recognize faces in an image:
ServiceCall<ImageFaces>	recognizeFaces(URL url, Boolean knowledgeGraph) Recognizes faces from a URL. For each face detected returns: Bounding box Gender Approximate age Name (if celebrity is detected) Here is an example of how to recognize faces in an image:

Methods inherited from class com.ibm.watson.developer_cloud.service.AlchemyService

getInputFormat, processServiceCall, setAuthentication

Methods inherited from class com.ibm.watson.developer_cloud.service.WatsonService

configureHttpClient, createServiceCall, getApiKey, getEndPoint, getName, getToken, setApiKey, setDefaultHeaders, setEndPoint, setUsernameAndPassword, toString

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait

Constructor Detail

AlchemyVision

public AlchemyVision()

Method Detail

getImageSceneText

public ServiceCall<ImageSceneText> getImageSceneText(File image)

Identifies text in an image.

Parameters:

image - the image file

Returns:

ImageSceneText

getImageSceneText

public ServiceCall<ImageSceneText> getImageSceneText(URL url)

Identifies text in an image specified by URL or in the primary image in a web page specified by URL.

Parameters:

url - the image URL

Returns:

ImageSceneText

getImageKeywords

public ServiceCall<ImageKeywords> getImageKeywords(File image,
                                                   Boolean forceShowAll,
                                                   Boolean knowledgeGraph)

Extracts keywords from an image.

Parameters:

image - the image file

forceShowAll - Includes lower confidence tags

knowledgeGraph - Include knowledge graph information in the the results.

Returns:

ImageKeywords

getImageKeywords

public ServiceCall<ImageKeywords> getImageKeywords(URL url,
                                                   Boolean forceShowAll,
                                                   Boolean knowledgeGraph)

Extracts keywords from a URL.

Parameters:

url - the image URL

forceShowAll - Includes lower confidence tags

knowledgeGraph - Include knowledge graph information in the the results.

Returns:

ImageKeywords

getImageLink

public ServiceCall<ImageLink> getImageLink(URL url)

Extracts main image link from a URL.

Parameters:

url - the image URL

Returns:

ImageLink

getImageLink

public ServiceCall<ImageLink> getImageLink(String html)

Extracts the main image link from a HTML page.

Parameters:

html - the HTML

Returns:

ImageLink

recognizeFaces

public ServiceCall<ImageFaces> recognizeFaces(File image,
                                              Boolean knowledgeGraph)

Recognizes faces from an image.
For each face detected returns:

• Bounding box
• Gender
• Approximate age
• Name (if celebrity is detected)

Here is an example of how to recognize faces in an image:

 AlchemyVision service = new AlchemyVision();
 service.setApiKey("<api_key>");
 
 File image = new File("obama.jpg");
 ImageFaces faces = service.recognizeFaces(image, true).execute();
 
 System.out.println(faces);
 

Parameters:

image - the image

knowledgeGraph - provide extra metadata for detected celebrities

Returns:

ImageFaces

recognizeFaces

public ServiceCall<ImageFaces> recognizeFaces(URL url,
                                              Boolean knowledgeGraph)

Recognizes faces from a URL.
For each face detected returns:

• Bounding box
• Gender
• Approximate age
• Name (if celebrity is detected)

Here is an example of how to recognize faces in an image:

 AlchemyVision service = new AlchemyVision();
 service.setApiKey("<api_key>");
 
 URL image = new URL("http://foo.com/the-image.png");
 ImageFaces faces = service.recognizeFaces(image, true).execute();
 
 System.out.println(faces);
 

Parameters:

url - the image URL

knowledgeGraph - provide extra metadata for detected celebrities

Returns:

ImageFaces