GeneXus Cognitive API - DetectScene procedure

Determines the scenario that the image is about (a city, a beach, a desert, etc.).

Parameters

• in:&image :: Image data type
  An image to identify its scenario.

• in:&provider :: Provider, GeneXusAI.Configuration
  Provider settings.

• inout:&Messages :: Messages, GeneXus.Common
  A collection of warning and error messages returned by the task. You should check in your code if an error was returned. Refer to error codes and descriptions for more information.

• out:&OutputLabels:: OutputLabel, GeneXusAI (collection)
  A set of labels with their confidence describing the image's scenario.

Configuration

The following table resumes the configuration properties (access credentials) you must set in order to use this AI task.

Sample

Taking the following image input, the table below shows the scenarios are identified for each provider (as a JSON structure) and the time it takes for processing it.

[{
	"label": "建筑",
	"confidence": 0.930
}, {
	"label": "广场",
	"confidence": 0.190
}, {
	"label": "人物",
	"confidence": 0.140
}, {
	"label": "户外",
	"confidence": 0.110
}, {
	"label": "室外",
	"confidence": 0.110
}]

[{
    "label": "Vacation",
    "confidence": 0.997
}, {
    "label": "Tourist",
    "confidence": 0.976
}, {
    "label": "Architecture",
    "confidence": 0.924
}, {
    "label": "Building",
    "confidence": 0.924
}, {
    "label": "Dome",
    "confidence": 0.787
}, {
    "label": "Clothing",
    "confidence": 0.715
}, {
    "label": "Monument",
    "confidence": 0.675
}, {
    "label": "People",
    "confidence": 0.610
}]

[{
	"label": "泰姬陵",
	"confidence": 1.000
}]

[{
    "label": "Taj Mahal",
    "confidence": 0.72149533
}]

[{
    "label": "outdoor, Taj Mahal",
    "confidence": 0.985146582126618
}, {
    "label": "people",
    "confidence": 0.64453125
}]

[]

[{
    "label": "GXAI_TCN_SCENE_193",
    "confidence": 0.974
}, {
    "label": "GXAI_TCN_SCENE_210",
    "confidence": 0.004
}, {
    "label": "GXAI_TCN_SCENE_92",
    "confidence": 0.004
}, {
    "label": "GXAI_TCN_SCENE_223",
    "confidence": 0.003
}, {
    "label": "GXAI_TCN_SCENE_65",
    "confidence": 0.002
}]

Notes

• The label assigned for an object depends on the provider used.
• Maximum image file size is 10MB.
• Tencent AI returns labels as 'GXAI_TCN_SCENE_{id}' tags, where the {id} is a numeric class provided by Tencent. You can use a Language object for mapping each tag with string label as other provider does. You can download this xpz which contains the SimplifiedChinese language object with the official mapping, and also contains the English language mapping using machine translation (it can be inaccurate). Once you import this xpz, for example, the 'GXAI_TCN_SCENE_193' label on the sample section will be translated to '清真寺外面' (or 'outside the mosque' in English) if you have set Translation type property in your environment with 'Run-time' value.
• ML Kit requires Google Vision enabled and works on the cloud (the inference is not made on the device).

Scope

Availability

This procedure is available as of GeneXus 16.

• As of GeneXus 16 upgrade 1:
  - Google Cloud AI is available.
• As of GeneXus 16 upgrade 2:
  - Amazon WS and Tencent AI are available.
• As of GeneXus 16 upgrade 3:
  - Baidu AI is available.
• As of GeneXus 16 upgrade 4:
  - Alibaba AI is available.
• As of GeneXus 16 Upgrade 11:
  - Firebase ML Kit is available for Android.