Official Content

Classifies an image in a set of categories.

Parameters

Configuration

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

  PropertyKey
ProviderType Id Key SecretKey
Alibaba - 用户AccessKey 用户AccessKey
Amazon - Rekognition Rekognition
Baidu 视觉技术 视觉技术 视觉技术
Google - Cloud Vision API -
IBM - Visual Recognition -
Microsoft - Computer Vision -
MLKit ML Kit API ML Kit API -
SAP - Sandbox Environment
(Deprecated)
-
Tencent 多标签识别 多标签识别 -

Additionally, for custom models, you must set the properties described in the following table. For more information, refer to HowTo: Build a custom model for GeneXus Cognitive API.

  PropertyKey
ProviderType ModelId ModelVersion ModelCredential
Alibaba - - -
Amazon - - -
Baidu - - -
Google AutoML (Project Id) - AutoML (Service Account Json)
IBM Visual Recognition (Model Id) - Visual Recognition (API Key)
Microsoft Custom Vision (Project Id) Custom Vision (Published Name) Custom Vision (Prediction Key)
MLKit - - -
SAP Customizable Image
Classification (Model Version)
(Deprecated)
Customizable Image
Classification (Model Version)
(Deprecated)
 
Tencent - - -

Sample

Taking the following image input, the table below shows the classification made for each provider and the time it takes for processing it.

GeneXusAI - Image module - Sample

 

Provider Output Benchmark
Alibaba
[{
    "label": "清真寺",
    "confidence": 0.99
}]

12435ms
Amazon
[{
	"label": "Vacation",
	"confidence": 0.998
}, {
	"label": "Sunglasses",
	"confidence": 0.996
}, {
	"label": "Person",
	"confidence": 0.995
}, {
	"label": "Tourist",
	"confidence": 0.982
}, {
	"label": "Building",
	"confidence": 0.906
}, {
	"label": "Architecture",
	"confidence": 0.906
}, {
	"label": "Clothing",
	"confidence": 0.709
}, {
	"label": "Dome",
	"confidence": 0.693
}, {
	"label": "Monument",
	"confidence": 0.656
}, {
	"label": "People",
	"confidence": 0.644
}]

4135ms
Baidu
[{
    "label": "建筑",
    "confidence": 0.952,
    "Info": [{
        "property": "ROOT",
        "value": "建筑-现代建筑"
    }]
}, {
    "label": "李维斯",
    "confidence": 0.799,
    "Info": [{
        "property": "ROOT",
        "value": "Logo"
    }]
}, {
    "label": "历史遗迹",
    "confidence": 0.515,
    "Info": [{
        "property": "ROOT",
        "value": "建筑-文明遗迹"
    }]
}, {
    "label": "情侣",
    "confidence": 0.235,
    "Info": [{
        "property": "ROOT",
        "value": "人物-人物特写"
    }]
}, {
    "label": "卡通动漫人物",
    "confidence": 0.023,
    "Info": [{
        "property": "ROOT",
        "value": "非自然图像-彩色动漫"
    }]
}]

8476ms
Google
[{
    "label": "landmark",
    "confidence": 0.914
}, {
    "label": "tourism",
    "confidence": 0.889
}, {
    "label": "tourist attraction",
    "confidence": 0.827
}, {
    "label": "historic site",
    "confidence": 0.824
}, {
    "label": "vacation",
    "confidence": 0.792
}, {
    "label": "travel",
    "confidence": 0.765
}, {
    "label": "temple",
    "confidence": 0.733
}, {
    "label": "sky",
    "confidence": 0.688
}, {
    "label": "fun",
    "confidence": 0.632
}, {
    "label": "place of worship",
    "confidence": 0.560
}]

8263ms
IBM
[{
    "label": "Taj Mahal",
    "confidence": 0.777
}, {
    "label": "Seven Wonders of the Ancient World",
    "confidence": 0.753
}, {
    "label": "religious building",
    "confidence": 0.635
}, {
    "label": "building",
    "confidence": 0.635
}, {
    "label": "memorial",
    "confidence": 0.601
}, {
    "label": "alabaster color",
    "confidence": 0.927
}]

6160ms
Microsoft
[{
    "label": "outdoor",
    "confidence": 0.003
}, {
    "label": "people",
    "confidence": 0.644
}]

3489ms
MLKit
[{
    "label": "Monument",
    "confidence": 0.861
}, {
    "label": "Vacation",
    "confidence": 0.787
}, {
    "label": "Sunglasses",
    "confidence": 0.782
}, {
    "label": "Building",
    "confidence": 0.715
}, {
    "label": "Event",
    "confidence": 0.627
}, {
    "label": "Leisure",
    "confidence": 0.612
}, {
    "label": "Plant",
    "confidence": 0.5
}]

1294ms
SAP
[{
    "label": "mosque",
    "confidence": 0.821
}, {
    "label": "palace",
    "confidence": 0.008
}, {
    "label": "bell cote, bell cot",
    "confidence": 0.003
}, {
    "label": "dome",
    "confidence": 0.003
}, {
    "label": "gondola",
    "confidence": 0.002
}]
4682ms
Tencent
[{
	"label": "广场",
	"confidence": 0.410
}, {
	"label": "天空",
	"confidence": 0.400
}, {
	"label": "欧式建筑",
	"confidence": 0.240
}, {
	"label": "男孩",
	"confidence": 0.190
}, {
	"label": "树木",
	"confidence": 0.140
}, {
	"label": "合影",
	"confidence": 0.120
}]

18196ms

Notes

  • The classification is made with the default classifier of each provider. For such reason, the categories (or labels) returned are not predefined and they depend on the provider used.
  • The maximum image file size is 10MB.
  • SAP Leonardo allows images of 1.0 MP at most.
  • Tencent AI and Baidu AI return labels as Chinese strings.
  • IBM provider: Deprecated as of December 22 (2021). Check IBM Visual Recognition's Release Notes.

Scope

Generators: .NET, .NET Framework, Java, Apple, Android
Connectivity: Online

Availability

This procedure is available as of GeneXus 16.

See also



Last update: February 2024 | © GeneXus. All rights reserved. GeneXus Powered by Globant