Vision AI API Documentation
asticaVision API is a general purpose computer vision model with state-of-the-art capabilities. Available through an API, it enables developers to provide users with a powerful and comprehensive suite of image analysis and understanding capabilities.
Vision AI Demo
Effortlessly process images and extract valuable insights using the asticaVision API to automate image moderation, automatic categorization, face recognition, and object detection.
https://vision.astica.ai/describe
curl --location --request POST 'https://vision.astica.ai/describe' \
--header 'Content-Type: application/json' \
--insecure \
--data '{
"tkn": "your_api_key",
"modelVersion": "2.5_full",
"input": "https://www.astica.org/inputs/analyze_3.jpg",
"visionParams": "gpt, describe, describe_all, tags, objects",
"objects_custom_kw": "",
"gpt_prompt": "",
"gpt_length": "90"
}'
Each call to the asticaVision API should include the computer vision parameters that you wish to detect. If you do not supply any parameters, then it will default to all and you will be billed for each transaction for every call.
List of Astica Vision Inputs- 2.5_full
-
2.1_full
older models - 1.0_full
- 2.0_full
- Max Filesize: 20MB
- Max Resolution: 16000x16000
- Compatible File Types
- .PNG
- .JPG version 2.5+ or higher:
- .BMP
- .JIFF
- Min characters: 8
- Max characters: 150 version 2.1 or lower
- Max characters: 325 version 2.5 or higher
- Required Parameter: gpt or gpt_detailed
- Min characters: 8
- Max characters: 125 version 2.1 or lower
- Max characters: 250 version 2.5 or higher
- Max characters: 245
- Required model version: v2.5 or higher
Each request to the API can contain one or more vision parameter which determines which capabilities will be engaged. Utilize multiple different Vision AI functions in a single API call.
Utilize multiple different Vision AI functions in a single API call. If left blank then all available parameters will be used. For cost-effective usage it is recommended to use only the vision parameters that are relevant to your usecase.
"visionParams": "gpt_detailed, describe, describe_all, faces, moderate",List of Computer Vision Parameters
Astica Vision AI provides responses that are generated as a result of a successful request. These responses appear based on the specific inputs and parameters that were provided during the initial request.
If the Vision response returns an error more information can be found in the Vision API Errors section
List of Vision ResponsesThe following output was produced by submitting this image.
{
"astica": {
"request": "vision",
"requestType": "analyze",
"modelVersion": "2.5",
"api_qty": 30.778
},
"caption": {
"text": "a dog standing on its hind legs and a person standing on the sidewalk",
"confidence": 1
},
"caption_GPTS": "In the image, we see a dog standing on its hind legs on a sidewalk, reaching out to a person standing nearby. The person is wearing black sneakers and jeans. The dog appears to be a German Shepherd, and it is interacting playfully with the person. The scene takes place in a park, with green grass and trees in the background. The person is extending their hand towards the dog, possibly offering a treat or engaging in a game of fetch with a frisbee. The interaction between the dog and the person is heartwarming and playful, showcasing a bond between human and animal.",
"caption_list": [
{
"text": "a dog being held by a person in a park",
"conf": 0.333,
"bbox": {
"w": 190,
"h": 461,
"x": 166,
"y": 0
},
"guid_object": "0_9aca5"
},
{
"text": "the dog's face is a man's hand and a dog's leg",
"conf": 0.133,
"bbox": {
"w": 190,
"h": 461,
"x": 166,
"y": 0
},
"guid_object": "0_9aca5"
},
{
"text": "the image is a german shepherd dog and a man",
"conf": 0.133,
"bbox": {
"w": 256,
"h": 413,
"x": 304,
"y": 45
},
"guid_object": "1_fe687"
},
{
"text": "a dog standing on its hind legs to reach a person's hand",
"conf": 0.133,
"bbox": {
"w": 256,
"h": 413,
"x": 304,
"y": 45
},
"guid_object": "1_fe687"
},
{
"text": "a dog and a person playing with a frisbee",
"conf": 0.133,
"bbox": {
"w": 256,
"h": 413,
"x": 304,
"y": 45
},
"guid_object": "1_fe687"
},
{
"text": "the shoe of a person standing on a skateboard",
"conf": 0.133,
"bbox": {
"w": 124,
"h": 67,
"x": 223,
"y": 394
},
"guid_object": "2_dbc99"
},
{
"text": "a person's feet and shoes on a sidewalk",
"conf": 0.133,
"bbox": {
"w": 124,
"h": 67,
"x": 223,
"y": 394
},
"guid_object": "2_dbc99"
},
{
"text": "a person wearing black shoes and jeans standing on a sidewalk",
"conf": 0.133,
"bbox": {
"w": 124,
"h": 67,
"x": 223,
"y": 394
},
"guid_object": "2_dbc99"
},
{
"text": "the dog's paw is a woman's hand",
"conf": 0.133,
"bbox": null,
"guid_object": ""
},
{
"text": "a dog standing on its hind legs to get a treat from a person",
"conf": 0.133,
"bbox": null,
"guid_object": ""
},
{
"text": "a dog and a person standing on a sidewalk",
"conf": 0.133,
"bbox": null,
"guid_object": ""
},
{
"text": "the dog's face is the same as the human",
"conf": 0.133,
"bbox": null,
"guid_object": ""
}
],
"objects": [
{
"name": "Person",
"conf": 0.83,
"guid_object": "0_9aca5",
"confidence": 0.83,
"rectangle": {
"x": 166,
"y": 0,
"w": 190,
"h": 461
}
},
{
"name": "Cat",
"conf": 0.63,
"guid_object": "1_fe687",
"confidence": 0.63,
"rectangle": {
"x": 304,
"y": 45,
"w": 256,
"h": 413
}
},
{
"name": "Sneakers",
"conf": 0.54,
"guid_object": "2_dbc99",
"confidence": 0.54,
"rectangle": {
"x": 223,
"y": 394,
"w": 124,
"h": 67
}
}
],
"objects_custom": [],
"tags": [
{
"name": "grass",
"confidence": 0.87
},
{
"name": "plant",
"confidence": 0.8
},
{
"name": "reed",
"confidence": 0.7
},
{
"name": "sky",
"confidence": 0.71
},
{
"name": "tree",
"confidence": 0.84
},
{
"name": "weed",
"confidence": 0.67
},
{
"name": "animal",
"confidence": 0.72
},
{
"name": "floor",
"confidence": 0.73
},
{
"name": "ledge",
"confidence": 0.68
},
{
"name": "log",
"confidence": 0.65
},
{
"name": "stand",
"confidence": 0.88
},
{
"name": "blanket",
"confidence": 0.76
},
{
"name": "fur",
"confidence": 0.73
},
{
"name": "pillow",
"confidence": 0.65
},
{
"name": "curtain",
"confidence": 0.72
},
{
"name": "dress shirt",
"confidence": 0.7
},
{
"name": "selfie",
"confidence": 0.6
},
{
"name": "tie",
"confidence": 0.84
},
{
"name": "woodpecker",
"confidence": 0.51
},
{
"name": "brown",
"confidence": 0.84
},
{
"name": "brown bear",
"confidence": 0.66
},
{
"name": "enclosure",
"confidence": 0.7
},
{
"name": "stone",
"confidence": 0.79
},
{
"name": "stare",
"confidence": 0.66
},
{
"name": "walk",
"confidence": 0.82
},
{
"name": "german shepherd",
"confidence": 0.67
},
{
"name": "black",
"confidence": 0.86
},
{
"name": "catch",
"confidence": 0.83
},
{
"name": "sheepdog",
"confidence": 0.72
},
{
"name": "dog",
"confidence": 1
},
{
"name": "man",
"confidence": 0.86
},
{
"name": "park",
"confidence": 0.89
},
{
"name": "paw",
"confidence": 0.76
},
{
"name": "play",
"confidence": 0.81
},
{
"name": "shepherd",
"confidence": 0.79
},
{
"name": "woman",
"confidence": 0.87
}
],
"colors": {
"dominantColors": [
"#dccbcb",
"#2e2729",
"#92766a"
],
"accentColor": "#1c181b",
"list": [
"#b89789",
"#93756a",
"#1c181b",
"#ece0e3",
"#403737",
"#ccb6b4",
"#6d584b"
]
},
"colors_object": [
{
"guid_object": "0_9aca5",
"primary": [
"#9d8a78",
"#282529",
"#ddd6d9"
],
"accent": "#161418",
"list": [
"#3a363a",
"#bea48d",
"#7c7163",
"#ddd6d9",
"#161418"
]
},
[
{
"guid_object": "1_fe687",
"primary": [
"#b1957f",
"#443932",
"#e9dcd9"
],
"accent": "#282120",
"list": [
"#e9dcd9",
"#282120",
"#957e6b",
"#605144",
"#cdac93"
]
}
],
[
{
"guid_object": "2_dbc99",
"primary": [
"#433e37",
"#af987d",
"#f2dfd7"
],
"accent": "#2a2727",
"list": [
"#c5ab92",
"#5c5547",
"#9a8569",
"#f2dfd7",
"#2a2727"
]
}
]
],
"categories": [],
"faces": [],
"brands": [],
"landmarks": [],
"celebrities": [],
"readResult": {
"stringIndexType": "TextElements",
"content": "",
"pages": [
{
"height": 486,
"width": 729,
"angle": 0,
"pageNumber": 1,
"words": [],
"spans": [
{
"offset": 0,
"length": 0
}
],
"lines": []
}
],
"styles": []
},
"moderate": {
"isAdultContent": false,
"isRacyContent": false,
"isGoryContent": false,
"adultScore": 0.01,
"racyScore": 0.01,
"goreScore": 0
},
"metadata": {
"width": 729,
"height": 486,
"format": "jpg"
},
"GPT_level": 0,
"status": "success"
}
The API will provide a handled error if it encounters an issue during a request to the API.
{
"status": "error",
"error": "Unable to handle asticaVision v2.1_full request."
}
1. Face Detection (Age and Gender):
asticaVision API employs advanced facial detection algorithms to accurately identify and analyze faces within images. In addition to detecting the presence of faces, it can also estimate the age and gender of the individuals, providing useful demographic information for targeted marketing or personalized user experiences.
2. Object Detection:
The API is also capable of identifying and detecting a wide range of objects within images, enabling users to ascertain the presence of specific items or elements. This powerful feature can be used for applications such as inventory management, surveillance, and visual search.
3. Image Tagging and Categorization:
asticaVision API uses machine learning techniques to automatically generate descriptive tags and assign appropriate categories to images based on their visual content. This feature simplifies the process of organizing and indexing large image databases, streamlining the search and retrieval of relevant images based on specific keywords or themes.
4. Content Moderation:
The API includes intelligent content moderation capabilities designed to automatically detect and filter out images containing adult content or mature subject matter. This feature significantly reduces the manual effort required to moderate visual content, ensuring that inappropriate material is not displayed on websites, social platforms, or digital applications.
5. Automatic Image Description and Captioning:
Leveraging its advanced computer vision capabilities, asticaVision API can automatically generate descriptive text and captions for images, providing an accurate and concise summary of the visual content. This feature not only helps in enhancing the accessibility of images for visually impaired users but also aids in improving the overall user experience by offering meaningful and contextual information about the images.
Discover More AI
Experiment with different kinds of artificial intelligence. See, hear, and speak with astica.