wizart-vision

Wizart Computer Vision SDK for JavaScript

The Computer Vision service provides developers with access to advanced algorithms for processing images and returning information. Computer Vision algorithms analyze the content of an image in different ways, depending on the visual features you're interested in.

You can use Computer Vision in your application to:

• Indoor semantic segmentation.
• Interior 3d reconstruction.
• Indoor layout and object detection.
• Analytics data such as image quality, interior type, camera parameters.

Looking for more documentation?

• SDK reference documentation
• Wizart Vision review

If you need access to Wizart Vision API, you can get API token by sending a request

Installation

npm install wizart-vision

Authentication

Once you received Vision API token, you need initialize vision client

const wv = require('./dist/main.bundle.js')

const client = new wv.WizartVision("your token")

Usage

The client allows you to perform requests similar to those described in the documentation.

• segmentation
• detection
• reconstruction
• analysis
• interior

You will operate just with few parameters.

• resource - file system path or http link to the image
• feature - some entity available in Wizart Vision SDK

const wv = require('./dist/main.bundle.js')

// use it for segmentation, detection, reconstruction and interior calls
wv.FeatureTypes

// contains next entities
wv.FeatureTypes.WALL
wv.FeatureTypes.CEILING
wv.FeatureTypes.FLOOR
wv.FeatureTypes.WINDOW

// use it for analysis call
wv.AnalysisTypes

// contains next entities
wv.AnalysisTypes.CAMERA
wv.AnalysisTypes.IMAGE_INFO
wv.AnalysisTypes.INTERIOR_TYPE

Segmentation

Semantic segmentation

const data = new FormData();
data.append("room_image", inputFile.files[0]);

client.segmentation(data).then(response => {})

Segmentation by feature

const data = new FormData();
data.append("room_image", inputFile.files[0]);

client.segmentation(data, wv.FeatureTypes.WALL).then(response => {})

To get mask contours

const data = new FormData();
data.append("room_image", inputFile.files[0]);
data.append('vectorized', true)

client.segmentation(data, wv.FeatureTypes.WALL).then(response => {})

Detection

All entities detection

const data = new FormData();
data.append("room_image", inputFile.files[0]);

client.detection(data).then(response => {})

Single entity detection

const data = new FormData();
data.append("room_image", inputFile.files[0]);

client.detection(data, wv.FeatureTypes.CEILING).then(response => {})

Reconstruction

Multiple

const data = new FormData();
data.append("room_image", inputFile.files[0]);

client.reconstruction(data).then(response => {})

Single

const data = new FormData();
data.append("room_image", inputFile.files[0]);

client.reconstruction(data, wv.FeatureTypes.FLOOR).then(response => {})

Analyze

Multiple

const data = new FormData();
data.append("room_image", inputFile.files[0]);

client.analysis(data).then(response => {})

Single

const data = new FormData();
data.append("room_image", inputFile.files[0]);

client.analysis(data, wv.AnalysisTypes.CAMERA).then(response => {})

Interior

All

const data = new FormData();
data.append("room_image", inputFile.files[0]);

client.interior(data).then(response => {})

Single

const data = new FormData();
data.append("room_image", inputFile.files[0]);

client.interior(data, wv.FeatureTypes.WALL).then(response => {})