Vision Pack - Shoe



The Vision Pack – Shoes (VPS, shoes recognition) service recognizes shoes in input images and provides the function to segment the shoes area.

You can process shoes images and use them in a variety of ways using the VPS service.


In image composition, mask gives the same effect as drawing in white on an image with an alpha channel. You can use mask to hide or show a desired area in an image.


The VPS service provided by LG AI Platform has the following features:

SSP 엔진의 특징
Features Description
Segmentation of the shoes area

This removes the background from the image where the shoes are included and segments the shoes area to provide a mask image.

Correction of the shoes area

A user can correct the shoes area precisely through input such as touch or mouse click.
(e.g: You can delete the part that is not the shoes area or include the part that is the shoes area by clicking the mouse.)

Excellent recognition performance

Shoes area recognition and division performance are excellent because of use of the latest deep learning technology.


The VPS service receives image data as input value, extracts the shoes area, and delivers the resulting image to the app.


Examples of Use

The VPS service can be used in a variety of ways as shown below:


Decorating my own shoes

A user can segment the shoes area and combine it with various backgrounds to create his or her own shoes image. 



Moreover, you can retouch the image or adjust the filter to improve lighting or a shoes image.



Virtual fitting

A user can combine his or her full body image with the shoes image without trying them to see himself or herself wearing them virtually.