Practical overview
When it fits
Use it when a MATLAB-based research workflow needs a documented pretrained detector for locating upper-, lower- and full-body clothing in fashion images.
Who it is for
- Researchers studying computer vision for fashion images.
- Educators using clothing detection in non-commercial teaching or research.
Documented uses
- Locate broad garment regions in a fashion image.
- Run a pretrained clothing detector as part of a non-commercial research or educational experiment.
Requirements & limits
The repository states that use is restricted to non-commercial research and educational purposes.
- The detector is built on Fast R-CNN and requires Fast R-CNN, EdgeBox and Piotr's Computer Vision Toolbox.
- The documented demo uses MATLAB and a pretrained Caffe model placed in ./models/.
- The stated use restriction is non-commercial research and education.
Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.
Set up and run the MATLAB detection demo
Prepare the documented dependencies and pretrained model, then run the repository's testing script.
Before you start
- MATLAB
- Fast R-CNN, EdgeBox and Piotr's Computer Vision Toolbox
- The pretrained fashion_detector.caffemodel file
Steps
Install and compile Fast R-CNN, EdgeBox and Piotr's Computer Vision Toolbox.
Download fashion_detector.caffemodel and place it in the repository's ./models/ directory.
Run the testing script with matlab ./demo.m.
Expected outcome
The repository's MATLAB testing demo runs the clothes detector on fashion images.
Guide limitations
- The software's stated use is restricted to non-commercial research and educational purposes.
Sources & review
Source record details
- Source availability
- Active
- Sources checked
- 18 October 2026
- Original website title
- liuziwei7/fashion-detection · Official homepage title · retained in its source language