Summary of Dl-ewf: Deep Learning Empowering Women’s Fashion with Grounded-segment-anything Segmentation For Body Shape Classification, by Fatemeh Asghari et al.
DL-EWF: Deep Learning Empowering Women’s Fashion with Grounded-Segment-Anything Segmentation for Body Shape Classification
by Fatemeh Asghari, Mohammad Reza Soheili, Faezeh Gholamrezaie
First submitted to arxiv on: 7 Apr 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper addresses a fundamental issue in the global fashion industry: the mismatch between body shapes and garments purchased by individuals. To develop innovative solutions, it’s crucial to consider inter-individual variability in body shapes. Traditional methods for determining human body shape are limited due to low accuracy, high costs, and time-consuming nature. Instead, this study utilizes digital imaging and deep neural networks (DNN) to identify human body shape. The Style4BodyShape dataset is used to classify body shapes into five categories: Rectangle, Triangle, Inverted Triangle, Hourglass, and Apple. The paper focuses on extracting the body shape segmentation from an image, disregarding surroundings and background, and then classifies the results using various pre-trained models such as ResNet18, ResNet34, ResNet50, VGG16, VGG19, and Inception v3. The Inception V3 model demonstrates superior performance regarding f1-score evaluation metric and accuracy compared to other models. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about how technology can help the fashion industry make clothes that fit people better. Right now, it’s hard for people with different body shapes to find clothes that fit well because of the way clothes are designed. Traditional ways of measuring body shape aren’t very accurate or helpful. This study uses special computer programs and images to identify human body shape and categorize it into five groups. The goal is to create a system that can help fashion designers make better-fitting clothes for people with different shapes. |
Keywords
* Artificial intelligence * F1 score
