Fusing Hierarchical Convolutional Features for Human Body Segmentation and Clothing Fashion Classification

TL;DR

This paper introduces a deep neural network that combines multi-scale convolutional features for accurate human body segmentation, enabling effective clothing fashion classification over multiple years.

Contribution

A novel fully convolutional network that fuses hierarchical features for improved body segmentation and fashion classification, focusing on segmented clothing parts.

Findings

High accuracy in body segmentation and fashion classification

Effective handling of background influence in clothing images

Successful classification across 8 years of fashion data

Abstract

The clothing fashion reflects the common aesthetics that people share with each other in dressing. To recognize the fashion time of a clothing is meaningful for both an individual and the industry. In this paper, under the assumption that the clothing fashion changes year by year, the fashion-time recognition problem is mapped into a clothing-fashion classification problem. Specifically, a novel deep neural network is proposed which achieves accurate human body segmentation by fusing multi-scale convolutional features in a fully convolutional network, and then feature learning and fashion classification are performed on the segmented parts avoiding the influence of image background. In the experiments, 9,339 fashion images from 8 continuous years are collected for performance evaluation. The results demonstrate the effectiveness of the proposed body segmentation and fashion classification methods.