Classification of Clothing Using Midlevel Layers
Classification of Clothing Using Midlevel Layers
复制标题
使用中层对服装进行分类
DOI：
10.5402/2013/630579
复制
发表时间：
2013
期刊：
影响因子：
--
通讯作者：
Stan Birchfield
中科院分区：
文献类型：
--
作者：
Bryan Willimon;I. Walker;Stan Birchfield
我们提出了一个多层的方法来分类的衣物在一堆洗衣。分类特征由来自局部和全局视角内的2D和3D数据的颜色、纹理、形状和边缘信息组成。本文的贡献是一种新的分类方法，称为L-M-H，更具体地说，LC-S-H的服装分类。多层方法将问题划分为高（H）层、多个中级（特征（C）、选择掩模（S））层和低（L）层。这种方法产生“局部”解决方案来解决全局分类问题。实验表明，该系统能够有效地将每件衣服分为七个类别（裤子，短裤，衬衫，袜子，连衣裙，衣服或夹克）之一。结果表明，
平均而言，分类率提高了
We present a multilayer approach to classify articles of clothing within a pile of laundry. The classification features are composed of color, texture, shape, and edge information from 2D and 3D data within a local and global perspective. The contribution of this paper is a novel approach of classification termed L-M-H, more specifically LC-S-H for clothing classification. The multilayer approach compartmentalizes the problem into a high (H) layer, multiple midlevel (characteristics (C), selection masks (S)) layers, and a low (L) layer. This approach produces “local” solutions to solve the global classification problem. Experiments demonstrate the ability of the system to efficiently classify each article of clothing into one of seven categories (pants, shorts, shirts, socks, dresses, cloths, or jackets). The results presented in this paper show
that, on average, the classification rates improve by