Sorting of garments is a time consuming and monotonous task. Manual sorting method have limitations in terms of low throughput rate, human error and less productivity. To overcome this, Convolutional Neural Network can be used to automate sorting with better efficiency. Thus, the study aims to develop a sorting mechanism for a garment warehouse. In this study, the performance of three popular CNN architectures: InceptionV3, MobileNet, and ResNet50 are compared for efficient sorter. The required data for the study is sourced from various online clothing websites like “Myntra”, “Flipkart”, “Ajio”, etc. Various experiments were performed to evaluate the performance of the three models. As per the results, ResNet50 model has better accuracy as compared to Inception V3 and MobileNet. Hence, it should be used to develop the automatic sorter that will reduce the manual work and will result in better efficiency.

错误:搜索内容不能为空,请输入英文关键词
错误:关键词超出字数限制,请精简
高级检索

Automatic Sorting of Apparels for Efficient Inventory Management: A Deep Learning Approach

  • Anchal,
  • Tripti Mahara,
  • V. L. Helen Josephine,
  • Vandana Srivastava

摘要

Sorting of garments is a time consuming and monotonous task. Manual sorting method have limitations in terms of low throughput rate, human error and less productivity. To overcome this, Convolutional Neural Network can be used to automate sorting with better efficiency. Thus, the study aims to develop a sorting mechanism for a garment warehouse. In this study, the performance of three popular CNN architectures: InceptionV3, MobileNet, and ResNet50 are compared for efficient sorter. The required data for the study is sourced from various online clothing websites like “Myntra”, “Flipkart”, “Ajio”, etc. Various experiments were performed to evaluate the performance of the three models. As per the results, ResNet50 model has better accuracy as compared to Inception V3 and MobileNet. Hence, it should be used to develop the automatic sorter that will reduce the manual work and will result in better efficiency.