Loading...

Content-based Image Retrieval of Clothing Items with Neural Networks

Ghayour Razmgah, Mahdi | 2022

93 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 56275 (19)
  4. University: Sharif University of Technology
  5. Department: Computer Engineering
  6. Advisor(s): Kasaei, Shohreh
  7. Abstract:
  8. One of the trends and important topics in computer vision is content based image retrieval. in this subject, we ask image as query from system, then system will search in pre-processed dataset and finds nearest images to the query and return them as result. in this thesis, our goal is to solve this problem in better way for fashion dataset. current solutions will generate bad results in case of rotation in input query or dataset. last recent years, transformers are generated really good results in NLP, then the ViT reproduced same idea in computer vision and gained comparable results due to CNNs. so, we are going to use vision transformers to solve content-based image retrieval problem with fashion images, who will be robust to rotation. we use to DeepFashion2 dataset to measure accuracy of this method. in this dataset we have images from same clothing item that published from users after buying a clothing item from shops, plus same item images from shops webpage. we used one of user images as query and system should return shop images in result. due to measure our solution for customer to shop problem, we used precision and recall metrics for information retrieval. after applying our idea average of recall@20 increased from 13.2% to 24.6% and standard deviation of recall@20 for different rotations decreased from 2.47 to 0.24, so its show that our method is more accurate and robust from traditional solutions.
  9. Keywords:
  10. Fashion Industries ; Neural Network ; Image Retrieval ; Rotation Robust ; Vision Transformer ; Content-Based Image Retrieval

 Digital Object List

 Bookmark

...see more