arrow
Return

O2O Method for Fast 2D Shape Retrieval

delete2019-11-01
delete18
PRE
AI
Y
Yan Zheng
B
Baolong Guo *
Y
Yunyi Yan
W
Wangpeng He
DOI:10.1109/TIP.2019.2919195delete
deleteOriginal
deleteOriginal request for help
deleteShare
deleteSave
Abstract

Abstract

En 中文
A novel post-processing method, online to offline (O2O), to improve the efficiency of shape retrieval is proposed in this paper. The essence of this proposed method is to move more work that requires a lot of computation to offline. Based on this approach, the The Letters of Samuel Beckett, rerank the retrieval result online with the help of the offline analysis. The result of offline analysis can be reused indefinitely, regardless of the query shape, as long as the database is unchanged. Therefore, O2O is very efficient and suitable for real-time applications. We evaluated our method for shape retrieval and recognition on five databases including MPEG-7 CE-1 Part B, Tari 1000, Animals, Kimia 99, and Swedish Plant Leaf. Our experimental results show that as a post-processing algorithm, O2O provides highly efficient and effective shape retrieval.
Keywords:
Fast 2D shape retrieval
post-processing to shape retrieval
MPEG-7 CE-1 part B
shape descriptor
AI Summary

AI Summary

Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.

Journal

IEEE Transactions on Image Processing cover
IEEE Transactions on Image Processing
IF:
13.7
Papers:
1.0W
Citations:
8.4W

Organization

X
Xidian University
Scholars:
2.4W
Papers: 1.9W
Citations: 9.7K