Image retrieval research based on feature points and affine invariant moments

2015 ◽  
pp. 293-298
Keyword(s):  
Image Retrieval ◽  
Feature Points ◽  
Affine Invariant ◽  
Invariant Moments

scholarly journals A Grid Feature-Point Selection Method for Large-Scale Street View Image Retrieval Based on Deep Local Features

2020 ◽  
Vol 12 (23) ◽  
pp. 3978
Author(s):  
Tianyou Chu ◽  
Yumin Chen ◽  
Liheng Huang ◽  
Zhiqiang Xu ◽  
Huangyuan Tan
Keyword(s):  
Image Retrieval ◽  
Large Scale ◽  
Local Features ◽  
Selection Method ◽  
Image Features ◽  
Feature Point ◽  
Feature Points ◽  
Point Selection ◽  
Retrieval Task ◽  
Street View

Street view image retrieval aims to estimate the image locations by querying the nearest neighbor images with the same scene from a large-scale reference dataset. Query images usually have no location information and are represented by features to search for similar results. The deep local features (DELF) method shows great performance in the landmark retrieval task, but the method extracts many features so that the feature file is too large to load into memory when training the features index. The memory size is limited, and removing the part of features simply causes a great retrieval precision loss. Therefore, this paper proposes a grid feature-point selection method (GFS) to reduce the number of feature points in each image and minimize the precision loss. Convolutional Neural Networks (CNNs) are constructed to extract dense features, and an attention module is embedded into the network to score features. GFS divides the image into a grid and selects features with local region high scores. Product quantization and an inverted index are used to index the image features to improve retrieval efficiency. The retrieval performance of the method is tested on a large-scale Hong Kong street view dataset, and the results show that the GFS reduces feature points by 32.27–77.09% compared with the raw feature. In addition, GFS has a 5.27–23.59% higher precision than other methods.

Affine-invariant image retrieval by correspondence matching of shapes

1999 ◽  
Vol 17 (7) ◽  
pp. 489-499 ◽  
Author(s):  
Dinggang Shen ◽  
Wai-him Wong ◽  
Horace H.S. Ip
Keyword(s):  
Image Retrieval ◽  
Affine Invariant ◽  
Correspondence Matching

A New Image Affine-Invariant Region Detector and Descriptor

2011 ◽  
Vol 130-134 ◽  
pp. 2911-2914
Author(s):  
Xiu Xin Chen ◽  
Ke Bin Jia ◽  
Chong Chong Yu ◽  
Shiang Wei
Keyword(s):  
Connected Region ◽  
Affine Invariant ◽  
Invariant Region ◽  
Region Detection ◽  
Invariant Moments ◽  
Invariant Regions

To solve the problems that exist in present affine-invariant region detection and description methods, a new affine-invariant region detector and descriptor are proposed in this paper. First, affine-invariant regions in an image are detected using a connected-region based method. And then a vector composed of a group of affine invariant moments is adopted to descript the regions. Experiments show the effectiveness and robustness of the method. It is also very fast.

Adding Affine Invariant Geometric Constraint for Partial-Duplicate Image Retrieval

2010 ◽  
Author(s):  
Zhipeng Wu ◽  
Qianqian Xu ◽  
Shuqiang Jiang ◽  
Qingming Huang ◽  
Peng Cui ◽  
...  
Keyword(s):  
Image Retrieval ◽  
Geometric Constraint ◽  
Affine Invariant
Sign in / Sign up

Export Citation Format

Share Document