ARTÍCULO
TITULO

Image clustering using pretrained neural networks

A.S. Kuznetsov    
E.Y. Semenov    
L.D. Matrosova    

Resumen

The article deals with the stages of solving image clustering problems using pre-trained neural networks. Some composite solutions of the clustering problem are presented, where clustering methods are used at the last stage, and most of the work is the extraction of features and their preprocessing. The analysis of modern approaches to feature extraction from images, including classical methods of pattern recognition theory and computer vision and feature extraction methods using convolutional neural networks. The paper provides recommendations for choosing the most effective architecture for convolutional neural networks, depending on the nature of the tasks. A classification of methods for reducing the dimension of images by types: preserving the distance between points when displaying from high-dimensional to low-dimensional space; preserving the global structure of data; search for the nearest vectors in large-dimensional spaces. We consider a special method of clustering images DeepCluster, which iteratively groups the features using a standard clustering algorithm. The obtained results can serve in further research in this area, as well as in solving problems in the preparation of pre-trained models of convolutional neural networks.

 Artículos similares

       
 
Yifeng Ren, Qingyan Li and Zhe Liu    
Plant diseases and pests may seriously affect the yield of crops and even threaten the survival of human beings. The characteristics of plant diseases and insect pests are mainly reflected in the occurrence of lesions on crop leaves. Machine vision disea... ver más
Revista: Applied Sciences

 
Yiming Tang, Rui Chen and Bowen Xia    
Nowadays, most fuzzy clustering algorithms are sensitive to the initialization results of clustering algorithms and have a weak ability to handle high-dimensional data. To solve these problems, we developed the viewpoint-driven subspace fuzzy c-means (VS... ver más
Revista: Applied Sciences

 
Pradeep S. Naulia, Arunava Roy, Junzo Watada and Izzatdin B. A. Aziz    
The purpose of the current study is to propose a novel meta-heuristic image analysis approach using multi-objective optimization, named ?Pixel-wise k-Immediate Neighbors? to identify pores and fractures (both natural and induced, even in the micro-level)... ver más
Revista: Algorithms

 
Christopher M. Holmes, Joshua Pritsolas, Randall Pearson, Carolyn Butts-Wilmsmeyer and Thorsten Schad    
In cultivated landscapes, grasslands are an important land use type for insect life. Grassland management practices can have a significant impact on insect ecology. For example, intense fertilization and frequent cutting can reduce the diversity and abun... ver más
Revista: Applied Sciences

 
Huichan Kim, Sunho Park and Seong-Yeob Jeong    
Growing interest in finding the optimal route through the arctic ocean, and sea ice concentration is also emerging as a factor to be considered. In this paper, an algorithm to calculate the sea ice concentration was developed based on the images taken du... ver más