Abstract
Deep learning has been well-known for a couple of years, and it indicates incredible possibilities for unsupervised learning of representations with the clustering algorithm. The forms of Convolution Neural Networks (CNN) are now state-of-the-art for many recognition and clustering tasks. However, with the perpetual incrementation of digital images, there exist more and more redundant, irrelevant, and noisy samples which cause CNN running to gradually decrease, and its clustering accuracy decreases concurrently. To conquer these issues, we proposed an effective clustering method for a large-scale image dataset which combines CNN and a Fuzzy-Rough C-Mean (FRCM) clustering algorithm. The main idea is that first a high-level representation, learned by multi-layers of CNN with one clustering layer, produce the initial cluster center, then during training image clusters, and representations, are updating jointly. FRCM is utilized to update the cluster centers in the forward pass, while the parameters of proposed CNN are updated by the backward pass based on Stochastic Gradient Descent (SGD). The concept of the rough set of lower and boundary approximations deal with uncertainty, vagueness, and incompleteness in cluster definition, and fuzzy sets enable efficient handling of overlapping partitions in the noisy environment. The experiment results show that the proposed FRCM based unsupervised CNN clustering method is better than the standard K-Mean, Fuzzy C-Mean, FRCM and also other deep-learning-based clustering algorithms on large-scale image data.
Highlights
Image clustering [1–13] is a consequential research field in image processing and computer vision applications
To overcome the above issues, the contribution of our work is that we can thedata training time and maintain and even improve the test accuracy by selectingdecrease noise-free for time and maintain and even improve the test accuracy by selecting noise‐free datathe for updating clusters by using the Fuzzy-Rough C-Mean (FRCM) algorithm
We provided image clustering using extracted from convolutional clustering layers in a Convolution Neural Network (CNN)
Summary
Image clustering [1–13] is a consequential research field in image processing and computer vision applications. CNN based architectures play an important role in the processing of image data due to their unique structure in the phase of feature representation, given a sufficiently large labeled training set. There have been few attempts to increase the performance of image clustering by deep-networks-based feature representation learning. Deep-networks-based feature representational learning does depend on much labeled training data, which is not accessible in unsupervised clustering. To overcome this problem, the model can be pre-trained in view of existing large-scale training image sets; the pre-trained model cannot fit the normal input data divider. The main contributions of the proposed algorithm are as follows: We present an FRCM-based unsupervised CNN clustering, which is robust to the uncertainties in.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
