Fuzzy adaptive learning control network (FALCN) for image clustering and content-based image retrieval on noisy dataset

It has been demonstrated that fuzzy systems are beneficial for classification and regression. However, they have been mainly utilized in controlled settings. An image clustering technique essential for content-based picture retrieval in big image datasets is developed using the contents of color, texture and shape. Currently, it is challenging to label a huge number of photos. The issue of unlabeled data has been addressed. Unsupervised learning is used. K-means is the most often used unsupervised learning algorithm. In comparison to fuzzy c-means clustering, K-means clustering has lower -dimensional space resilience and initialization resistance. The dominating triple HSV space was shown to be a perceptual color space made of three modules, S (saturation), H (hue) and V (value), referring to color qualities that are significantly connected to how human eyes perceive colors. A deep learning technique for segmentation (RBNN) is built on the Gaussian function, fuzzy adaptive learning control network (FALCN), clustering and the radial basis neural network. The segmented image and critical information are fed into a radial basis neural network classifier. The suggested fuzzy adaptive learning control network (FALCN) fuzzy system, also known as the unsupervised fuzzy neural network, is very good at clustering images and can extract image properties. When a conventional fuzzy network system receives a noisy input, the number of output neurons grows needlessly. Finally, random convolutional weights extract features from data without labels. Furthermore, the state-of-the-art uniting the proposed FALCN with the RBNN classifier, the proposed descriptor also achieves comparable performance, such as improved accuracy is 96.547 and reduced mean squared error of 36.028 values for the JAFE, ORL, and UMIT datasets.

Automated summary

It has been shown that fuzzy systems are useful for classification and regression, but they are mostly used in controlled environments. An image clustering technique using color, texture, and shape information is developed for content-based picture retrieval in large image datasets. The challenge of labeling a large number of photos is addressed by using unsupervised learning, specifically the K-means clustering algorithm. In comparison to fuzzy c-means clustering, K-means clustering has better performance in lower-dimensional space resilience and initialization resistance. The dominant triple HSV color space is a perceptual color space composed of saturation (S), hue (H), and value (V), which are closely related to human color perception. A deep learning technique called RBNN is built using Gaussian function, fuzzy adaptive learning control network (FALCN), clustering, and radial basis neural network to achieve image segmentation and feature extraction. The suggested FALCN fuzzy system is excellent at clustering images and extracting image properties. Traditional fuzzy network systems tend to have redundant output neurons when receiving noisy input. Finally, random convolutional weights are used to extract features from unlabeled data.