Aug 2026· ИНФОРМАЦИОННЫЕ СИСТЕМЫ И ТЕХНОЛОГИИ· Vol 25, pp. 23-32· 0 citations
TL;DR
A hybrid Fuzzy-CNN method is proposed: pixels or visual features are first «fuzzified» in a logical sense to account for uncertainties, and then fed into the neural network.
Abstract
This study explores methods for combining fuzzy logic and convolutional neural networks (CNN) to improve image analysis when images are blurry, noisy, or have low contrast. Fuzzy logic is used to represent areas of imprecision in an image by assigning each pixel a degree of membership to different sets, while convolutional neural networks automatically detect important features and identify objects present. Thus, the paper proposes a hybrid Fuzzy-CNN method: pixels or visual features are first «fuzzified» in a logical sense to account for uncertainties, and then fed into the neural network. A defuzzification stage is then applied to the output to obtain a clear and interpretable final result. This approach enhances the reliability of tasks such as segmentation, classification, or image enhancement, particularly in medical or industrial contexts where image quality may be degraded. Tests conducted demonstrate that this hybrid strategy outperforms classical approaches based solely on fuzzy logic or CNN alone, providing higher accuracy and robustness to visual variations and uncertainties. Thus, it represents a solid foundation for more intelligent and adaptive image processing in challenging conditions.
This study focuses on enhancing handwritten Devanagari character recognition using deep learning models, specifically fine-tuned Convolutional Neural Networks (CNNs), combined with hybrid mathematical methods for image enhancement, proposing a fuzzy-enabled Power-Law transformation for image enhancement.
Akshara Sreenivasan, Vinodkumar Vinodkumar Arumugam, Sriramakrishnan Pathmanaban et al.· Chaos and Fractals· 0 citations
This paper introduces the Fuzzy Rule-Based Network (FRBN or FN), a novel machine learning architecture designed to bridge the gap between high-performance modeling and human-understandable decision-making. By combining the layered, hierarchical structure of artificial neural networks (NN) with the logical transparency of fuzzy systems, the FN operates as an interpretable “gray-box” model. Unlike traditional “black-box” neural networks that obscure their internal logic, the FN explicitly encodes its learned knowledge using fuzzy “if-then” rules at every layer, providing structural modularity and insight into how decisions are made. To optimize both FN and NN models, various strategies were comprehensively evaluated, including first-order gradient methods such as Adam, the quasi-second-order Levenberg–Marquardt algorithm, the gradient-free Bacterial Evolutionary Algorithm (BEA), and a hybrid Bacterial Memetic Algorithm (BMA) implemented for both neural and fuzzy network models. The predictive accuracy, structural modularity, and interpretability of the proposed FN model were assessed on several synthetic regression benchmarks, including the sinc function (where the FN model achieved a best-fold validation MSE of
$$6.2 \times 10^{-8}$$
), a multidimensional trigonometric dataset and validated on an industrial Micro-Electromechanical Systems (MEMS) sensor dataset. These experimental results demonstrate that the FN model provides a solution competitive with the NN model in terms of accuracy and training efficiency. The experiments demonstrate how the structural modularity of the FN model enables the reduction of parameters through the post-hoc extraction of localized sub-models. These specific fuzzy rule-sets maintain the exact predictive accuracy of the full model within their designated sub-intervals. The study further illustrates how the significance score identifies which specific rules govern particular subdomains, while the minimum antecedent coverage ratio evaluates the spatial scope of rules to distinguish between global and local influences. Additionally, the model’s interpretability is validated on the MEMS dataset, where linguistic interpretations are associated with the fuzzy rules. The FN can be initialized using domain knowledge, which stabilizes and accelerates training convergence. Finally, the trained rules can be translated back into human-understandable if-then statements, representing a step towards transparent decision-making.
H. Lukács, Ádám Smidla, Tamás Fischl et al.· Scientific Reports· 0 citations
Disease diagnosis and clinical treatment involve the combination of medical images, which is one of the major technologies in the medical field. As per literature analysis, the traditional methods have some limitations for generating the fused image, including low contrast, uncertainty, and distorted sides. To address these issues, we suggest a hybrid method of image fusion using NSCT (non-subsampled contourlet transform) and fuzzy sets. Firstly, the source images were fuzzified via a normalization process. After that, the fuzzy images are decomposed into approximation and detail layers at the various scales using multi-scale decomposition, i.e., NSCT. Secondly, the maximum and local variance-based rules are used to extract the significant structural and edge details from approximation and detail coefficients, respectively. Thirdly, the reconstruction process is carried out to achieve the final fused image, followed by the defuzzification process. This approach demonstrates the efficiency of the proposed fusion process with visual analysis, including different existing algorithms. Furthermore, the quantitative analysis proves the effectiveness of the proposed model using various quality metrics such as mean, standard deviation, and average gradient.
P. Mahesh, N. Srinu, M. Haribabu· 2026 7th International Confe...· 0 citations
Images of medical patients that were taken in low light or low contrast areas frequently have issues with noise, visibility, and important information for physicians to use in deciding on patient care. An Adaptive Hybrid Convolutional Neural Network Discrete Wavelet Transform Enhancement Technique for Low Light Medical Images is presented for use in helping to detect latent disease in X-ray and Magnetic Resonance Images. The method works as follows: The input image first goes through a Discrete Wavelet Transform to break it down into high frequency and low frequency components. Separating out the high frequency (noise) and low frequency parts of the image allows for a more efficient way to reduce noise while still preserving the critical structure of the image. Once the first step has been completed, multi-scale wavelet features are used to create a Convolutional Neural Network (CNN) enhancement module that learns how to adaptively learn how to make illumination corrections and improve contrast. The final part of the process is an Adaptive Histogram Equalization postprocessing step that improves visual clarity, therefore enhancing the final image to allow for good clinical interpretation. There are experimental results that demonstrate the new proposed framework is significantly better than existing methods on several common image quality metrics such as PERMANENT CRYSTAL, PSNR, and SSIM, and that it preserves the critical diagnostic features of the medical image. This method is extremely beneficial to radiologists because it allows for the accurate and reliable analysis of MRI images using Computer Assisted Diagnosis (CAD) systems and can be integrated with existing CAD systems to enhance and improve the radiologist’s ability to interpret the medical images of their patients.
D. Ferlin, D. Shahila, D. Stephen· International Conference on...· 0 citations
Image classification is a key application of computer vision with direct relevance to medical diagnostics, autonomous vehicles, and remote sensing. This paper discusses the use of an adaptive learning convolutional neural network (AL-CNN) for image classification, with results reported on a large-scale benchmark dataset that is widely accepted for performance evaluation. The AL-CNN architecture integrates convolutional, pooling, and fully connected layers. The model was systematically trained on a subset of the dataset and subsequently tested on an independent validation subset to evaluate its efficiency and generalization capability. In addition, optimization techniques such as data augmentation, dropout, and advanced activation functions were employed to further enhance model performance. The results, based on accuracy metrics, indicate the successful implementation of the proposed AL-CNN model for reliable and accurate image classification. This study demonstrates the potential of the AL-CNN approach to address various complexities in image classification, thereby enabling further innovation in this domain.
M. Chawla, Rashmi Agrawal, Bharat Bhushan· Bulletin of Electrical Engin...· 0 citations
Image Processing Using Machine Learning is an intelligent Artificial Intelligence-based system designed to analyze,
process, classify, and enhance digital images using Machine Learning and Deep Learning techniques. In today's digital era,
enormous amounts of image data are generated from medical imaging systems, surveillance cameras, social media platforms,
satellite systems, and industrial applications. Traditional image processing methods often depend on manual feature extraction
and predefined algorithms, which face limitations in terms of accuracy, scalability, automation, and real-time performance. This
project addresses these challenges by providing an intelligent and automated image processing framework that utilizes Artificial
Intelligence, Machine Learning, and Computer Vision techniques.The system processes images through multiple stages,
including image acquisition, preprocessing, feature extraction, classification, segmentation, and image enhancement to generate
meaningful and accurate outputs. It analyzes image characteristics such as color, texture, edges, and shapes to identify patterns
and make intelligent decisions. The proposed system integrates modern technologies including Artificial Intelligence, Machine
Learning algorithms, Deep Learning models, Convolutional Neural Networks (CNNs), Computer Vision techniques, image
enhancement methods, and database management systems to ensure high accuracy, efficiency, scalability, and real-time
processing capabilities.By combining intelligent image analysis with automated learning and enhancement mechanisms, the
Image Processing Using Machine Learning system aims to provide a reliable, efficient, and scalable solution suitable for
healthcare diagnostics, surveillance systems, multimedia applications, autonomous vehicles, satellite image analysis,
agricultural monitoring, and industrial quality inspection systems.
R. Rajesh, R. Aswini· International Journal for Re...· 0 citations