Object Recognition with Contextual Reasoning Based Fuzzy Neural Networks for the Uncertainty Output
JSHS · 2023
Overview
Object recognition is an important task in image processing and fuzzy neural network (FNN) is a popular tool for object recognition. However, when applied to datasets that present complex and fuzzy features, the accuracy of such FNN is degraded, and their uncertainty of output is increased. T o tackle this problem, we propose in this paper a contextual reasoning based fuzzy neural network. The proposed method, called CR-FNN, is composed of two phases. In the first phase, the CR-FNN algorithm is a classifier for object recognition, which outputs the predicted value of the FNN. In the second phase, the categories of images are used as the basis for context comparisons. We embed the network output with a local search strategy to determine the object category by the features ranking and the distance between the contextual knowledge and the object. The performance of the developed algorithm has been evaluated on three datasets. The datasets both present the characteristics of complex and fuzzy image features. Further analysis is made with parameter metrics such as accuracy (ACC), Hamming loss (HL), average precision (AP), weighted accuracy (WA), recall, and Area under the ROC Curve (AUC). The proposed FNN with contextual reasoning has better performance over the traditional FNN and existing baseline algorithms. The experimental results show that the accuracies of CR-FNN are 19.8%, 9.8%, and 11.2% higher than the traditional FNN on the three datasets respectively and provide a new solution to the uncertainty of the output of FNNs.
Competition history
- JSHS 2023
Resources
Related projects
ISEF · 2023
Object Recognition With Contextual Reasoning Based Fuzzy Neural Networks for the Uncertainty Output
ISEF · 2021
Fusing LiDAR and Camera Data for Advanced Context Recognition in Autonomous Navigation Sensory Systems Through Multidimensional Deep Neural Network Architectures
ISEF · 2023
Boundary Based Anomaly Detection in Deep Neural Networks
ISEF · 2026
A Novel Evaluation of the Impact of Object Deformation on Real-Time Vision-Based Waste Classification Utilizing Low-Cost AI Systems
ISEF · 2018
Deep Learning Real-Time Object Detection Through Convolutional Neural Networks Using OpenCV and Optical Flow Algorithms for the Visually-Impaired
ISEF · 2019
Protection of Deep Neural Networks against Adversarial Attacks with Application to Facial Recognition
ISEF · 2021
CET-CNN: Modular Hierarchical Image Classification Using Conditional-Execution Tree CNNs
ISEF · 2015
Functional Neural Networks Evaluated by Weierstrass Polynomials
Closest projects by meaning, across every fair and year in the corpus.