Subspace learning (SL) is one of the most useful tools for image analysis and recognition. A large number of such techniques have been proposed utilizing a priori knowledge about the data. In this paper, new subspace learning techniques are presented that use symmetry constraints in their objective functions. The rational behind this idea is to exploit the a priori knowledge that geometrical symmetry appears in several types of data, such as images, objects, faces, and so on. Experiments on artificial, facial expression recognition, face recognition, and object categorization databases highlight the superiority and the robustness of the proposed techniques, in comparison with standard SL techniques.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1109/TIP.2014.2367321 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Water quality prediction and carbon reduction mechanisms in wastewater treatment in Northwest cities using Random Forest Regression model.
Sci Rep
December 2024
School of Public Administration, Guangzhou University, Guangzhou, 510006, China.
With the accelerated urbanization and economic development in Northwest China, the efficiency of urban wastewater treatment and the importance of water quality management have become increasingly significant. This work aims to explore urban wastewater treatment and carbon reduction mechanisms in Northwest China to alleviate water resource pressure. By utilizing online monitoring data from pilot systems, it conducts an in-depth analysis of the impacts of different wastewater treatment processes on water quality parameters.
View Article and Find Full Text PDFExplainable AI-Based Skin Cancer Detection Using CNN, Particle Swarm Optimization and Machine Learning.
J Imaging
December 2024
PolitoBIOMed Lab, Department of Mechanical and Aerospace Engineering, Politecnico di Torino, 10129 Turin, Italy.
Skin cancer is among the most prevalent cancers globally, emphasizing the need for early detection and accurate diagnosis to improve outcomes. Traditional diagnostic methods, based on visual examination, are subjective, time-intensive, and require specialized expertise. Current artificial intelligence (AI) approaches for skin cancer detection face challenges such as computational inefficiency, lack of interpretability, and reliance on standalone CNN architectures.
View Article and Find Full Text PDFBrain-inspired multisensory integration neural network for cross-modal recognition through spatiotemporal dynamics and deep learning.
Cogn Neurodyn
December 2024
School of Electrical and Information Engineering, Tianjin University, Tianjin, 300072 China.
The integration and interaction of cross-modal senses in brain neural networks can facilitate high-level cognitive functionalities. In this work, we proposed a bioinspired multisensory integration neural network (MINN) that integrates visual and audio senses for recognizing multimodal information across different sensory modalities. This deep learning-based model incorporates a cascading framework of parallel convolutional neural networks (CNNs) for extracting intrinsic features from visual and audio inputs, and a recurrent neural network (RNN) for multimodal information integration and interaction.
View Article and Find Full Text PDFSoft sensor modeling method for Pichia pastoris fermentation process based on substructure domain transfer learning.
BMC Biotechnol
December 2024
Key Laboratory of Agricultural Measurement and Control Technology and Equipment for Mechanical Industrial Facilities, School of Electrical and Information Engineering, Jiangsu University, Zhenjiang, 212013, China.
Background: Aiming at the problem that traditional transfer methods are prone to lose data information in the overall domain-level transfer, and it is difficult to achieve the perfect match between source and target domains, thus reducing the accuracy of the soft sensor model.
Methods: This paper proposes a soft sensor modeling method based on the transfer modeling framework of substructure domain. Firstly, the Gaussian mixture model clustering algorithm is used to extract local information, cluster the source and target domains into multiple substructure domains, and adaptively weight the substructure domains according to the distances between the sub-source domains and sub-target domains.
A comprehensive review of metasurface-assisted direction-of-arrival estimation.
Nanophotonics
November 2024
Interdisciplinary Center for Quantum Information, State Key Laboratory of Modern Optical Instrumentation, ZJU-Hangzhou Global Scientific and Technological Innovation Center, Zhejiang University, Hangzhou 310027, China.
Article Synopsis
- Direction of Arrival (DoA) estimation is a critical area in array signal processing, with advancements in algorithms being driven by new metasurface technology and artificial intelligence.
- The study reviews the integration of traditional DoA algorithms with metasurfaces and explores the use of subspace and sparse representation methods to improve wave detection capabilities.
- Lastly, it highlights the challenges and opportunities that arise from merging metasurfaces and AI to enhance DoA detection and hardware implementation.
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!