BEIA is happy to announce a new publication in MDPI Information Journal (Special Issue Trends in Computational and Cognitive Engineering).
See below more info about the paper
Paper name: Image Geo-Site Estimation Using Convolutional Auto-Encoder and Multi-Label Support Vector Machine
Authors: by Arpit Jain, Chaman Verma, Neerendra Kumar, Maria Simona Raboaca, Jyoti Narayan Baliya and George Suciu
Abstract
The estimation of an image geo-site solely based on its contents is a promising task. Compelling image labelling relies heavily on contextual information, which is not as simple as recognizing a single object in an image. An Auto-Encode-based support vector machine approach is proposed in this work to estimate the image geo-site to address the issue of misclassifying the estimations. The proposed method for geo-site estimation is conducted using a dataset consisting of 125 classes of various images captured within 125 countries. The proposed work uses a convolutional Auto-Encode for training and dimensionality reduction. After that, the acquired preprocessed input dataset is further processed by a multi-label support vector machine. The performance assessment of the proposed approach has been accomplished using accuracy, sensitivity, specificity, and F1-score as evaluation parameters. Eventually, the proposed approach for image geo-site estimation presented in this article outperforms Auto-Encode-based K-Nearest Neighbor and Auto-Encode-Random Forest methods.
Keywords:
SVM classification; convolutional Auto-Encoder; Auto-Encoder-KNN algorithm; random forest algorithm
Acknowledgments
This paper was partially supported by UEFISCDI Romania and MCI through BEIA projects AutoDecS, SOLID-B5G, T4ME2, DISAVIT, PIMEO-AI, AISTOR, MULTI-AI, ADRIATIC, Hydro3D, PREVENTION, DAFCC, EREMI, ADCATER, MUSEION, FinSESCo, iPREMAS, IPSUS, U-GARDEN, CREATE and by European Union’s Horizon 2020 research and innovation program under grant agreements No. 101073932 (RITHMS).
Find out here the full paper.