Title :
Scene image classification using a wigner-based Local Binary Patterns descriptor
Author :
Sinha, Aloka ; Banerji, Sourangsu ; Chengjun Liu
Author_Institution :
New Jersey Inst. of Technol., Newark, NJ, USA
Abstract :
This paper introduces a new local feature description method to categorize scene images. We encode local image information by exploring the pseudo-Wigner distribution of images and the Local Binary Patterns (LBP) technique and make four major contributions. In particular, we first define a multi-neighborhood LBP for small image blocks. Second, we combine the multi-neighborhood LBP with the pseudo-Wigner distribution of images for feature extraction. Third, we derive the innovative WLBP feature vector by utilizing the frequency domain smoothing, the bag-of-words model and spatial pyramid representations of an image. Finally, we perform extensive experiments to evaluate the performance of the proposed WLBP descriptor. Specifically, we test our descriptor for classification performance using a Support Vector Machine (SVM) classifier on three fairly challenging publicly available image datasets, namely the UIUC Sports Event dataset, the Fifteen Scene Categories dataset and the MIT Scene dataset. Experimental results reveal that the proposed WLBP descriptor outperforms the traditional LBP technique and yields results better than some other popular image descriptors.
Keywords :
Wigner distribution; feature extraction; image classification; performance evaluation; smoothing methods; support vector machines; LBP technique; SVM classifier; UIUC sports event dataset; WLBP descriptor; Wigner-based local binary patterns descriptor; bag-of-words model; classification performance; feature extraction; fifteen scene categories dataset; frequency domain smoothing; image block; image descriptor; innovative WLBP feature vector; local feature description method; local image information; multineighborhood LBP; performance evaluation; pseudo-Wigner distribution; scene image classification; spatial pyramid image representation; support vector machine classifier; Feature extraction; Frequency-domain analysis; Histograms; Kernel; Training; Vectors; Visualization;
Conference_Titel :
Neural Networks (IJCNN), 2014 International Joint Conference on
Conference_Location :
Beijing
Print_ISBN :
978-1-4799-6627-1
DOI :
10.1109/IJCNN.2014.6889660