Remote sensing image pan sharpening has attracted researchers’ interest, since spatial resolution of multispectral (MS) image can be enhanced by injecting spatial details of a panchromatic image to MS image. In this paper, a novel sparse representation based pan sharpening method is proposed to overcome the disadvantages of traditional methods such as color distortion and blurring effect. This learning based method utilizes a compact single dictionary generated from texture information of high-resolution MS images in order to provide more effective and robust pan sharpening. Two data sets acquired from IKONOS and Quickbird satellites are used to evaluate the performance and robustness of the proposed algorithm. The proposed method is compared with nine well-known component substitution and multiresolution analysis methods and a state-of-art method using several quality measurement indices with references. The experimental results demonstrate that the proposed algorithm is competitive or superior to other conventional methods in terms of visual and quantitative analysis, as it preserves spectral information and provides high quality spatial details in the final product image.
1 September 2008 in Journal of Computer Science and Technology
Incremental feature extraction algorithms are designed to analyze large-scale data streams. Many of them suffer from high computational cost, time complexity, and data dependency, which adversely affects the processing of the data stream. With this motivation, this paper presents a novel incremental feature extraction approach based on the Discrete Cosine Transform (DCT) for the data stream. The proposed approach is separated into initial and sequential phases, and each phase uses a fixed-size windowing technique for processing the current samples. The initial phase is performed only on the first window to construct the initial model as a baseline. In this phase, normalization and DCT are applied to each sample in the window. Subsequently, the efficient feature subset is determined by a particle swarm optimization-based method. With the construction of the initial model, the sequential phase begins. The normalization and DCT processes are likewise applied to each sample. Afterward, the feature subset is selected according to the initial model. Finally, the k-nearest neighbor classifier is employed for classification. The approach is tested on the well-known streaming data sets and compared with state-of-the-art incremental feature extraction algorithms. The experimental studies demonstrate the proposed approach’s success in terms of recognition accuracy and learning time.