Guiqing He

Image fusion with nonsubsampled contourlet transform and sparse representation

Abstract. Image fusion combines several images of the same scene into a fused image, which contains all important information. Multiscale transform and sparse representation can solve this problem effectively. However, due to the limited number of dictionary atoms, it is difficult to provide an accurate description for image details in the sparse representation–based image fusion method, and it needs a great deal of calculations. In addition, for the multiscale transform–based method, the low-pass subband coefficients are so hard to represent sparsely that they cannot extract significant features from images. In this paper, a nonsubsampled contourlet transform (NSCT) and sparse representation–based image fusion method (NSCTSR) is proposed. NSCT is used to perform a multiscale decomposition of source images to express the details of images, and we present a dictionary learning scheme in NSCT domain, based on which we can represent low-frequency information of the image sparsely in order to extract the salient features of images. Furthermore, it can reduce the calculation cost of the fusion algorithm with sparse representation by the way of nonoverlapping blocking. The experimental results show that the proposed method outperforms both the fusion method based on single sparse representation and multiscale decompositon.

An Infrared and Visible Image Fusion Method Based on Non-Subsampled Contourlet Transform and Joint Sparse Representation

In conventional fusion methods based on NonSubsampled Contourlet Transform (NSCT), low-frequency subband coefficient of an image fails to express sparsely the images low-frequency information, not in favor of extracting source image features. To address this issue, an infrared and visible image fusion method based on NSCT and joint sparse representation (JSR) was proposed, in which, JSR transform of the images low-frequency information is conducive to improving sparsity of low-frequency subband containing main energy of the image, as to high-frequency information, use of feature product as a fusion rule is beneficial to extract detail feature of the source image. Experimental result indicates that, compared with conventional multiscale transform-based DWT, NSCT-based fusion method and sparse representation-based SR and JSR algorithms, the method in this paper achieved better fusion effect, capable of keeping target information of the infrared image and background detail information (edge, texture, etc.) of the visible image better.

Research on Course Quality Evaluation Method of University Bilingual Education

Course quality evaluation is a basic issue and main section of bilingual education. This paper researches the course quality evaluation theory which is of characters of university bilingual education. It first discusses the current study situation in this field. And then, proposes the detail operation methods of bilingual course quality evaluation from the teaching materials, special knowledge learning, English ability promotion and experimental skill. The research is of benefit to the development of bilingual education.

Discussion on the Bilingual Teaching Methods of Chinese University

As Chinese economy is brought into the development trend of globalization and the communication with other countries is becoming more and more frequent, cultivating of bilingual personnel has become one of important goals of Chinese education. This paper first studies the bilingual education modes of some representative countries which have abundant experience in these aspects, then discusses some issues deeply about bilingual education in Chinese university concerned with its present situation. The issues are about Chinese bilingual education mode, transitional mode and most concerned problems, as well as the bilingual teaching methods. It is helpful to improvement of Chinese university bilingual education.

Panchromatic and multi-spectral image fusion for new satellites based on multi-channel deep model

With the launch and rapid development of new satellites such as WorldView-3, the bands number of multi-spectral images from new satellites is greatly increased. However, the spectral matching between the panchromatic image and multi-spectral images is deteriorated with the existing image fusion methods. In this paper, a novel method based on the multi-channel deep model is proposed to fuse images for new satellites. The deep model is implemented by convolutional neural networks and trained on each band to reduce the impact of spectral range mismatch. The proposed method also preserves the detailed information in multi-spectral images, which is ignored by the traditional methods. It also effectively alleviates the inconvenience for obtaining the remote sensing images by the data augmentation processing. In addition, it reduces the randomness of manual setting parameters using the parameter self-learning. Visual and quantitative assessments of fusion results show that the proposed method clearly improves the fusion quality compared to the state-of-the-art methods.

An Image Fusion Method Based on Simultaneous Sparse Representation with Nonsubsampled Contourlet Transform

The image fusion method based on sparse representation in the single-scale image domain has produced better fusion results than the classic methods based on multi-scale analysis nowadays. However, due to the limited number of dictionary atoms, it is difficult to provide an accurate description for image details in the sparse-representation-based image fusion methods, and it requires a lot of time. A novel dictionary is constructed with non-subsampled contourlet transform and sparse representation by using the proposed simultaneous strategy. Then the novel dictionary could combine the sparsity attribute of the learning dictionary with a multi-scale feature of non-subsampled contourlet transform. Moreover, the simultaneous strategy is combined with this novel dictionary so that sparse coefficients can be represented with the same dictionary atoms and thus they can be compared in a reasonable and accurate way. Finally, the image fusion method along with this novel dictionary is proposed and named non-subsampled contourlet transform (NSCT)-simultaneous sparse representation (SSR). Experimental results show that the proposed fusion method NSCT-SSR, with its more excellent fusion effect and better anti-noise capability, outperforms the existing fusion methods, which are based on both multi-scale domain and sparse representation in the single-scale image domain.

Study on panchromatic and multispectral image fusion based on SFIM and CA transform

With the successive launch and rapid development of the new satellite WorldView-2 and WorldView-3, panchromatic and multispectral image fusion become a hot research topic. To resolve the dilemma of the currently existing methods for panchromatic and multispectral image fusion, viz. unavoidable spectral distortion or the need to introduce cumbersome frequency analysis and reconstruction, a method has been proposed which is based on SFIM (Smoothing Filter-based Intensity Modulation) and CA (Correspondence Analysis). Firstly, the weighted gradient adaptive filtering SFIM model is introduced, whose simple calculation feature has been utilized to extract the spatial information of panchromatic images. Secondly, the statistical CA transform has been brought in and its multivariable analysis feature has been used to process the infusion of spatial information. As a result of the above two processes the novel fusion method has been proposed which is based on SFIM and CA transform. Theoretical and experimental studies show that the proposed method can not only significantly maintain spectral characteristics, in absence of frequency decomposition and reconstruction, but also effectively infuse detailed spatial information, along with the elegancy of simple calculation and real time. In the scenario of panchromatic and multi-spectral image fusion such as similar lighting conditions and physical properties, the proposed method is more suitable for the fusion systems which require fast interactive processing and real-time visualization, and is better than those which are based upon multi-scale analysis.

Study on algorithm evaluation of image fusion based on multi-hierarchical synthetic analysis

To resolve the algorithm evaluation issue of multi-sensor image fusion, we propose a novel synthetic evaluation method using multi-hierarchical gray relational analysis mechanism, which has the merit of using small-sized samples and of allowing unitary comparison. The proposed method combines a priori knowledge and quantization evaluation. In this paper we first outline a basic three-step procedure in order toperform the gray relational analysis for a single-hierarchy evaluation system, and then give a four-step procedure to perform multi-hierarchical evaluation system. Therefore, we obtain a synthetic evaluation result that is more quantitative and comprehensive than conventional subjective and objective measures such as correlation coefficient and average gradient. The novel evaluation method can give not only overall performance evaluation for image fusion algorithm but also specific performance evaluation. Extensive experimental analysis shows that the proposed method generates better evaluation result with respect to quantization, precision, objectivity, reliability, and real-time evaluation. These advantages make it applicable to fusion systems with feedback capability, and can enrich and perfect the image fusion system.

Study on WorldView-2 Image Fusion Method Based on NMF and HCS Transform

With the launch and rapid development of a novel satellite WorldView-2, study on fusion of panchromatic and multispectral images from the satellite has become a hot spot. As there are generally a pair of contradictions existing in the panchromatic and multispectral image fusion method: either failure to avoid spectral distortion, or need of introducing a complex and time-consuming frequency decomposition and reconstruction process, a panchromatic and multispectral image fusion method based on non-negative matrix factorization (NMF) and hyperspherical color sharpening (HCS) was proposed in this paper. Owing to the mismatch of special coverage range of Worldview-2 panchromatic and multispectral images, the intensity component I extracted from multispectral images differs greatly from that extracted from panchromatic images (PAN), causing increased spectral distortion. In the component I extraction method based on NMF proposed in this paper, image fusion is conducted using the advantage that NMF can automatically find the hidden mode or trend behind data and further using the WorldView-2 faced HCS transform. The experimental results show that this algorithm can significantly retain the spectral characteristics, and does not contain a frequency decomposition and reconstruction process, in addition, spatial detail information is effectively incorporated, so the algorithm has simple calculation and good real-time property, and has important application reference value for fusion systems that need rapid interactive processing and real-time visualization.