Earticle

An effective visible light and infrared image fusion method using a deep learning framework is designed to obtain a fused image which contains all the features from infrared and visible images. First, the source images are decomposed into low frequency and high frequency sub bands using wavelet transform. Then the low frequency is fused by maximum fusion rule. For the high frequency sub bands a deep learning network is used to find activity level measurements and then fused using the maximum fusion rule. For reconstruction, the optimized orthogonal matching pursuit algorithm and inverse wavelet transform are used.

본 논문에서는 시각적인 자극을 희소 분포로 표현함으로써 입력 자극이 가지고 있는 형태적인 시맨틱을 기억하고 리 콜하는 모델을 제안한다. 사람의 두뇌에서 대뇌 신피질은 정보 처리와 기억을 담당하며 대뇌 신피질에서 뉴런의 동 작 메커니즘은 희소 분포 표현(SDR; Sparse Distributed Representation)으로 모델링 할 수 있다. 이와 같은 희소 분포 표현 기반의 기억 모델은 입력 자극을 기억하는 과정과 유사한 기억을 리콜하는 과정으로 구분하여 고려 할 수 있다. 먼저, 기억 과정은 시각 자극을 희소 분포 표현으로 변환하는 과정이며, 이 과정에서 기본적으로 입력 정보의 형태적인 시맨틱이 유지된다고 생각할 수 있다. 다음으로 이와 같이 기억된 정보와 새로운 입력 자극에 대한 희소 분포 표현들을 비교함으로써 유사한 형태적 시맨틱을 가지고 있는 기억을 리콜할 수도 있다. 본 논문에서는 리 콜 과정에서 형태적 시맨틱의 유사도를 측정하기 위한 기준으로 희소 분포 표현의 중첩률을 사용한다. MNIST (Modified National Institute of Standards and Technology) 데이터를 활용한 제안 모델의 실험 결과 10,000 개의 영상을 기억에 사용하고 주어진 시각 자극에 대한 리콜 실험을 한 결과 희소 분포 표현이 시각 자극의 형태적 시맨틱을 잘 유지하고 있음을 확인하였다.

This paper proposes a model to remember and recall morphological semantic of input visual stimuli using SDR(sparse distributed representation). Neocortex in human brain is in charge of information processing and memory, and operation of neurons in neocortex can be modeled by sparse distributed representation. This memory model based on sparse distributed representation can be considered as memory precess and recall process separately. First, memory process means a process to convert input visual stimuli to sparse distributed representation, and in this process, morphological semantic of input visual stimuli can be preserved. Next, recall process can be considered by comparing sparse distributed representation of new input visual stimulus and remembered sparse distributed representations. Superposition of sparse distributed representation is used to measure similarities. Experimental results using 10,000 images in MNIST(Modified National Institute of Standards and Technology) data set show that the sparse distributed representation of the proposed model efficiently keeps morphological semantic of the input visual stimuli.

In this paper, we propose a fast and robust tracking method based on reversed sparse representation. Be different from other sparse representation based visual tracking methods, the target template is sparsely represented by the candidate particles which are gotten by particle filter. In order to improve the robustness of the method, we use a target template set. Meanwhile, a two level competition mechanism is also introduced. In the first level, each target template is sparsely represented and all the candidate particles compete with each other by a similarity calculation, which is based on sparse coefficients. Then, the winners construct a target candidate set. In the second level, all the target candidates in the target candidate set compete with each other and the one which is the most similar to the template set is considered as the target. In addition, a template set update strategy is proposed to adapt the appearance variations of the target. Experimental results on challenging benchmark video sequences demonstrate that the proposed tracking algorithm performs favorably against several state-of-the-art methods.

In this paper, we propose a robust tracking method with a novel appearance model based on fragments-based PCA sparse representation. It samples non-overlapped local image patches within the templates in PCA subspace. Then, the candidate local image patches are sparse represented by the local template patches in PCA subspace. Finally, tracking is continued using the particle filter for propagating sample distributions over time. In addition, the templates are updated online based on incremental subspace learning .Using the fragments-based PCA templates rather than the image templates facilitates the tracker to handle significant illumination and pose change as well as occlusion. Experimental results on challenging videos show that our method can track accurately and robustly, and outperform many other state-of-the- art trackers.

Facial recognition (FR) is a challenging area of research due to difficulties with robust FR when the number of training samples is very small. The state-of-the-art sparse representation-based classification (SRC) shows very excellent FR performance. However, the recognition rate of SRC will drop dramatically when the number of training samples per class is very limited. To solve these issues, we propose a weighted multi-classifier optimization and sparse representation based (WMSRC) method for FR, which efficiently combines the local and global characteristics of face images. A face image is firstly divided into continuous but non-overlapped blocks by multi-resolution based blocking and each block is sparsely represented over the corresponding set of blocks of all training samples. The multi-scale SRC classifiers are then established and associated with different weights based on sub-block dictionary learning. According to the multiple voting results of the classifiers, the weights of multi-classifiers are optimized by a least-squares optimization equation with 2l-norm regularization. Finally, the classification results of all the blocks are combined by a weighted fusion criterion. Our experiments show that the WMSRC algorithm outperforms many existing block-based sparse representation classification algorithms, especially for FR when the available training samples per subject are very limited.

In allusion to the losses of image detail and texture structure information during image de-noising process, an image de-noising algorithm based on non-related dictionary learning is proposed in this paper. Firstly, this algorithm is adopted to obtain self-adaption redundant dictionary for the noisy image through the dictionary learning algorithm; secondly, HOG features and gray-level statistical features of each atom in the dictionary are extracted to form the feature set, and meanwhile the feature set of the atoms is adopted to divide the atoms into two types (non-noisy atoms and noisy atoms); finally, the non-noisy atoms are adopted to recover the image, thus to realize the de-nosing purpose. The experiment result shows: the proposed algorithm does not need to know the prior information of the noise and PSNR performance thereof is better than that of existing algorithms, and meanwhile the proposed algorithm can well keep the image detail and texture structure information, thus to improve visual effect.

Signal sparse matrix structure, the degree of relationship between signal sparse representation, which affect application of compression perception to the effect of recovery reconstruction for signal. In order to solve this problem, a variety of dictionary learning algorithm such as KSVD, OLM (Online dictionary learning method) should be put forward. These algorithms used overlapping image blocks to build a dictionary, produced a large number of sparse coefficients, resulting in a fitting and calculation too slowly, and cannot ensure convergence. Based on this, it designed a fast dictionary learning algorithm based on proximal gradient. Algorithm based on the analysis of proximal gradient multiple, on the basis of convex optimization problem, applied to the dictionary learning involved in solving optimization, reduce the complexity of each iteration, reduces the iterative overhead, at the same time to ensure the convergence. Experiments on synthetic data show that the proposed algorithm dictionary learning speed, the time is short, and obtain a better dictionary.

Due to the limitation of hardware, Infrared (IR) image has low-resolution (LR) and poor visual quality. To enhance the Infrared image’s resolution, super-resolution (SR) is a good solution. However, the conventional SR methods have some drawbacks. Firstly, the trained dictionary is an unstructured dictionary, which may lead to worse results. Secondly, the representation of the image is too simple to effectively represent image. Finally, only one high-resolution (HR)-LR dictionary pair is adopted to infer HR IR image. However one HR-LR dictionary pair is not good enough to obtain good results. To resolve these problems, in this paper, firstly, the sparse dictionary is introduced into the IR image SR to get better results. Secondly, nonsubsampled contourlet transform (NSCT) is employed to obtain a better representation of IR image. Finally, to achieve better r-esults, two HR–LR sparse dictionary pairs, which consists of a primitive sparse dictionary pair and a residual sparse dictionary pair, instead of one HR-LR dictionary pair are adopted. The experiment results indicate that the subjective visual effect and objective evaluation acquire excellent performance in the proposed method. Besides, this method is superior to other methods.

For hyperspectral remote sensing image denoising, this paper proposed image denoising based on non-local low-rank dictionary learning. The basic idea of algorithm is to use strong relativity of all wave bands of hyperspectral remote sensing image with local self-similarity and local sparsity of image to improve the denoising performance. First of all, combined with the strong relativity, non-local self-similarity and local sparsity, non-local low-rank dictionary learning is established. Then iterative method is used to solve the model to get redundant dictionary and sparsity to represent coefficient. Finally, redundant dictionary and sparsity is used to express restored image of coefficient. Compared with the existing advanced algorithm, by making full use of strong relativity each band of hyperspectral image, it makes the algorithm obtain the information on details to well keep the hyperspectral remote sensing image, to improve the visual effect. Experimental results verify the effectiveness of the algorithm in this paper.

Features for representing the target are the fundamental ingredient when constructing the appearance model in the tracking problem. Only one type of features is utilized to represent the target in most current algorithms. However, the limited representation of a single feature might not resist all appearance changes of the target during the tracking process. To cope with this problem, we propose a novel tracking algorithm - Mean Kernel Tracker (MKT) - to robustly locate the object. The MKT combines three complementary features - Color, HOG (Histogram of Oriented Gradient) and LBP (Local Binary Pattern) - to represent the target. And Extensive experiments on public benchmark sequences show MKT performs favorably against several state-of-the-art algorithms.

The concept of the quaternion is useful for colour image processing and recognition. This paper introduces quaternion discrete Tchebichef moments (QTM), which use the traditional Tchebichef moments (TM) of each colour channel to describe colour images. A set of invariants that are invariant to translation and scale transformations is introduced for colour object recognition and image classification. A theoretical framework is provided for the recognition of colour face images by combining the proposed quaternion Tchebichef moment functions with the sparse representation classification (SRC) strategy for improving recognition despite partial occlusions. Simulation results on standard colour face databases demonstrate the effectiveness of the proposed algorithm, even when the images include Gaussian or pepper-and-salt noise.

Under today’s big data environment, with the rapid development of computer network technology and information technology, data mining is becoming more and more important in computer science. Classification is one of the most important aspects in data mining research Field. Recently, representation methods, such as sparse representation and low rank representation, have been much concerned. They both have wide applications in scientific and engineering fields. However, sparse representation and low rank representation include many methods, although these methods have their own characteristics, they are all effective for handling classification problems. This paper focuses on the performance comparison of different representation methods currently used in handling classification problems and views other conventional methods that can be applied in this field.

In this paper, a machine-learning approach called Sparse Representation-based Classification (SRC) is used for automatic chord recognition in music signals. We extracted different Pitch Class Profile (PCP) features from raw audio and achieved sparse representation of classes via 1 -norm minimization on feature space to recognize 24 major and minor triads. This recognition model is evaluated on MIREX’09 dataset including the Beatles corpus. Our method is compared with various methods that entered the Music Information Retrieval Evaluation eXchange (MIREX) in 2014 towards the audio chord estimation of MIREX’09 dataset in Audio Chord Estimation task of MIREX. Experimental results demonstrate that our method has good accuracy rate in recognizing maj-min chords.

Recently, an emerging method called image sparse representation has attracted more attentions. The method has been proved to be effective in various image processing applications. It is important to note that few sparse representation methods fail to analyze the aliasing in satellite image restoration. To address the problem, firstly, we employ adaptive reciprocal cell as a image quality estimation tool, which can analyze the satellite image degradation factors including aliasing, blur and noise. Then, with the help of the powerful tool, the estimation about the satellite image quality is introduced into the sparse representation model . Experiment results show that our method can produce good quality restored results.

In this paper, we have proposed an optimized sparse representation algorithm based on Log-Gabor (Sparse Representation-based Classification Based on Log-Gabor, Log-GSRC), which applies local features information of samples to the sparse representation method. Actually, SRC (Sparse Representation-based Classification) is using a linear correlation between the samples of one class which can be assumed that these samples exist in a subspace, and also can be linear represented with each other. It is a global representation and it ignores the local features information of the samples, while in the case of there are a smaller number of training samples per class, SRC will obtain an inaccurate classification result which may correspond to one and more classes in the process of sparse decomposition. However, the Log-GSRC combines global and local features information of the samples and also improves the robustness of SRC. The experimental results clearly showed that Log-GSRC has much better performance than SRC and also has much higher recognition rates than SRC in face recognition.

Image denoising is a basic problem in image processing, due to the image structure has the characteristic of self-similar, using the ideas of nonlocal, this paper proposes a non-local denoising method based on sparse representation, the structure information of image is improved after denoising, at the same time making similar image tiles have similar sparse representation, image reconstruction effect is better, through the numerical simulation the results show that the method has good application value.

The emergence of a large number of databases for capturing 3D human motions has made the efficient analysis and processing of human motion data to effectively use these databases a new challenge. To reduce high-dimension complexity, a dimensional feature based on the 3D spatial–temporal characteristic should be extracted from human motions. Moreover, the motion data should be re-expressed by sparse representation to realize the projection from high dimensional data to a low-dimensional subspace. The different motions should then be recognized and classified to obtain the automatic recognition and automatic retrieval of 3D human motions.

In this paper, a machine-learning approach called Sparse Representation Classification(SRC) Viterbi Algorithm is proposed for automatic chord recognition in music. We extracted Pitch Class Profile(PCP) features or Log PCP from raw audio and achieved sparse representation of classes via -norm minimization on feature space to recognize 24 major and minor triads. This recognition model is evaluated MIREX'09 dataset including the Beatles corpus. Our method is also compared with various methods that entered the Music Information Retrieval Evaluation exchange (MIREX) in 2013 and 2014. Experimental results demonstrate that our method has good accuracy rate in recognizing signal chord and has fewer train data.

In this paper, we present a new approach to reconstruct a high resolution (HR) image from a low resolution (LR) input image based on a two dimensional (2D) sparse method. The new method consists of three phases. Firstly, the nonlinear feature of the input LR image is divided into the linear subspace, and then LR-HR dictionaries are learned to reduce the blurred artifacts of the image. Secondly, 2D sparse representation and self-similarity are developed to strengthen and enhance the image structure. Finally, the final HR image is achieved by reconstruction of all HR patches. Simulation results demonstrated that our proposed method achieved superior results on real images, and shows various improvements in terms of PSNR and SSIM values as compared with some other competent methods.

We propose a novel image inpainting approach in which the exemplar and the sparse representation are combined together skillfully. In the process of image inpainting, often there will be such a situation: although the sum of squared differences (SSD) of exemplar patch is the smallest among all the candidate patches, there may be a noticeable visual discontinuity in the recovered image when using the exemplar patch to replace the target patch. In this case, we cleverly use the sparse representation of image over a redundant dictionary to recover the target patch, instead of using the exemplar patch to replace it, so that we can promptly prevent the occurrence and accumulation of errors, and obtain satisfied results. Experiments on a number of real and synthetic images demonstrate the effectiveness of proposed algorithm, and the recovered images can better meet the requirements of human vision.