Earticle

In this paper, we conduct research on issues related to the primary features of the Internet of things system and the corresponding data communication characteristics based on sparse coding and joint deep neural network. Internet of things is more than the underlying device difference communication method and it is the Internet of things needs to study in the field of hot issue. Using traditional algorithm for Internet communication equipment need particle filter was carried out on the acquisition of communication signal processing. Communication technology enables the Internet of things will perceive the information between different terminals for efficient transmission and exchange, exchange and sharing and the information resources is the key to the functions of things. To enhance the robustness and efficiency of the current IOT systems, we adopt the sparse coded dictionary learning theory to detect the size of the data and optimize the compressive sensing technique to modify the resolution. With the advances of the deep neural network, we analyze the topology of the system network structure and extract the pattern features and characteristics to make the signal transmission process more quickly and feasible. To enhance the objective function, we obtain the restricted optimization algorithm to help terminate the iteration for the higher efficiency. In the final part, we simulation our algorithm for times compared with other well-performed approaches. The result indicates that our method outperforms both in the accuracy layer an in the time-consuming layer which will hold specific meaning.

Hyperspectral image classification has received an increasing amount of interest in recent years. However, when representing pixels as vectors, the dimensionality of feature space is high, which causes “curse of dimensionality” problem. In this paper, in order to alleviate the impact of above problem, a manifold sparse coding method is proposed. Firstly, matrix decomposition technique is used to find a concept set and calculates relative data projection in the concept set. Secondly, manifold learning regularization is imported into objective function to capture the intrinsic geometric structure in the data. Finally, LASSO regularization is used to obtain sparse representation of data projection. Experimental results on real hyperspectral image show that the proposed method has better performance than the other state-of-the-art methods.

측면주사 소나 영상 획득의 효율성을 향상시키고자 저해상도의 수중 영상을 복원 기법을 이용하여 고화질 영상으로 개선시키는 연구가 시도되고 있다. 측면주사 소나 영상은 광학 영상과 같은 2차원 신호를 사용한다는 측면에서 기존 광학 영상 복원에 적용된 기법의 응용을 고려할 수 있다. 광학 영상에 대한 가장 대표적인 복원 방법 중 하나는 스파스 코딩이며, 수중 영상의 희소성을 분석하여 스파스 코딩 기법을 수중 영상에 적용할 수 있음을 증명하는 연구가 진행되었다. 스파스 코딩은 입력 신호에 대하여 사전과 스파스 계수의 선형 결합으로 복원 신호를 얻는 방식이다. 하지만 스파스 계수의 값을 정확히 추정하기 위해서는 많은 연산량을 필요로 한다. 본 연구에서는 스파스 코딩 기반의 수중 영상 초해상도 복원을 수행하되, 수중 영상 내 객체 영역에 한해서 선택적으로 복원 기법을 적용하는 방법을 제안함으로써 전체 연산 시간을 단축시킨다. 이를 위하여 수중 영상에서 경계를 검출하고 그 분포에 따라 객체 영역과 비객체 영역을 구분하는 방법을 제안하고, 이를 스파스 코딩 기반의 초해상도 복원 기법과 접목시킨다. 실험을 통해 제안하는 방법이 기존 방식과 동일 수준의 PSNR(Peak Signal-to-Noise Ratio) 수치를 유지하며, 영상 복원에 필요한 시간은 32 % 만큼 단축시킴을 확인함으로써 제안 방법의 유효성을 증명하였다.

Efforts have been made to reconstruct low-resolution underwater images to high-resolution ones by using the image SR (Super-Resolution) method, all to improve efficiency when acquiring side-scan sonar images. As side-scan sonar images are similar with the optical images with respect to exploiting 2-dimensional signals, conventional image restoration methods for optical images can be considered as a solution. One of the most typical super-resolution methods for optical image is a sparse coding and there are studies for verifying applicability of sparse coding method for underwater images by analyzing sparsity of underwater images. Sparse coding is a method that obtains recovered signal from input signal by linear combination of dictionary and sparse coefficients. However, it requires huge computational load to accurately estimate sparse coefficients. In this study, a sparse coding based underwater image super-resolution method is applied while a selective reconstruction method for object region is suggested to reduce the processing time. For this method, this paper proposes an edge detection and object and non object region classification method for underwater images and combine it with sparse coding based image super-resolution method. Effectiveness of the proposed method is verified by reducing the processing time for image reconstruction over 32 % while preserving same level of PSNR (Peak Signal-to-Noise Ratio) compared with conventional method.

In this paper, we propose a new approach to learning a discriminative model for figure/ground segmentation by incorporating the bag-of-features and conditional random field (CRF) techniques. We advocate the use of image patches instead of superpixels as the basic processing unit. The latter has a homogeneous appearance and adheres to object boundaries, while an image patch often contains more discriminative information (e.g., local image structure) to distinguish its categories. We use pixel-level sparse coding to represent an image patch. With the proposed feature representation, the unary classifier achieves a considerable binary segmentation performance. Further, we integrate unary and pairwise potentials into the CRF model to refine the segmentation results. The pairwise potentials include color and texture potentials with neighborhood interactions, and an edge potential. High segmentation accuracy is demonstrated on three benchmark datasets: the Weizmann horse dataset, the VOC2006 cow dataset, and the MSRC multiclass dataset. Extensive experiments show that the proposed approach performs favorably against the state-of-the-art approaches.

In this paper, we present a method that can recognize face images by use of a sparse population code that is a learning model about a receptive fields of the simple cells in the primary visual cortex. Twenty front-view facial images form twenty persons were used for the training process, and 200 varied facial images, 20 per person, were used for test. The correct recognition rate was 100% for only the front-view test facial images, which include the images either with spectacles or of various expressions, while it was 90% in average for the total input images that include rotated faces. We analyzed the effect of nonlinear functon that determine the sparseness, and compared recognition rate using the sparese population code with that using eigenvectors (eigenfaces), which is compact code that makes contrast with the sparse population code.