Search

Magnetic resonance imaging can only acquire volume data with finite resolution due to various factors. In particular, the resolution in the slice direction is much lower than that in the in-plane direction, yielding un-realistic visualizations. To solve this problem, interpolation techniques have conventionally been applied. However, classical interpolation techniques generally cause some artifact noise such as jaggedness and blurring in the edge regions. In this paper, we propose a new superresolution framework for generating high-resolution data in the slice direction. In the proposed approach, we estimate the high-frequency component using a learning-based super-resolution technique with sparse representation and prove that the dictionary can be constructed using the in-plane frame as the input data without any other high-resolution data as training. Furthermore, we optimize estimated high-resolution data by adding a new regularization term with a nonlocal means algorithm. Experiments confirm that our proposed method is more effective than the conventional methods. [ABSTRACT FROM PUBLISHER]

This paper presents a learning-based method called image super-resolution (SR) for generating a high-resolution (HR) image from a single low-resolution (LR) image. Recent research investigated the image SR problem using sparse coding, which is based on good reconstruction of any image local patch by a sparse linear combination of atoms from an overcomplete dictionary. However, sparse-coding-based SR (ScSR) generally takes a significant amount of computational time to compute an HR image. Further, it can yield only a global dictionary D = [Dh;Dl] by jointly training the concatenated HR and LR image local patches, which results in no accurate correspondence between the HR and LR dictionaries. Therefore, we propose the generation of an HR image using a linear combination of several anchor points (codes) for a local patch based on locality-constrained linear coding (LLC), which is a fast implementation of local coordinate coding (LCC). In the proposed LLC-based strategy, each local patch is represented by a weighted linear combination of its nearer codes in a predefined codebook, and the linear weights become its local coordinate coding. Experimental results show that the recovered HR images with our proposed approach can achieve comparable performance at a processing time much shorter than those of conventional methods. [ABSTRACT FROM PUBLISHER]

Recent years have seen an increasing interest in codebook-based model(bag-of-words-BOW) for image representation, which includes the basic bag-of-words model and its improved version for local descriptor reconstruction with sparse coding (SC) and locality-constrained linear coding (LLC) etc. Although the recent coding strategies in the BoW model can lead to prospect performance using large amounts of codes (codebooks) for image classification, it is usually computational expensive for obtaining the global image representation through calculating the similarities between each local descriptor and all codes. Therefore, this study proposes to represent a local descriptor with an adaptive code or its variation modes (adaptive subdomain) in a small set of codebooks. The proposed strategy can adaptively select one code to saliently representation, or adaptively select one sub-domain of a code for group sparse reconstruction of a local descriptor. Due to computational cost mainly on the similarity calculation between local descriptors and the predefined codebooks, our proposed strategy using small set of codebook can greatly reduce computational time, and in addition, shows prospect performances for image classification on an scene database, called OM-RON scene dataset, and the benchmark data: 15 natural scene dataset. [ABSTRACT FROM PUBLISHER]

In clinical course of the chronic liver disease, the liver finally develops liver cirrhosis from the state of the chronic hepatitis. In the process, the patients are complicated with esophagogastric varices due to the portal hypertension and a hepatocellular carcinoma. It is very useful to be diagnosed using MDCT morphologically. A quantitative assessment has been tried from the CT images of the liver. A morphologic diagnosis of the chronic liver disease using the CT and a quantitative assessment are described in this article. [ABSTRACT FROM PUBLISHER]

In medical imaging, the data resolution is usually insufficient for accurate diagnosis in clinical medicine. Especially in most case, the resolution in the slice direction (Z direction) is much lower than that of the in-plane resolution (XY direction). Therefore it is difficult to construct isotropic voxels, which is very important in 3-D visualization systems, such as surgical system. In this paper, we propose a method for improving resolution in the slice direction for medical volume images based on Principal Component Regression (PCR), which can be considered as one of the learning based super-resolution techniques. The experimental results verify the effectiveness of the proposed method by comparison with the conventional interpolation methods. [ABSTRACT FROM PUBLISHER]

Recently, with the increasing of unhealthy diets and the attracted attention for healthy life, how to manage the dietary life is becoming more and more important. In this paper, we aim to construct a system, which can auto-recognize the menu contents from food image taken by mobile phone. As we know that the viewpoints can be varied in any direction when taking food images, and then, rotation-robust features for image representation are very important. Therefore, in this paper, we propose to extract rotation invariant features using circle-segmentation called SPIN for food recognition, and construct a Food-Log system, which records the contents of food menu, calories and nutritional value for management of the dietary life. [ABSTRACT FROM PUBLISHER]

Example-Based Super-Resolution is a learning-based technique that attempts to recover high-resolution (HR) image according to the corresponding relation in a set of training low-resolution (LR) and high-resolution image pairs prepared in advance. The conventional learning-based method for image super-resolution usually cannot achieve the high-frequency components accurately, which are lost in the input LR image, for recovering the HR image, since it only estimates the lost information using one most similar training LR patch to the input patch, and its corresponding HR pair. Therefore, we propose to use a manifold learning method- Locally Linear Embedding (LLE) for reconstructing the input LR patch with a linear weight summation of its several most similar training LR patches, and then can recover HR patch using the same linear summation of the corresponding training HR patches. Furthermore, in order to solve the expensive computational problem in the conventional exampled-based learning method, only the patches with larger variance, which means with high-frequency components, are selected for super-resolution procedures. Finally, Experimental results show that the recovered high-resolution images by our proposed approach are much better than those by conventional method and interpolation techniques. [ABSTRACT FROM PUBLISHER]