The sparse representation models have been widely applied in image super-resolution. The certain optimization problem is supposed and can be solved by the iterative shrinkage algorithm. During iteration, the update of dictionaries and similar patches is necessary to obtain prior knowledge to better solve such ill-conditioned problem as image super-resolution. However, both the processes of iteration and update often spend a lot of time, which will be a bottleneck in practice. To solve it, in this paper, we present the concept of image quality difference based on generalized Gaussian distribution feature which has the same trend with the variation of Peak Signal to Noise Ratio (PSNR), and we update dictionaries or similar patches from the termination strategy according to the adaptive threshold of the image quality difference. Based on this point, we present two sparse representation algorithms for image super-resolution, one achieves the further improvement in image quality and the other decreases running time on the basis of image quality assurance. Experimental results also show that our quantitative results on several test datasets are in line with exceptions.

Within information hiding technology, digital watermarking is one of the most important technologies for copyright protection of digital content. Many digital watermarking schemes have been proposed in academia. However, these schemes are not used, because they are not practical; one reason for this is that the evaluation criteria are loosely defined. To make the evaluation more concrete and improve the practicality of digital watermarking, watermarking schemes must use common evaluation criteria. To realize such criteria, we organized the Information Hiding and its Criteria for Evaluation (IHC) Committee to create useful, globally accepted evaluation criteria for information hiding technology. The IHC Committee improves their evaluation criteria every year, and holds a competition for digital watermarking based on state-of-the-art evaluation criteria. In this paper, we describe the activities of the IHC Committee and its evaluation criteria for digital watermarking of still images, videos, and audio.

This paper deals with the diffraction of a monochromatic plane wave by a periodic grating. We discuss a problem how to obtain a numerical diffraction efficiency (NDE) satisfying the reciprocity theorem for diffraction efficiencies, because diffraction efficiencies are the subject of the diffraction theories. First, this paper introduces a new formula that decomposes an NDE into two components: the even component and the odd one. The former satisfies the reciprocity theorem for diffraction efficiencies, but the latter does not. Therefore, the even component of an NDE becomes an answer to our problem. On the other hand, the odd component of an NDE represents an unwanted error. Using such the decomposition formula, we then obtain another new formula that decomposes the conventional energy error into two components. One is the energy error made by even components of NDE's. The other is the energy error constructed by unwanted odd ones and it may be used as a reciprocity criterion of a numerical solution. This decomposition formula shows a drawback of the conventional energy balance. The total energy error is newly introduced as a more strict condition for a desirable solution. We point out theoretically that the reciprocal wave solution, an approximate solution satisfying the reciprocity for wave fields, gives another solution to our problem. Numerical examples are given for the diffraction of a TM plane wave by a very rough periodic surface with perfect conductivity. In the case of a numerical solution by the image integral equation of the second kind, we found that the energy error is much reduced by use of the even component of an NDE as an approximate diffraction efficiency or by use of a reciprocal wave solution.

In this paper, an analysis of the basic process of a class of interactive-graph-cut-based image segmentation algorithms indicates that it is unnecessary to construct n-links for all adjacent pixel nodes of an image before calculating the maximum flow and the minimal cuts. There are many pixel nodes for which it is not necessary to construct n-links at all. Based on this, we propose a new algorithm for the dynamic construction of all necessary n-links that connect the pixel nodes explored by the maximum flow algorithm. These n-links are constructed dynamically and without redundancy during the process of calculating the maximum flow. The Berkeley segmentation dataset benchmark is used to prove that this method can reduce the average running time of segmentation algorithms on the premise of correct segmentation results. This improvement can also be applied to any segmentation algorithm based on graph cuts.

Light-field image processing has been widely employed in many areas, from mobile devices to manufacturing applications. The fundamental process to extract the usable information requires significant computation with high-resolution raw image data. A graphics processing unit (GPU) is used to exploit the data parallelism as in general image processing applications. However, the sparse memory access pattern of the applications reduced the performance of GPU devices for both systematic and algorithmic reasons. Thus, we propose an optimization technique which redesigns the memory access pattern of the applications to alleviate the memory bottleneck of rendering application and to increase the data reusability for depth extraction application. We evaluated our optimized implementations with the state-of-the-art algorithm implementations on several GPUs where all implementations were optimally configured for each specific device. Our proposed optimization increased the performance of rendering application on GTX-780 GPU by 30% and depth extraction application on GTX-780 and GTX-980 GPUs by 82% and 18%, respectively, compared with the original implementations.

The privacy of users' data has become a big issue for cloud service. This research focuses on image cloud database and the function of similarity search. To enhance security for such database, we propose a framework of privacy-enhanced search scheme, while all the images in the database are encrypted, and similarity image search is still supported.

Inter-person occlusion handling is a critical issue in the field of tracking, and it has been extensively researched. Several state-of-the-art methods have been proposed, such as focusing on the appearance of the targets or utilizing knowledge of the scene. In contrast with the approaches proposed in the literature, we propose to address this issue using a social interaction model, which allows us to explore spatio-temporal information pertaining to the targets involved in the occlusion situation. Our experimental results show promising results compared with those obtained using other methods.

This paper proposes a Bayesian approach to image recognition based on separable lattice hidden Markov models (SL-HMMs). The geometric variations of the object to be recognized, e.g., size, location, and rotation, are an essential problem in image recognition. SL-HMMs, which have been proposed to reduce the effect of geometric variations, can perform elastic matching both horizontally and vertically. This makes it possible to model not only invariances to the size and location of the object but also nonlinear warping in both dimensions. The maximum likelihood (ML) method has been used in training SL-HMMs. However, in some image recognition tasks, it is difficult to acquire sufficient training data, and the ML method suffers from the over-fitting problem when there is insufficient training data. This study aims to accurately estimate SL-HMMs using the maximum a posteriori (MAP) and variational Bayesian (VB) methods. The MAP and VB methods can utilize prior distributions representing useful prior information, and the VB method is expected to obtain high generalization ability by marginalization of model parameters. Furthermore, to overcome the local maximum problem in the MAP and VB methods, the deterministic annealing expectation maximization algorithm is applied for training SL-HMMs. Face recognition experiments performed on the XM2VTS database indicated that the proposed method offers significantly improved image recognition performance. Additionally, comparative experiment results showed that the proposed method was more robust to geometric variations than convolutional neural networks.

Automatic detection of immunoreactive areas in fluorescence microscopic images is becoming a key technique in the field of biology including neuroscience, although it is still challenging because of several reasons such as low signal-to-noise ratio and contrast variation within an image. In this study, we developed a new algorithm that exhaustively detects co-localized areas in multi-channel fluorescence images, where shapes of target objects may differ among channels. Different adaptive binarization thresholds for different local regions in different channels are introduced and the condition of each segment is assessed to recognize the target objects. The proposed method was applied to detect immunoreactive spots that labeled membrane receptors on dendritic spines of mouse cerebellar Purkinje cells. Our method achieved the best detection performance over five pre-existing methods.

In general, in-focus images are used in visual object detection because image blur is considered as a factor reducing detection accuracy. However, in-focus images make it difficult to separate target objects from background images, because of that, visual object detection becomes a hard task. Background subtraction and inter-frame difference are famous schemes for separating target objects from background but they have a critical disadvantage that they cannot be used if illumination changes or the point of view moves. Considering these problems, the authors aim to improve detection accuracy by using images with out-of-focus blur obtained from a camera with a shallow depth of field. In these images, it is expected that target objects become in-focus and other regions are blurred. To enable visual object detection based on such image blur, this paper proposes a novel scheme using DFT-based feature extraction. The experimental results using synthetic images including, circle, star, and square objects as targets showed that a classifier constructed by the proposed scheme showed 2.40% miss rate at 0.1 FPPI and perfect detection has been achieved for detection of star and square objects. In addition, the proposed scheme achieved perfect detection of humans in natural images when the upper half of the human body was trained. The accuracy of the proposed scheme is better than the Filtered Channel Features, one of the state-of-the-art schemes for visual object detection. Analyzing the result, it is convincing that the proposed scheme is very feasible for visual object detection based on image blur.

In this paper, we propose an improved method of embedding and detecting data in a printed image using a camera of a mobile device. The proposed method is based on the data diffusion method. We discuss several problems in the conventional lens distortion correction method. In addition, the possibility of using multiple captured images by employing a motion-image-capturing technique is also examined. A method of selecting captured images that are expected to obtain a high detection rate is also proposed. From the experimental results, it is shown that the proposed method is effective for improving data detection.

In this paper, we aim to investigate the potential usefulness of machine learning in image quality assessment (IQA). Most previous studies have focused on designing effective image quality metrics (IQMs), and significant advances have been made in the development of IQMs over the last decade. Here, our goal is to improve prediction outcomes of “any” given image quality metric. We call this the “IQM's Outcome Improvement” problem, in order to distinguish the proposed approach from the existing IQA approaches. We propose a method that focuses on the underlying IQM and improves its prediction results by using machine learning techniques. Extensive experiments have been conducted on three different publicly available image databases. Particularly, through both 1) in-database and 2) cross-database validations, the generality and technological feasibility (in real-world applications) of our machine-learning-based algorithm have been evaluated. Our results demonstrate that the proposed framework improves prediction outcomes of various existing commonly used IQMs (e.g., MSE, PSNR, SSIM-based IQMs, etc.) in terms of not only prediction accuracy, but also prediction monotonicity.

A number of successful tone mapping operators (TMOs) for contrast compression have been proposed due to the need to visualize high dynamic range (HDR) images on low dynamic range devices. This paper proposes a novel inverse tone mapping (TM) operation and a new remapping framework with the operation. Existing inverse TM operations require either the store of some parameters calculated in forward TM, or data-depended operations. The proposed inverse TM operation enables to estimate HDR images from LDR ones mapped by the Reinhard's global operator, not only without keeping any parameters but also without any data-depended calculation. The proposed remapping framework with the inverse operation consists of two TM operations. The first TM operation is carried out by the Reinhard's global operator, and then the generated LDR one is stored. When we want different quality LDR ones, the proposed inverse TM operation is applied to the stored LDR one to generate an HDR one, and the second TM operation is applied to the HDR one to generate an LDR one with desirable quality, by using an arbitrary TMO. This framework allows not only to visualize an HDR image on low dynamic range devices at low computing cost, but also to efficiently store an HDR one as an LDR one. In simulations, it is shown that the proposed inverse TM operation has low computational cost, compared to the conventional ones. Furthermore, it is confirmed that the proposed framework allows to remap the stored LDR one to another LDR one whose quality is the same as that of the LDR one remapped by the conventional inverse TMO with parameters.

In this paper, we propose a digital image enlargement method based on a fuzzy technique that improves half-pixel generation, especially for convex and concave signals. The proposed method is a modified version of the image enlargement scheme previously proposed by the authors, which achieves accurate half-pixel interpolation and enlarges the original image by convolution with the Lanczos function. However, the method causes impulse-like artifacts in the enlarged image. In this paper, therefore, we introduce a fuzzy set and fuzzy rule for generating half-pixels to improve the interpolation of convex and concave signals. Experimental results demonstrate that, in terms of image quality, the proposed method shows superior performance compared to bicubic interpolation and our previous method.

A secure identification scheme for JPEG images is proposed in this paper. The aim is to robustly identify JPEG images which are generated from the same original image under various compression levels in security. A property of the positive and negative signs of DCT coefficients is employed to achieve a robust scheme. The proposed scheme is robust against a difference in compression levels, and does not produce false negative matches in any compression level. Conventional schemes that have this property are not secure. To construct a secure identification system, we combine a new error correction technique with 1-bit parity with a fuzzy commitment scheme, which is a well-known biometric cryptosystem. In addition, a way for speeding up the identification is also proposed. The experimental results show the proposed scheme is effective for not only still images, but also video sequences in terms of the querying such as false positive, false negative and true positive matches, while keeping a high level of the security.

Protanopes and deuteranopes are difficult to distinguish some color pairs. In this letter, a new lightness modification method which considers the Craik-O'Brien effect is proposed. The lightness modification is performed at parts which are difficult to distinguish in the protanopia or deuteranopia. Experiments show the validity of the proposed method.

Encoding multiple SIFT descriptors into a single vector is a key technique for efficient object image retrieval. In this paper, we propose an extension of local coordinate system (LCS) for image representation. The previous LCS approaches encode each SIFT descriptor by a single local coordinate, which is not adequate for localizing its position in the descriptor space. Instead, we use multiple local coordinates to represent each descriptor with PCA-based decorrelation. Experiments show that this simple modification can improve retrieval performance significantly.

The dark channel prior (DCP)-based image dehazing method has been widely used for enhancing visibility of outdoor images. However, since the DCP-based method assumes that the minimum values within local patches of natural outdoor haze-free images are zero, underestimation of the transmission is inevitable when the assumption does not hold. In this letter, a novel iterative image dehazing algorithm is proposed to compensate for the underestimated transmission. Experimental results show that the proposed method can improve the dehazing performance by increasing the transmission estimation accuracy.

We propose an edge-preserving multiscale image decomposition method using filters for non-equispaced signals. It is inspired by the domain transform, which is a high-speed edge-preserving smoothing method, and it can be used in many image processing applications. One of the disadvantages of the domain transform is sensitivity to noise. Even though the proposed method is based on non-equispaced filters similar to the domain transform, it is robust to noise since it employs a multiscale decomposition. It uses the Laplacian pyramid scheme to decompose an input signal into the piecewise-smooth components and detail components. We design the filters by using an optimization based on edge-preserving smoothing with a conversion of signal distances and filters taking into account the distances between signal intervals. In addition, we also propose construction methods of filters for non-equispaced signals by using arbitrary continuous filters or graph spectral filters in order that various filters can be accommodated by the proposed method. As expected, we find that, similar to state-of-the-art edge-preserving smoothing techniques, including the domain transform, our approach can be used in many applications. We evaluated its effectiveness in edge-preserving smoothing of noise-free and noisy images, detail enhancement, pencil drawing, and stylization.

In this letter, a local characteristic image restoration based on convolutional neural network is proposed. In this method, image restoration is considered as a classification problem and images are divided into several sub-blocks. The convolutional neural network is used to extract and classify the local characteristics of image sub-blocks, and the different forms of the regularization constraints are adopted for the different local characteristics. Experiments show that the image restoration results by the regularization method based on local characteristics are superior to those by the traditional regularization methods and this method also has lower computing cost.