Takamichi Miyata

Novel inverse colorization for image compression

Colorization is the process that restores colors on a grayscale image from user-generated color-assignation information. A novel approach to image compression has recently been proposed that extracts such color assignation from an input color image (we called this inverse colorization). Previous studies on inverse colorization have represented color assignation as a set of color points. However, in regions with flat color and fluctuating luminance, numerous color points are needed to correctly resore the color. Therefore, we propose a novel method of inverse colorization that represents color assignation in a more human-like manner - as a set of color line segments. To extract the minimum necessary line segments from an input image, iterative updating of tentative color assignation was introduced. The experimental results revealed that our proposed method can drastically suppress color information compared to either conventional inverse colorization or JPEG.

Colorization-based coding by focusing on characteristics of colorization bases

Colorization is a method that adds color components to a grayscale image using only a few representative pixels provided by the user. A novel approach to image compression called colorization-based coding has recently been proposed. It automatically extracts representative pixels from an original color image at an encoder and restores a full color image by using colorization at a decoder. However, previous studies on colorization-based coding extract redundant representative pixels and do not extract the pixels required for suppressing coding error. This paper focuses on the colorization basis that restricts the decoded color components. From this viewpoint, we propose a new colorization-based coding method. Experimental results revealed that our method can drastically suppress the information amount (number of representative pixels) compared conventional colorization based-coding while objective quality is maintained.

Vectorized total variation defined by weighted L infinity norm for utilizing inter channel dependency

Vectorized total variation (VTV) is very successful convex regularizer to solve various color image recovery problems. Despite the fact that color channels of natural color images are closely related, existing variants of VTV can not utilize this prior efficiently. We proposed L∞-VTV as a convex regularizer can penalize the violation of such inter-channel dependency by employing weighted L∞ (L-infty) norm. We also introduce an effective algorithm for an image denoising problem using L∞-VTV. Experimental results shows that our proposed method can outperform the conventional methods.

Missing region recovery by promoting blockwise low-rankness

In this paper, we propose a novel missing region recovery method by promoting blockwise low-rankness. It is natural to assume that images often have local repetitive structures. Hence, any small block extracted from an image is expected to be a low-rank matrix. Based on this assumption, we formulate missing region recovery as a convex optimization problem via newly introduced block nuclear norm which promotes blockwise low-rankness of an image with missing regions. An iterative scheme for approximating a global minimizer of the problem is also presented. The scheme is based on the alternating direction method of multipliers (ADMM) and allows us to restore missing regions efficiently. Experimental results reveal that the proposed method can recover missing regions with detailed local structures.

Evaluation model considering static-temporal quality degradation and human memory for SSCQE video quality

To perform Quality of Service (QoS) control of video communication more efficiently, it is necessary to develop an objective quality evaluation method for coded video. Many proposed conventional methods to obtain video quality require the availability of both reference and processed video sequence. However, in case of re-encoding the coded video stream at the receiver side where reference video sequence is not present, it is impossible to do such a full-reference evaluation. Therefore, we have developed a video quality evaluation model by using reduced reference for evaluated value obtained by SSCQE method. In this approach, we use some features extracted from reference video. It is called reduced-reference method by VQEG. Transmitting these features with coded video, the proposed model can estimate the video quality, even in the absent of the full original video in the decoder side. The video quality rating obtained from the proposed model shows good agreement with subjective quality.

Total variation-wavelet-curvelet regularized optimization for image restoration

Solving image restoration problems requires the use of efficient regularization terms that represent certain features of the original image. Natural images generally have three features: smooth regions, textures, and edges. However, conventional optimization techniques typically adopt only one or two reg-ularization terms, and there is no regularized optimization problem that represents such features exactly and completely. By applying three regularization terms corresponding to these three features, we can restore images more efficiently in ill-posed conditions. We propose here total variation (TV), wavelet, and curvelet regularized optimization for image restoration. These regularization terms correspond exactly to the smooth region, textures, and edges. We also present an algorithm to solve the proposed optimization problem, and ensure its convergence. Experimental results revealed that our optimization technique was more effective for image restoration than conventional methods.

L infinity total generalized variation for color image recovery

For solving color image recovery problems, we previously proposed an L∞ vectorial total variation (L∞-VTV) as a regularization term considering the inter color channel dependency. However, the result images suffer from pseudo contours known as staircasing effect. For suppressing this, Bredies et al. proposed to add higher-order derivative terms to VTV. However, since it does not consider the inter channel dependency properly, it cannot reduce pseudo color noises on the edge regions. Based on these observations, we proposed a new convex regularization term L∞ vectorial total generalized variation (L∞-VTGV) by combining two ideas: using L∞ norm for penalizing the violation of the inter color channel dependency and introducing higher order derivative term. Furthermore, we address the effective numerical algorithm for various image recovery problems using L∞-VTGV as a regularization term. Experimental results shows that our proposed method can outperform the conventional methods.

Maximum-Bandwidth ALM Tree on Tree Network

It is important to use an ALM (application layer multicast) tree with broad bandwidth to ensure the quality of streaming applications. However, when constructing an ALM tree without information on underlay traffic, we cannot know how much congestion there is in links. Therefore, if unexpected congestion in links occurs, the quality of ALM transmissions may worsen. However, no polynomial-time algorithms for constructing maximum-bandwidth ALM trees with information on underlay traffic exist. We regarded an underlay network as a tree network topology in our previous work, and presented a polynomial-time algorithm that was used to construct a maximum-bandwidth ALM tree. We also proved that we could obtain an optimal ALM tree. However, we had not yet evaluated our algorithm by simulation. Here, we discuss our evaluation of the algorithm we propose and a conventional one. We found our algorithm could achieve a broader bandwidth ALM tree at lower computational cost, especially in large networks.

Luminance constrained total variation and its application for optimized decoding of JPEG 2000

We propose a new semi-norm named luminance constrained total variation (LCTV) to utilize a correlation and an imbalance of information amounts between luminance and chrominance for solving image recovery problems. As an example of LCTV application, we also propose a method for restoring chrominance components of JPEG 2000 compressed images. We cast this method into an ℓ1 (LCTV)-ℓ2 combined optimization problem. The algorithm to solve this optimization problem by using variable splitting is also proposed and its convergence is confirmed. Experimental results show our proposed optimized decoding method outperforms the existing state-of-the-art denoising methods.

Proof of optimal algorithm for maximum-bandwidth ALM tree construction

We construct an ALM (application layer multicast) tree that achieves the maximum bandwidth by using underlay traffic information. Since this problem was previously shown to be NP-hard, no polynomial-time algorithms for maximum-bandwidth ALM tree construction exist. In our work, we assume that the underlay network has a tree network topology, and we show a polynomial-time algorithm that constructs a maximum-bandwidth ALM tree on such a tree network topology. We propose an ALM tree construction algorithm that achieves bandwidth b and apply this algorithm with various bandwidth values b. We show that it can make a maximum-bandwidth ALM tree in polynomial time.