SKSeisuke Kyochi

Seisuke Kyochi

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Seisuke Kyochi has a total of 17 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • A Design of Denser-Graph-Frequency Graph Fourier Frames for Graph Signal Analysis

    by Kaito Nitani, Seisuke Kyochi

    This paper introduces a design method for densergraph-frequency graph Fourier frames (DGFFs) to enhance graph signal processing and analysis. The graph Fourier transform (GFT) enables us to analyze graph signals in the graph spectral domain and facilitates various graph signal processing tasks, such as filtering, sampling and reconstruction, denoising, and so on. However, the conventional GFT faces two significant limitations. First, unlike the discrete Fourier transform and its variants (such as discrete cosine transforms), the graph frequencies of the derived graph Fourier basis (GFB) from a given graph tend to be unevenly distributed or localized, which leads to biased spectral analysis. Second, the GFB used in GFT does not provide an efficient sparse representation of graph signals compared to overcomplete systems like frames. To overcome these challenges, we propose adding oscillating vectors with intermediate graph frequencies between the original vectors in the GFB for both undirected and directed graphs, constructing GFFs with densergraph frequencies. The resulting DGFFs are expected to enable more accurate graph signal analysis. Furthermore, we propose a graph filtering method based on the DGFFs. In experiments, we apply the DGFFs to practical applications such as graph signal recovery, demonstrating superior performance compared to existing GFBs.

  • Sparsity-Enhanced Multilayered Non-Convex Regularization With Epigraphical Relaxation for Debiased Signal Recovery

    by Akari Katsuma, Seisuke Kyochi, Shunsuke Ono, Ivan Selesnick

    This paper proposes a precise signal recovery method utilizing a composition of multiple non-convex regularization functions, termed multilayered non-convex regularization functions, to enhance sparsity and low-rankness in high-dimensional signals, including images and videos. In optimization-based signal recovery, multilayered convex regularization functions based on the l1 and nuclear norms not only guarantee a globally optimal solution but also improve estimation accuracy over single-layered ones by effectively modeling structured sparsity and low-rankness across various domains, such as spatial, spectral, and temporal domains. However, they often yield biased solutions with underestimated amplitudes. To address this underestimation, multilayered non-convex regularization functions have been explored but face challenges: 1) their closed-form proximity operators are often unavailable, and 2) convergence may lead to local optima. To overcome these issues, we propose the ER-LiGME model, which integrates epigraphical relaxation (ER) with the linearly-involved generalized Moreau-enhanced (LiGME) model. ER decomposes a multilayered composite function into its outermost function and epigraph constraints, facilitating proximity operator computation. Meanwhile, the LiGME model transforms convex regularization functions into non-convex ones while preserving convexity of the optimization model. By leveraging ER to reformulate multilayered convex regularization functions and integrating the LiGME model, the proposed approach provides a framework for diverse multilayered non-convex regularization functions that ensure global optimality, reducing bias and high-accuracy of high-dimensional signal recovery. Numerical experiments demonstrate the proposed method’s effectiveness in image recovery and principal component analysis.


  • Regularity-Constrained Fast Sine Transforms

    by Taizo Suzuki, Seisuke Kyochi, Yuichi Tanaka

    This letter proposes a fast implementation of the regularity-constrained discrete sine transform (R-DST). The original DST leaks the lowest frequency (DC: direct current) components of signals into high frequency (AC: alternating current) subbands. This property is not desired in many applications, particularly image processing, since most of the frequency components in natural images concentrate in DC subband. The characteristic of filter banks whereby they do not leak DC components into the AC subbands is called regularity. While an R-DST has been proposed, it has no fast implementation because of the singular value decomposition (SVD) in its internal algorithm. In contrast, the proposed regularity-constrained fast sine transform (R-FST) is obtained by just appending a regularity constraint matrix as a postprocessing of the original DST. When the DST size is $M\times M$ ($M=2^\ell$, $\ell \in \mathbb {N}_{\geq 1}$), the regularity constraint matrix is constructed from only $M/2-1$ rotation matrices with the angles derived from the output of the DST for the constant-valued signal (i.e., the DC signal). Since it does not require SVD, the computation is simpler and faster than the R-DST while keeping all of its beneficial properties. An image processing example shows that the R-FST has fine frequency selectivity with no DC leakage and higher coding gain than the original DST. Also, in the case of $M=8$, the R-FST saved approximately $0.126$ seconds in a 2-D transformation of $512\times 512$ signals compared with the R-DST because of fewer extra operations.

  • Open Access

    Directional Analytic Discrete Cosine Frames

    by Seisuke Kyochi, Taizo Suzuki, Yuichi Tanaka

    Block frames called directional analytic discrete cosine frames (DADCFs) are proposed for sparse image representation. In contrast to conventional overlapped frames, the proposed DADCFs require a reduced amount of 1) computational complexity, 2) memory usage, and 3) global memory access. These characteristics are strongly required for current high-resolution image processing. Specifically, we propose two DADCFs based on discrete cosine transform (DCT) and discrete sine transform (DST). The first DADCF is constructed from parallel separable transforms of DCT and DST, where the DST is permuted by row. The second DADCF is also designed based on DCT and DST, while the DST is customized to have no DC leakage property which is a desirable property for image processing. Both DADCFs have rich directional selectivity with slightly different characteristics each other and they can be implemented as non-overlapping block-based transforms, especially they form Parseval block frames with low transform redundancy. We perform experiments to evaluate our DADCFs and compare them with conventional directional block transforms in image recovery.


  • Epigraphical Relaxation for Minimizing Layered Mixed Norms

    by Seisuke Kyochi, Shunsuke Ono, Ivan Selesnick

    This paper proposes an epigraphical relaxation (ERx) technique for non-proximable mixed norm minimization. Mixed norm regularization methods play a central role in signal reconstruction and processing, where their optimization relies on the fact that the proximity operators of the mixed norms can be computed efficiently. To bring out the power of regularization, sophisticated layered modeling of mixed norms that can capture inherent signal structure is a key ingredient, but the proximity operator of such a mixed norm is often unavailable (non-proximable). Our ERx decouples a layered non-proximable mixed norm into a norm and multiple epigraphical constraints. This enables us to handle a wide range of non-proximable mixed norms in optimization, as long as both the proximal operator of the outermost norm and the projection onto each epigraphical constraint are efficiently computable. Moreover, under mild conditions, we prove that ERx does not change the minimizer of the original problem despite relaxing equality constraints into inequality ones. We also develop new regularizers based on ERx:one is decorrelated structure-tensor total variation for color image restoration, and the other is amplitude-spectrum nuclear norm for low-rank amplitude recovery. We examine the power of these regularizers through experiments, which illustrates the utility of ERx.


  • Open Access

    Sound Event Detection Using Graph Laplacian Regularization Based on Event Co-occurrence

    by Keisuke Imoto, Seisuke Kyochi

    The types of sound events that occur in a situation are limited, and some sound events are likely to co-occur; for instance, "dishes" and "glass jingling." In this paper, we propose a technique of sound event detection utilizing graph Laplacian regularization taking the sound event co-occurrence into account. In the proposed method, sound event occurrences are represented as a graph whose nodes indicate the frequency of event occurrence and whose edges indicate the co-occurrence of sound events. This graph representation is then utilized for sound event modeling, which is optimized under an objective function with a regularization term considering the graph structure. Experimental results obtained using TUT Sound Events 2016 development, 2017 development, and TUT Acoustic Scenes 2016 development indicate that the proposed method improves the detection performance of sound events by 7.9 percentage points compared to that of the conventional CNN-BiGRU-based method in terms of the segment-based F1-score. Moreover, the results show that the proposed method can detect co-occurring sound events more accurately than the conventional method.


  • Universal Approach for DCT-Based Constant-Time Gaussian Filter with Moment Preservation

    by Kenjiro Sugimoto, Seisuke Kyochi, Sei-Ichiro Kamata

    This paper presents a universal approach for constant-time Gaussian filters (O(1) GF) based on the Discrete Cosine Transform (DCT). It is well known that DCT has the eight types of definitions. Existing methods of O(1) GF use difference DCT type according to their original concepts. However, all types of DCT have not been studied comprehensively and quantitatively. Unlike existing methods, the proposed approach covers all types of DCT and moment preservation for arbitrary orders, which enables us to clarify differences of O(1) GF derived from each DCT through a comprehensive analysis. Based on the universal approach, a closed-form solution to optimize weight coefficients is also proposed based on a simple convex analysis. Experiments found that DCT-7 shows the highest approximate accuracy, which is a new conclusion different from existing methods.


  • Open Access

    Joint Sparsity and Order Optimization Based on ADMM With Non-Uniform Group Hard Thresholding

    by Ryo Matsuoka, Seisuke Kyochi, Shunsuke Ono, Masahiro Okuda

    This paper proposes a new optimization framework for the joint optimization of sparsity and filter order (JOSFO) for FIR filter design. Since the cost function for JOSFO involves ℓ 0 and non-uniform overlapped group ℓ 0 norms, which are not convex, a global optimal solution is difficult to obtain. To find an approximate solution of the non-convex problem, existing approaches repeat the following steps: 1) approximate the cost function; 2) find candidates of zero coefficients by minimizing the cost function; and 3) set them to zero. On the other hand, this paper directly solves the optimization problem, without any approximation to the cost function, by using the alternating direction method of multipliers with the pseudo-proximity operators of ℓ 0 and non-uniform non-overlapped group ℓ 0 norms. Experimental results show that resulting filters designed by the proposed method have sparser coefficients and lower orders, while satisfying filter specifications, such as an error from a desired frequency response.


  • Image Boundary Extension With Mean Value for Cosine–Sine Modulated Lapped/Block Transforms

    by Ryoma Ishibashi, Taizo Suzuki, Seisuke Kyochi, Hiroyuki Kudo

    We present a novel image boundary extension, mean value extension (MVE), for directional lapped transforms, particularly cosine-sine modulated lapped transforms (CSMLTs). Lapped transforms are usually used with an extension technique, such as periodic extension (PE) or symmetric extension (SE), for nonexpansive convolution at signal boundaries. When directional textures (oblique lines and curves) appear at the 2D signal (image) boundaries, both PE and SE produce directional discontinuities, which degrade the sparsity of the transformed coefficients, especially in the case of directional lapped transforms. MVE reduces the discontinuities for directional textures better than PE or SE do; it thus improves the efficiency of the sparse representation based on directional lapped transforms. Moreover, to reduce computational costs compared with those of directional lapped transforms, we introduce new directional block transforms, called cosine-sine modulated block transforms (CSMBTs). These new transforms are derived from a minimum tile processing (tiling) of M-band CSMLTs with 2M filter lengths and nonexpansive convolutions. The resulting directional block transforms, particularly in the case of the MVE, have richer directional selectivity and have higher performance compared with a discrete Fourier transform (DFT) as shown in experiments.


  • Directional discrete cosine transforms arising from discrete cosine and sine transforms for directional block-wise image representation

    by Tomohiro Ichita, Seisuke Kyochi, Taizo Suzuki, Yuichi Tanaka

    Directional block transforms (DBTs), such as discrete Fourier transforms, are basically less efficient for sparse image representation than directional overlapped transforms, such as curvelet and contourlet, but have advantages in practical computation, such as less computational cost, less amount of memory usage to be used, and parallel processing. In order to realize efficient DBTs, this paper proposes directional discrete cosine transforms (DDCTs) by using discrete cosine and sine transforms. The resulting transforms provide richer directional orientations of atoms than conventional DBTs, and thus they are expected to be more efficient for image analysis and processing. In experiments, we evaluate DDCTs with conventional DBTs in image recovery by a convex optimization.