Kazu Mishiba

Seam merging for image resizing with structure preservation

In image resizing process, preserving structure on an image is important to produce plausible results. We proposed seam merging, a seam-carving-based image resizing method, and a new energy criterion for structure preservation. Seam merging reduces the size of an image by merging a two-pixel-width seam into a one-pixel width seam. To find the optimal seam that minimizes structural distortion after merging, we introduce an energy function which has a large value when the merging breaks the structure. We further show the way to find the optimal seam using dynamic programming. Experimental results demonstrate that our proposal algorithm can produce fewer artifacts and successfully preserve structure.

Edge-adaptive image interpolation using constrained least squares

Some adaptive image interpolation methods have been proposed to create higher visual quality images than traditional interpolation methods such as bicubic interpolation. These methods, however, often suffer from high computational costs and unnatural texture interpolation. This paper proposes a novel edge-adaptive image interpolation method using an edge-directed smoothness filter. Our approach estimates the enlarged image from the original image based on an observation model. The estimated image is constrained to have many edge-directed smooth pixels which are measured by using the edge-directed smoothness filter introduced in this paper. Simulation results show that the proposal method produces images with higher visual quality, higher PSNRs and faster computational times than the conventional methods.

Block-based seam carving

Content aware image resizing technique has become more important with the development of device technology. Although the seam carving method produces high-quality resized images, it requires high computational complexity. In this paper, we propose a block-based seam carving method, which is extended from the seam carving method. In our method, a seam element is a pixel block, and a seam is a path of blocks. The blocks on a seam are downsampled in the step of image shrinking. Our method creates resized images with less distortion and runs faster than seam carving. In addition, we present an image magnification technique with our method. Unlike the seam carving method, our technique defines the optimal seam for enlargement. Simulation results show the advantage of our method over seam carving method.

Image resizing using improved seam merging

In this paper, we propose the improved seam merging method for content-aware image resizing. This method merges a two-pixel-width seam element into one new pixel in image reduction and inserts a new pixel between the two pixels in image enlargement. To preserve important contents and structure, our method uses importance and structure energies. Using the cartoon image of an original image for calculation of structure energy, our method can preserve main structure. In addition, we introduce new energy to suppress distortion generated by excessive reduction or enlargement in the iterative merging or inserting. Experimental results demonstrate that the proposed method can produce satisfactory results in both image reduction and enlargement.

Quadrilateral Remeshing with Global Alignment

In this paper, we propose a new remeshing algorithm that captures the global structure of an object for 3D editing. The resulting meshes are quadrilateral, are of global alignment and have a multi-resolution structure. Additionally, their low-resolution mesh shows object features with a few vertices. Our algorithm is summarized as follows. First, a 3D object is converted into voxels, and then the object skeleton is computed. Next, the initial mesh is obtained from the skeleton. Finally, the remeshed object is yielded by moving vertices on the mesh to the voxel boundary. We show experimental results of remeshing some objects to validate the proposed algorithm.