Improved Seam Merging for Content-Aware Image Resizing
スポンサーリンク
概要
- 論文の詳細を見る
In this paper, we propose an 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 energy terms associated with importance and structure. Our method preserve the main structures by using a cartoon version of the original image when calculating the structure energy. In addition, we introduce a new energy term to suppress the distortion generated by excessive reduction or enlargement in iterated merger or insertion. Experimental results demonstrate that the proposed method can produce satisfactory results in both image reduction and enlargement.
著者
-
Ikehara Masaaki
Department Of Electrical Engineering Keio University
-
YOSHITOME Takeshi
Department of Electrical and Electronic Engineering, Tottori University
-
MISHIBA Kazu
Department of Electrical and Electronic Engineering, Tottori University
関連論文
- Integer Discrete Cosine Transform via Lossless Walsh-Hadamard Transform with Structural Regularity for Low-Bit-Word-Length
- A Class of Near Shift-Invariant and Orientation-Selective Transform Based on Delay-Less Oversampled Even-Stacked Cosine-Modulated Filter Banks
- A Novel Design of Regular Cosine-Modulated Filter Banks for Image Coding
- A Bottom-Up Design Approach of Critically Sampled Contourlet Transform for Efficient Image Representation
- An efficient lifting structure of M-channel maximally decimated filter banks for lossless-to-lossy image coding (信号処理)
- An efficient lifting structure of M-channel maximally decimated filter banks for lossless-to-lossy image coding (VLSI設計技術)
- An efficient lifting structure of M-channel maximally decimated filter banks for lossless-to-lossy image coding (回路とシステム)
- M-Channel Paraunitary Filter Banks Based on Direct Lifting Structure of Building Block and Its Inverse Transform for Lossless-to-Lossy Image Coding
- Design of M-Channel Perfect Reconstruction Filter Banks with IIR-FIR Hybrid Building Blocks(Digital Signal Processing)
- Image Interpolation Using Edge-Directed Smoothness Measure Filter
- Fast LOT with Unequal Length Basis Functions : Realization and Application in Subband Image Coding
- A Simplified Lattice Structure of Two Dimensional Generalized Lapped Orthogonal Transform
- FOREWORD
- Digital Compensation Scheme for Coefficient Errors of Complex Filter Bank Parallel A/D Converter in Low-IF Receivers(Special Issue on Software Defined Radio Technology and Its Applications)
- Design and Lattice Structure of FIR Paraunitary Filter Banks with Linear Phase
- A Linear Optimization of Dual-Tree Complex Wavelet Transform
- Two Dimensional Non-separable Adaptive Directional Lifting Structure of Discrete Wavelet Transform
- Two Dimensional M-Channel Non-separable Filter Banks Based on Cosine Modulated Filter Banks with Diagonal Shifts
- Improved Seam Merging for Content-Aware Image Resizing
- Adaptive Reversible Data Hiding via Integer-to-Integer Subband Transform and Adaptive Generalized Difference Expansion Method
- Content Aware Image Resizing with Constraint of Object Aspect Ratio Preservation