scholarly journals Rate-dependent seam carving and its application to content-aware image coding

2013 ◽  
Vol 2 ◽  
Author(s):  
Yuichi Tanaka ◽  
Taichi Yoshida ◽  
Madoka Hasegawa ◽  
Shigeo Kato ◽  
Masaaki Ikehara
Keyword(s):  
Computational Complexity ◽  
Image Coding ◽  
Side Information ◽  
Image Data ◽  
Seam Carving ◽  
Image Resizing ◽  
Rate Dependent ◽  
Coding Method ◽  
Content Aware ◽  
High Computational Complexity

Content-aware image resizing (CAIR) is desired because it preserves prominent regions in a resized image. However, CAIR requires high computational complexity to perform in mobile devices, though it is desired for these displays. Moreover, transmitting the side information for CAIR from the encoder is a problem since it usually requires high bitrates compared with those for image data. In this paper, we present a rate-dependent CAIR method that produce various retargeting results based on the bitrates for side information. Furthermore, we apply the proposed technique to wavelet-based image coding. Our proposed content-aware image coding method provides good performances for both CAIR and image coding.

Wavelet-based content-aware image coding with rate-dependent seam carving

2012 ◽  
Author(s):  
Taichi Yoshida ◽  
Yuichi Tanaka ◽  
Madoka Hasegawa ◽  
Shigeo Kato ◽  
Masaaki Ikehara
Keyword(s):  
Image Coding ◽  
Seam Carving ◽  
Rate Dependent ◽  
Content Aware

Detection of Content-Aware Image Resizing Using Seam Properties

2013 ◽  
Vol 284-287 ◽  
pp. 3074-3078 ◽  
Author(s):  
Seung Jin Ryu ◽  
Hae Yeoun Lee ◽  
Heung Kyu Lee
Keyword(s):  
Empirical Evidence ◽  
Superior Performance ◽  
Seam Carving ◽  
Large Database ◽  
Image Resizing ◽  
Image Content ◽  
Content Aware

Visually convincing content-aware image resizing, which preserves semantically important image content, has been actively researched in recent years. This paper proposes a resizing detector that reveals the trace of seam carving and seam insertion. To unveil the evidence of seam carving, we exploit energy bias of seam carved images. In addition, the correlation between adjacent pixels is analyzed to estimate the inserted seams. Empirical evidence from a large database of test images demonstrates the superior performance of the proposed detector under a variety of settings.

Detection of Content-Aware Image Resizing for Forensic Applications

2014 ◽  
Vol 6 (2) ◽  
pp. 23-39
Author(s):  
Guorui Sheng ◽  
Tiegang Gao ◽  
Shun Zhang
Keyword(s):  
Transition Probability ◽  
Transition Probability Matrix ◽  
Experimental Result ◽  
Seam Carving ◽  
Image Resizing ◽  
Markov Transition ◽  
Digital Image Forgery ◽  
Markov Features ◽  
Content Aware ◽  
Better Than

Seam-Carving is widely used for content-Aware image resizing. To cope with the digital image forgery caused by Seam-Carving, a new detecting algorithm based on Expanded Markov Feature (EMF) is presented. The algorithm takes full advantage of Transition Probability Matrix to represent correlation change caused by Seam-Carving operation. Different with traditional Markov features, the EMF not only reflects the change of correlation within the intra-DCT block, it also represents the change of correlation in more extensive range. The EMF is a fusion of traditional and expanded Markov Transition Probability Matrix. In the proposed algorithm, The EMF of normal image and that of forged image is trained by SVM, and thus the nornal image and forged image by Seam-Carving can be discriminated by SVM. The experimental result shows that the performance of proposed method is better than that of the method based on traditional Markov features and other existing methods

scholarly journals A Fast Sparse Coding Method for Image Classification

2019 ◽  
Vol 9 (3) ◽  
pp. 505 ◽  
Author(s):  
Mujun Zang ◽  
Dunwei Wen ◽  
Tong Liu ◽  
Hailin Zou ◽  
Chanjuan Liu
Keyword(s):  
Computational Complexity ◽  
Image Classification ◽  
Sparse Coding ◽  
Cluster Method ◽  
Spatial Pyramid Matching ◽  
Mutual Dependence ◽  
Coding Method ◽  
Pyramid Matching ◽  
Spatial Pyramid ◽  
High Computational Complexity

Image classification is an important problem in computer vision. The sparse coding spatial pyramid matching (ScSPM) framework is widely used in this field. However, the sparse coding cannot effectively handle very large training sets because of its high computational complexity, and ignoring the mutual dependence among local features results in highly variable sparse codes even for similar features. To overcome the shortcomings of previous sparse coding algorithm, we present an image classification method, which replaces the sparse dictionary with a stable dictionary learned via low computational complexity clustering, more specifically, a k-medoids cluster method optimized by k-means++. The proposed method can reduce the learning complexity and improve the feature’s stability. In the experiments, we compared the effectiveness of our method with the existing ScSPM method and its improved versions. We evaluated our approach on two diverse datasets: Caltech-101 and UIUC-Sports. The results show that our method can increase the accuracy of spatial pyramid matching, which suggests that our method is capable of improving performance of sparse coding features.

Video Splitting Based on Error-Distortion Computation Model

2012 ◽  
Vol 241-244 ◽  
pp. 3047-3052 ◽  
Author(s):  
Jin Xiang Peng ◽  
Jian Zhang ◽  
Wei Ming Yang
Keyword(s):  
Image Coding ◽  
Image Data ◽  
Video Object ◽  
2Nd Generation ◽  
Coding Scheme ◽  
Object Based ◽  
Coding Method ◽  
Development Direction ◽  
Image Data Compression ◽  
Machine Interaction

Various video compressed coding standards have been established with some differences broughtby buildersfollowing the requirements on the data of voice and image, and developed continuously subject to people’s demand of people. Now, video compressed coding research divides into two main directions: one is that DCT hybrid coding scheme based on tradition; the other is the coding scheme built from the objects put forward based on the 2nd generation image coding technology. The object-based coding method can actualize both the function that enlarges image data compression ratios and the man-machine interaction, giving our projection of the future video compressed coding development direction. In this paper, the object-based coding model selection algorithm is studied, and using the concepts of video object in MPEG-4, the method of splitting video is given.

scholarly journals Neural network used in Energy Function of Content-aware Image Resizing method to preserve skin color region

2019 ◽  
Author(s):  
Savio Rabelo ◽  
Tamara Pereira ◽  
Nivando Bezerra ◽  
Saulo Oliveira
Keyword(s):  
Neural Network ◽  
Human Skin ◽  
Energy Function ◽  
Skin Color ◽  
Visual Quality ◽  
Superior Performance ◽  
Seam Carving ◽  
Image Resizing ◽  
Original Algorithm ◽  
Content Aware

Seam Carving is a content-aware image resizing method capable of modifying the width or height of pictures. Such an algorithm applies an energy function to evaluate the importance of each pixel in the image. In exceptional cases, such as images that contain people, the method frequently presents deformation of objects due to the energy function not being able to detect a person. In this context, this paper presents a modification of the energy function used in seam carving by employing a neural network which can detect human skin patterns. Such a modification aims at better-preserving people in images. The experiments show that the proposed method achieves superior performance in terms of visual quality through qualitative indexes compared to the original algorithm.

Content-aware image resizing: An improved and shadow-preserving seam carving method

2019 ◽  
Vol 155 ◽  
pp. 233-246 ◽  
Author(s):  
Mahdi Hashemzadeh ◽  
Bahareh Asheghi ◽  
Nacer Farajzadeh
Keyword(s):  
Seam Carving ◽  
Image Resizing ◽  
Content Aware
Sign in / Sign up

Export Citation Format

Share Document