Zhang Y.-L.,Zhejiang University of Technology |
Zhang Y.-L.,Key Laboratory of Visual Media Intelligent Processing Technology of Zhejiang Province |
Zhang W.,Zhejiang University of Technology |
Xiao G.,Zhejiang University of Technology |
And 3 more authors.
International Conference on Control, Automation and Systems | Year: 2012
Image segmentation is an important and classic problem in image processing and computer vision. Thresholding is applied to many fields, because of its less computation and stable performance. The key of thresholding method is to determine the adaptive threshold. In order to segment biological image effectively, a new adaptive thresholding method is proposed. First, two dimension minimum entropy is computed based on gray-gradient co-occurrence matrix; and then the genetic algorithm is applied to encode the two-dimension threshold vector; Finally, the optimum threshold is calculated based on fitness function and uniformity measurement(UM). Experimental results show that this method has three advantages: 1) improve computational efficiency so that it can run in real time; 2) retain more object and edge information so that it can meet the practical requirement; 3) robust to the uneven distribution of light. © 2012 ICROS.
Fan J.,Zhejiang University of Technology |
Fan J.,Key Laboratory of Visual Media Intelligent Processing Technology of Zhejiang Province |
Shi X.Y.,Zhejiang University of Technology |
Zhou Z.,Zhejiang University of Technology |
Tang Y.,Zhejiang University of Technology
Science China Information Sciences | Year: 2013
The framework of texture-by-numbers (TBN) synthesizes images of global-varying patterns with intuitive user control. Previous TBN synthesis methods have difficulties in achieving high-quality synthesis results and efficiency simultaneously. This paper proposes a fast TBN synthesis method based on texture optimization, which uses global optimization to solve the controllable non-homogeneous texture synthesis problem. Our algorithm produces high quality synthesis results by combining texture optimization into TBN framework with two improvements. The initialization process is adopted to generate the initial output of the global optimization algorithm, which speeds up the algorithm's convergence rate and enhances synthesis quality. Besides distance metrics to measure image similarities are specifically designed for different images to better match human visual perception for structural patterns and a user study is conducted to verify the effectiveness of the metrics. To further improve the synthesis speed, the algorithm is entirely implemented on GPU based on CUDA architecture. The optimized TBN method is applied to various visual applications including not only traditional TBN applications, but also image in-painting and texture-based flow visualization. The experimental results show that our method synthesizes images of higher or comparable qualities with higher efficiency than other state-of-art synthesis methods. © 2013 Science China Press and Springer-Verlag Berlin Heidelberg.
Liu S.,Zhejiang University of Technology |
Liu S.,Key Laboratory of Visual Media Intelligent Processing Technology of Zhejiang Province |
Jin H.,Zhejiang University of Technology |
Mao X.,Zhejiang University of Technology |
And 3 more authors.
The Scientific World Journal | Year: 2013
This paper proposes a segmentation-based global optimization method for depth estimation. Firstly, for obtaining accurate matching cost, the original local stereo matching approach based on self-adapting matching window is integrated with two matching cost optimization strategies aiming at handling both borders and occlusion regions. Secondly, we employ a comprehensive smooth term to satisfy diverse smoothness request in real scene. Thirdly, a selective segmentation term is used for enforcing the plane trend constraints selectively on the corresponding segments to further improve the accuracy of depth results from object level. Experiments on the Middlebury image pairs show that the proposed global optimization approach is considerably competitive with other state-of-the-art matching approaches. © 2013 Sheng Liu et al.
Mao J.-F.,Zhejiang University of Technology |
Mao J.-F.,Beijing University of Posts and Telecommunications |
Mao J.-F.,Key Laboratory of Visual Media Intelligent Processing Technology of Zhejiang Province |
Niu X.-X.,Beijing University of Posts and Telecommunications |
And 4 more authors.
Ruan Jian Xue Bao/Journal of Software | Year: 2014
Steganography payload is one of the four key performance indicators for information hiding. Previous research on information hiding has mainly focused on the other three performance indicators, namely, the robustness, transparency and computational complexity, with very few work being carried out regarding to the steganography payload. This research aims to effectively improve the theoretical system of information hiding. According to the JPEG2000 compression standard and the human eye sensitivity of changing wavelet coefficients, along with the aid of distortion cost function, the study discriminates the wavelet coefficients' carrying capacity of secret information: The smaller the distortion cost function value, the stronger the wavelet coefficients' carrying capacity. Conversely, the larger distortion cost function value, the weaker the wavelet coefficients' carrying capacity. When the distortion cost function value is greater than one, the coefficient will not have enough capacity to carry information, i.e., wet coefficients. By means of the maximum steganography payload experiments along with the bit full embedding, over bits embedding and wet embedding experiments, the effectiveness of the proposed estimation method in this work is verified. © 2014 ISCAS.
Qin X.,Zhejiang University of Technology |
Qin X.,Key Laboratory of Visual Media Intelligent Processing Technology of Zhejiang Province |
Wang H.,Zhejiang University of Technology |
Du Y.,Zhejiang University of Technology |
And 3 more authors.
Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of Computer-Aided Design and Computer Graphics | Year: 2013
In structured light geometry reconstruction, as the projecting modes and lighting conditions are complex and changeful, detail information in dark areas are usually lost in the result images. An improved Retinex algorithm are proposed based on HSV color space with color restoration and color saturation correction strategy. According to the requirement of color retain, the algorithm includes following steps. Firstly, an input color image is converted from RGB color space into HSV color space. Then the traditional multi-scale Retinex algorithm is applied only to V-component through the analysis of HSV color space model. At the same time, the coefficient of correlation is used to adaptively adjust the S-component base in the enhancement of V-component. Finally by transforming HSI model into RGB model, the enhanced color image with color restoration is obtained. Experimental results show that, the algorithm used in structured light stripe image enhancement, the color of the structured light image is maintained and the detail information is enhanced very well, which is more favorable to follow-up stripe information extraction and automatic coding.