Kaihua Zhang

Prof. Kaihua Zhang

School of Computer Science, Nanjing University of Information Science and Technology, Nanjing, China
orcid

Research Focus & Metrics

Academic Career Length

17Years (2010-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 April 2010 in Pattern Recognition
Verified
Journal Article
Closed access
Kaihua ZhangKaihua Zhang
Kaihua Zhang
HSHuihui Song
Huihui Song
LZLei Zhang
Lei Zhang

1 April 2010 in Image and Vision Computing
Verified
Journal Article
Closed access
Kaihua ZhangKaihua Zhang
Kaihua Zhang
LZLei Zhang
Lei Zhang
HSHuihui Song
Huihui Song
WZWengang Zhou
Wengang Zhou

1 January 2013 in Pattern Recognition
Verified
Journal Article
Closed access
Kaihua ZhangKaihua Zhang
Kaihua Zhang
HSHuihui Song
Huihui Song

17 August 2012 in IEEE Transactions on Image Processing
Verified
Journal Article
Open access
Kaihua ZhangKaihua Zhang
Kaihua Zhang
LZLei Zhang
Lei Zhang
HSHuihui Song
Huihui Song
DZDavid Zhang
David Zhang
This paper presents a novel reaction-diffusion (RD) method for implicit active contours that is completely free of the costly reinitialization procedure in level set evolution (LSE). A diffusion term is introduced into LSE, resulting in an RD-LSE equation, from which a piecewise constant solution can be derived. In order to obtain a stable numerical solution from the RD-based LSE, we propose a two-step splitting method to iteratively solve the RD-LSE equation, where we first iterate the LSE equation, then solve the diffusion equation. The second step regularizes the level set function obtained in the first step to ensure stability, and thus the complex and costly reinitialization procedure is completely eliminated from LSE. By successfully applying diffusion to LSE, the RD-LSE model is stable by means of the simple finite difference method, which is very easy to implement. The proposed RD method can be generalized to solve the LSE for both variational level set method and partial differential equation-based level set method. The RD-LSE method shows very good performance on boundary antileakage. The extensive and promising experimental results on synthetic and real images validate the effectiveness of the proposed RD-LSE approach.

1 September 2010
Verified
Conference Paper
Closed access
Kaihua ZhangKaihua Zhang
Kaihua Zhang
LZLei Zhang
Lei Zhang
SZSu Zhang
Su Zhang
This paper presents a novel level set approach to simultaneous tissue segmentation and bias correction of Magnetic Resonance Imaging (MRI) images. We first model the distribution of intensity belonging to each tissue as a Gaussian distribution with spatially varying mean and variance. Then a sliding window is used to transform the intensity domain to another domain, where the distribution overlap between different tissues is significantly suppressed. A maximum likelihood objective function is defined for each point in the transformed domain, which is then integrated over the entire domain to form a variational level set formulation. Tissue segmentation and bias correction are simultaneously achieved via a level set evolution process. The proposed method is robust to initialization, thereby allowing automatic applications. Experiments on images of various modalities demonstrated the superior performance of the proposed approach over state-of-the-art methods.

1 January 2021 in Pattern Recognition
Verified
Journal Article
Closed access
JCJin Chen
Jin Chen
HSHuihui Song
Huihui Song
Kaihua ZhangKaihua Zhang
Kaihua Zhang
BLBo Liu
Bo Liu
QLQingshan Liu
Qingshan Liu