A novel image edge detection algorithm based on neutrosophic set

Automatic optimal filament segmentation with sub-pixel accuracy using generalized linear models and B-spline level-sets.

This paper proposes novel second order and fourth order anisotropic diffusion models for image denoising. These two models are based on CONvolutional Virtual Electric Field (CONVEF). The proposed second order anisotropic diffusion model was introduced by introducing the CONVEF into the Perona-Malik (P-M) equation and the fourth order one is coined by combining CONVEF and the You-Kaveh (Y-K) equation. The employment of the CONVEF model allows to improve the estimation of high order derivatives and makes the proposed methods more robust to noise. In addition, the proposed CONVEF-based Y-K model is an anisotropic diffusion equation which can avoid the over-smoothness of edges and provide better edge protection capability except for better denoising. Some experiments are conducted to demonstrate the efficiency of the proposed methods.

Anisotropic second and fourth order diffusion models based on Convolutional Virtual Electric Field for image denoising

Peripheral nerves are important pathways for receiving afferent sensory impulses and sending out efferent motor instructions, as carried out by sensory nerve fibers and motor nerve fibers. It has remained a great challenge to functionally reconnect nerve internal fiber bundles (or fascicles) in nerve repair. One possible solution may be to establish a 3D nerve fascicle visualization system. This study described the key technology of 3D peripheral nerve fascicle reconstruction. Firstly, fixed nerve segments were embedded with position lines, cryostat-sectioned continuously, stained and imaged histologically. Position line cross-sections were identified using a trained support vector machine method, and the coordinates of their central pixels were obtained. Then, nerve section images were registered using the bilinear method, and edges of fascicles were extracted using an improved gradient vector flow snake method. Subsequently, fascicle types were identified automatically using the multi-directional gradient and second-order gradient method. Finally, a 3D virtual model of internal fascicles was obtained after section images were processed. This technique was successfully applied for 3D reconstruction for the median nerve of the hand-wrist and cubital fossa regions and the gastrocnemius nerve. This nerve internal fascicle 3D reconstruction technology would be helpful for aiding peripheral nerve repair and virtual surgery.

/pdf/three-dimensional-reconstruction-of-peripheral-nerve-4v55ygetkp.pdf

Three-dimensional Reconstruction of Peripheral Nerve Internal Fascicular Groups

The accuracy of tracking based on Camshift would decrease due to the similarity between target color and background color or the target is obscured. For the above problems, improved target tracking algorithm based on Camshift is proposed in this paper. The Camshift algorithm is improved by using the contour features of the target, and Camshift search window is updated according to the contour feature of the target. Thus, interference of background and strong light is weakened. Kalman filtering algorithm is used to predict the motion state of the tracking target, enhancing the efficiency of tracking when the tracking target is obscured. Experiments show that Camshift is combined with the contour feature of target and make the tracking more effectively under the conditions of background. And the Kalman filtering algorithm is used to predict position of the target to make the tracking effectively when the target is obscured.

Improved target tracking algorithm based on Camshift

Contour extraction of gait recognition based on improved GVF Snake model

Contour extraction of gait recognition

DSA image registration based on 3D space-time detection

Digital watermarking algorithm based on space-time coding

A contour segmentation algorithm is proposed based on GVF Snake model and Contourlet transform Firstly, object contours of images can be obtained based on Contourlet Transform, and those contours will be identified as the initial contour of GVF Snake model Secondly, GVF Snake model is used to detect the contour edge of human gait motion Experimental results show that the proposed method can extract the edge feature accurately and efficiently

Rui Li

Papers

Contour extraction of gait recognition based on improved GVF Snake model

Contour extraction of gait recognition

DSA image registration based on 3D space-time detection

Digital watermarking algorithm based on space-time coding

Contour segmentation based on GVF snake model and contourlet transform