Zhenkang Shen

A refined coherent point drift (CPD) algorithm for point set registration

The coherent point drift (CPD) algorithm is a powerful approach for point set registration. However, it suffers from a serious problem-there is a weight parameter w that reflects the assumption about the amount of noise and number of outliers in the Gaussian mixture model, and its value has an influence on the point set registration performance In the original CPD algorithm, the value of w is set manually, and hence an improper value will lead to poor registration results. To solve this problem, a fully automatic algorithm for the selection of an optimal weight parameter is proposed using a hybrid optimization scheme that combines the genetic algorithm with the Nelder-Mead simplex method. The experiments show that the refined CPD algorithm is more effective and extends the original CPD algorithm in its methodology and applications.

A Coarse-to-Fine Matching Algorithm for FLIR and Optical Satellite Image Registration

The registration of a forward-looking infrared (FLIR) image and an optical satellite image (visible image) is challenging but important for image-based navigation systems. To solve this problem effectively, a coarse-to-fine matching algorithm is proposed. First, geometric rectification based on the attitude angles and height parameter is carried out to eliminate the distinct rotation and scale discrepancies between the FLIR and visible images. Then, in the fine registration step, the edges of the visible image and rectified infrared image are extracted, and a robust point set registration algorithm which can deal with the similarity transformation distortion is proposed. Finally, the experiments on both the simulated images and real images show that our algorithm can achieve excellent performance in terms of both robustness and accuracy, and the registration precision of real images can be around one pixel.

Contour detection based on SUSAN principle and surround suppression

A contour edge detector combing SUSAN principle and surround suppression is proposed in this paper. Specifically, the operator follows the flow of the Canny edge detector. Firstly, the edge gradient information and modified SUSAN principle are utilized to classify contour edge points and texture edge points approximately. Secondly, surround suppression is applied on the texture edges to suppress them. Finally, contour map is constructed through two hysteresis thresholding procedures. Performance comparison with three other detectors is made and experimental results show that our contour detector performs better.

Contour detection based on contextual influences

A contour edge detector combing surround facilitation and suppression is proposed in this paper. Specifically, the detector follows the flow of the Canny edge detector while incorporating surround facilitation and suppression into it. Firstly, edge gradient magnitude and edge density information is utilized to classify potential contour points and texture points approximately. Secondly, surround facilitation and suppression are applied on the potential contour points and texture points respectively to enhance the contours and suppress textures. Finally, contour map is constructed through two hysteresis thrsholding procedures. Performance comparison with three other edge detectors is made and the experimental results show that our contour detection method performs better.

Contour detection improved by frequency domain filtering of gradient image

We propose an intermediate computational step, frequency domain filtering of gradient image, to improve contour detection performance of gradient-based edge detectors. This step is inspired by analyzing the spectrum distribution of object contours and texture edges in the frequency domain of gradient image. We illustrate the principle and effect of this step by adding it to the Canny edge detector. The resulting operator can selectively retain object contours and region boundaries, and meanwhile can dramatically reduce non-meaningful elements caused by textured background. We use several types of images to compare the proposed method and other related methods qualitatively and quantitatively. Experimental results show that the proposed method can effectively enhance the contour detection of Canny edge detector and achieves similar detection performance to two other related methods but runs faster.

Correction to “A Coarse-to-Fine Matching Algorithm for FLIR and Optical Satellite Images Registration” [Jul 12 599-603]

In the above titled paper (ibid., vol. 9, no. 4, pp.599-603, Jul. 2012), formulas (10) and (12) are incorrect. Their correct forms are presented here.

Contour Detection Based on Center-Surround Contrast

A contour edge detector based on center-surround contrast is proposed in this paper.Specifically, the detector follows the flow of the Canny edge detector while using center-surround contrast instead of gradient magnitude to detect contour edges. Firstly, image gradient is computed in the same way as the traditional Canny detector. Secondly, center-surround contrast is computed using gradient information. Finally, contour map is constructed from center-surround contrast through non-maxima suppression and hysteresis thrsholding procedures. Performance comparison with two other edge detectors is made and the experimental results show that our contour edge detection method performs better.