Shou-Der Wei

Fast Template Matching Based on Normalized Cross Correlation With Adaptive Multilevel Winner Update

In this paper, we propose a fast pattern matching algorithm based on the normalized cross correlation (NCC) criterion by combining adaptive multilevel partition with the winner update scheme to achieve very efficient search. This winner update scheme is applied in conjunction with an upper bound for the cross correlation derived from Cauchy-Schwarz inequality. To apply the winner update scheme in an efficient way, we partition the summation of cross correlation into different levels with the partition order determined by the gradient energies of the partitioned regions in the template. Thus, this winner update scheme in conjunction with the upper bound for NCC can be employed to skip unnecessary calculation. Experimental results show the proposed algorithm is very efficient for image matching under different lighting conditions.

Robust face recognition under lighting variations

In this paper, we propose a new face recognition algorithm based on the matching of relative image gradient magnitudes between images. The recognition algorithm first uses a face localization procedure to provide rough face regions under different lighting conditions, followed by an iterative optimization procedure for precise face matching. Both our face localization and matching procedures are based on matching relative image gradient to be robust against lighting variations. Then a robust face similarity measure based on comparison of relative image gradients is used to determine the face recognition results. The face localization step finds some candidate poses of the face in the image through a fast k-NN search of the best match of the relative gradient features from the database of training feature vectors, which are obtained through image synthesis. After the face images are aligned, the face similarity measure is computed from the normalized correlation between the relative gradients. Experimental results are shown to demonstrate its robust recognition performance under different lighting conditions.

Fast Optimal Motion Estimation Based on Gradient-Based Adaptive Multilevel Successive Elimination

In this paper, we propose a fast and optimal solution for block motion estimation based on an adaptive multilevel successive elimination algorithm. This algorithm is accomplished by applying a modified multilevel successive elimination algorithm (SEA) with the elimination order determined by the sum of the gradient magnitudes of each subblock and the elimination process terminated by comparing the above sum with a threshold. In addition a fast approximate motion estimation method and the accumulated distortion scheme are employed to make the proposed algorithm even more efficiently. Experimental results show that the proposed adaptive multilevel successive elimination strategy (AdaMSEA) algorithm significantly outperforms other previous optimal motion estimation algorithms, including SEA, MSEA, and FGSE on a wide variety of video sequences. Finally, we modify the proposed AdaMSEA to an approximate motion estimation algorithm to achieve very fast computational speed, and the experimental results show superior performance of this approximate algorithm over some fast motion estimation algorithms.

Robust and Efficient Image Alignment Based on Relative Gradient Matching

In this paper, we present a robust image alignment algorithm based on matching of relative gradient maps. This algorithm consists of two stages; namely, a learning-based approximate pattern search and an iterative energy-minimization procedure for matching relative image gradient. The first stage finds some candidate poses of the pattern from the image through a fast nearest-neighbor search of the best match of the relative gradient features computed from training database of feature vectors, which are obtained from the synthesis of the geometrically transformed template image with the transformation parameters uniformly sampled from a given transformation parameter space. Subsequently, the candidate poses are further verified and refined by matching the relative gradient images through an iterative energy-minimization procedure. This approach based on the matching of relative gradients is robust against nonuniform illumination variations. Experimental results on both simulated and real images are shown to demonstrate superior efficiency and robustness of the proposed algorithm over the conventional normalized correlation method

Efficient NCC-Based Image Matching in Walsh-Hadamard Domain

In this paper, we proposed a fast image matching algorithm based on the normalized cross correlation (NCC) by applying the winner-update strategy on the Walsh-Hadamard transform. Walsh-Hadamard transform is an orthogonal transformation that is easy to compute and has nice energy packing capability. Based on the Cauchy-Schwarz inequality, we derive a novel upper bound for the cross-correlation of image matching in the Walsh-Hadamard domain. Applying this upper bound with the winner update search strategy can skip unnecessary calculation, thus significantly reducing the computational burden of NCC-based pattern matching. Experimental results show the proposed algorithm is very efficient for NCC-based image matching under different lighting conditions and noise levels.

A hybrid motion estimation approach based on normalized cross correlation for video compression

In this paper we propose a new hybrid approach for block based motion estimation (ME) by adaptively using the normalized cross correlation (NCC) and sum of absolute differences (SAD) measures. We use the SAD value and gradient sum as the criterion to determine which similarity measure to be used for motion estimation. In general, using the NCC as the similarity measure in the motion estimation leads to more uniform residuals than those of using the SAD. This leads to larger DC terms and smaller AC terms, which yields less information loss after DCT quantization. However, NCC is not suitable for homogeneous regions since the best match may have a high NCC value but with large average gray level difference. Thus, we propose to alternatively use the SAD and NCC as the ME criterion for homogeneous and inhomogeneous blocks. Experimental results show the proposed hybrid motion estimation algorithms can provide superior PSNR and SSIM values than the traditional SAD-based ME method.

Efficient normalized cross correlation based on adaptive multilevel successive elimination

In this paper we propose an efficient normalized cross correlation (NCC) algorithm for pattern matching based on adaptive multilevel successive elimination. This successive elimination scheme is applied in conjunction with an upper bound for the cross correlation derived from Cauchy-Schwarz inequality. To apply the successive elimination, we partition the summation of cross correlation into different levels with the partition order determined by the gradient energies of the partitioned regions in the template. Thus, this adaptive multi-level successive elimination scheme can be employed to early reject most candidates to reduce the computational cost. Experimental results show the proposed algorithm is very efficient for pattern matching under different lighting conditions.

Fast Template Matching by Applying Winner-Update on Walsh-Hadamard Domain

Fast template matching is strongly demanded for many practical applications related to computer vision and image processing. In this paper, we propose a fast template matching method by applying the winner-update strategy on the Walsh-Hadamard domain. By taking advantage of the nice energy packing property of the Walsh-Hadamard transformation, we can just apply the winner-update process with a small number of Walsh-Hadamard coefficients to reduce the computational burden for template matching in an image. Experimental results demonstrate the efficiency and robustness of the proposed template matching algorithm under different noise levels.

Reliable image matching based on relative gradients

We present an image alignment algorithm based on the matching of relative gradient maps between images. This algorithm consists of two stages; namely, a learning-based approximate pattern search and an iterative energy-minimization procedure for matching relative image gradient. The first stage finds some candidate poses of the pattern in the image through a fast search of the best match of the relative gradient features from the database of training feature vectors. The training database is obtained from the synthesis of the template image under a number of uniform samplings in a range of the geometric transformation space. Subsequently, the approximate candidate poses are further verified and refined by matching the relative gradient images through an iterative energy-minimization procedure. This approach based on the matching of relative gradients has the advantage of robustness against inhomogeneous illumination variations. Some experimental results are shown to demonstrate the efficiency and robustness of the proposed algorithm.

A novel motion estimation method based on normalized cross correlation for video compression

In this paper we propose to use the normalized cross correlation (NCC) as the similarity measure for block-based motion estimation (ME) to replace the sum of absolute difference (SAD) measure. NCC is a more suitable similarity measure than SAD for reducing the temporal redundancy in video comparison since we can obtain flatter residual after motion compensation by using the NCC as the similarity measure in the motion estimation. The flat residual results in large DC term and smaller AC term, which means less information is lost after quantization. Thus, we can obtain better quality in the compressed video. Experimental results show the proposed NCC-based motion estimation algorithm can provide similar PSNR but better SSIM than the traditional full search ME with the SAD measure.