Fast Frequency Template Matching Using Higher Order Statistics

Abstract

This correspondence proposes a novel template matching technique using a fourth central moment. The fourth central moment is an established estimator which uses higher order statistics theory, important in the presence of an additive Gaussian noise. By use of some substitutions and complex arithmetic, computation of the fourth central moment is derived from correlation functions of substituting functions. The fourth central moment can be computed using the fast Fourier transform (FFT) approach. Simulation results show that the proposed algorithm performs better than the classical estimators in terms of robustness, while the extra computational cost is negligible.

Wavelet Band-pass Filters for Matching Multiple Templates in Real-time

“…Figure 6 shows the template set and sample frames in the test set. We compared our approach with SSD [5] and M4 [3]. The method SSD Correlation [5] is selected for its simplicity of realization and the method of OHT SSD [20] produces equivalent matches to other SSD algorithms.…”

“…Table 3 extends the comparison table in [3]. When the frame size is of 512 × 512 and template size is of 64 × 64, even for the one template and one frame case, WBPFs have only 2% of the computation for optimal SSD Correlation [5], which is the fastest of the algorithms listed in [3] and 10% of OHT SSD [20].…”

“…According to the way similarity measurements are performed, such template matching methods can roughly be classified into two groups: 1) patch matching schemes, such as the sum of absolute difference (SAD) [1], the sum of squared difference (SSD) [5], or cross correlation (XCORR) [27], where the similarity measurement relies directly on pixel information from the patch of interest; and 2) feature matching schemes, such as invariant features [3,15] and bags of features [14,16,22,24], where similarity measurement relies on features describing the template and the frame. Patch matching methods are not robust, especially when noise, skew, or errors occur [25].…”

“…Further, they consume a large amount of time [21], because of expensive sliding window search for calculating the similarity score over all possible locations. Several techniques have been explored for accelerating such matching methods, including early rejections [27] and correlation techniques [3,5]. However, the computation cost could still be unaffordable when the frame size is large.…”

Vehicle Plate Recognition using Template Matching

“…Template matching is a technique in digital image processing to find small parts of images that match the image template [14]. Template matching is one of the ideas used to explain how our brain recognizes forms or patterns.…”