Fast Correlation Matching Based on Fast Fourier Transform and Integral Image

Song-feng, 殷松峰 Yin; Yicheng, 王一程 Wang; Liangcai, 曹良才 Cao; Guofan, 金国藩 Jin; Yong-shun, 凌永顺 Ling

doi:10.3788/gzxb20103912.2246

Cited by 5 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Suppose the target image to be searched is T, the length and width of the image are m and n; the image to be searched (large image) is I, and the image length and width are M and N; and M is greater than or equal to m, N Less than or equal to n. Assuming that the length and width of the sub-image of the image to be searched are m and n, and the upper left vertex of the sub-image is (x, y), assuming that the sub-image is, the template coefficients of the sub-block and the template image are defined as [6]: at (k, l)point, T(k,l) represents the gray value of the target image T at (k, l) point, and x,,y I represents the gray value of the sub-image, -T respectively represents the gray value of the template image T Mean.…”

Section: Introduction To Related Matching Algorithmsmentioning

confidence: 99%

Implementation and Optimization of Template Matching Algorithm for FT-M6678

Hu¹,

Shang²,

Chen³

et al. 2020

dtcse

View full text Add to dashboard Cite

Feiteng FT-M6678 (hereinafter referred to as M6678) DSP is a multi-core highperformance DSP with completely independent intellectual property rights. M6678 adopts the Harvard architecture and the new KeyStone multi-core architecture that store instructions and data separately. In general, the multiple classic image processing classic algorithms including correlation matching are not efficient for M6678 DSP architecture. To promote the application of domestic DSP chips in the field of image processing and artificial intelligence. Here, the correlation matching algorithm based on the correlation coefficient is transplanted to the M6678 platform, combining the algorithm characteristics and the architecture characteristics of the target platform, performance optimization in terms of parallelism and locality is carried out. The performance of the program is obviously improved, and the unique computing resources of the platform are more fully utilized, which is meaningful for the transplantation and optimization of other image processing algorithms on the platform.

show abstract

Section: Introduction To Related Matching Algorithmsmentioning

confidence: 99%

Implementation and Optimization of Template Matching Algorithm for FT-M6678

Hu¹,

Shang²,

Chen³

et al. 2020

dtcse

View full text Add to dashboard Cite

show abstract

“…Image registration algorithm is usually divided into two categories: one is gray correlation algorithm [2]; the other is feature-based registration algorithm [3]. Gray-based match the image data directly, which include normalized cross-correlation registration, template registration, the fast Fourier algorithm, projection registration, sequential similarity detection registration and so on [4][5][6][7][8]. The other called feature registration includes point, line, area and other significant features primitives [9].…”

Section: Introductionmentioning

confidence: 99%

A Image Registration Algorithm Based on Wavelet Pyramid for CCD Image

Lü

Kang

Zhai

2014

AMM

View full text Add to dashboard Cite

Image registration is the key process in analyzing images and data from satellites. Feature-based methods find correspondence pixels which point to the same place between two images. In this paper, a wavelet pyramid hierarchical image registration algorithm is presented. First mismatching exclusion policy on the top of pyramid is used. Other hand search strategy which gets the scope of the search layer on the bottom of the pyramid is adopted. Both of them rely on pair of matching-right points. Experimental results show that the algorithm can significantly improve the search efficiency, and obtain a good match accuracy and reliability.

show abstract

Groove-center detection in gas metal arc welding using a template-matching method

Wang

Shi

et al. 2016

Int J Adv Manuf Technol

View full text Add to dashboard Cite

To achieve welding automation, the center of the groove needs to be detected accurately during welding. We developed a method based on template-matching to detect the groove center during gas metal arc welding (GMAW). To avoid the negative influence of the strong GMAW arc light, a high-dynamic-range camera was used to capture details of the welding arc, molten pool, and the V-groove simultaneously in a single image. Two imageprocessing and object-detection algorithms were developed to detect the center of the welding pool and the groove based on template matching. The experimental results of the latter algorithm were more accurate for identifying the position of the groove center. However, interference in the welding process caused the template-matching method to fail under certain conditions. Therefore, the two detection algorithms were combined to improve the detection accuracy. After filtration of the detected welding-pool center, the groove-center detection algorithm based on template matching results in higher accuracy.

show abstract

Fast Correlation Matching Based on Fast Fourier Transform and Integral Image

Cited by 5 publications

References 0 publications

Implementation and Optimization of Template Matching Algorithm for FT-M6678

Implementation and Optimization of Template Matching Algorithm for FT-M6678

A Image Registration Algorithm Based on Wavelet Pyramid for CCD Image

Groove-center detection in gas metal arc welding using a template-matching method

Contact Info

Product

Resources

About