The evaluation of normalized cross correlations for defect detection

Tsai, Du‐Ming; Lin, Chien-Ta; Chen, Jeng-Fung

doi:10.1016/s0167-8655(03)00098-9

Cited by 96 publications

(32 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Depending on the size of the images, and for 20+ circles, the sum-table method is ~11-28 (9)(10)(11)(12)(13)(14)(15)(16)(17)(18)(19)(20) Note that the computational saving does not utilize the fact that the motion vector between two 50% overlapping sub-images does not change significantly. To find the motion vector for the current template centre, the closest motion vector of a previously computed template centre could be used as an approximation.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Fast normalized cross correlation for motion tracking using basis functions

Hii

Hann

Chase

et al. 2006

Computer Methods and Programs in Biomedicine

View full text Add to dashboard Cite

Digital Image-based Elasto-tomography (DIET) is an emerging method for noninvasive breast cancer screening. Effective clinical application of the DIET system requires highly accurate motion tracking of the surface of an actuated breast with minimal computation. Normalized cross correlation (NCC) is the most robust correlation measure for determining similarity between points in two or more images providing an accurate foundation for motion tracking. However, even using fast fourier transform (FFT) methods, it is too computationally intense for rapidly managing several large images. A significantly faster method of calculating the NCC is presented that uses rectangular approximations in place of randomly placed landmark points or the natural marks on the breast. These approximations serve as an optimal set of basis functions that are automatically detected, dramatically reducing computational requirements. To prove the concept, the method is shown to be 37-150 times faster than the FFT-based NCC with the same accuracy for simulated data, a visco-elastic breast phantom experiment and human skin. Clinically, this approach enables thousands of randomly placed points to be rapidly and accurately tracked providing high resolution for the DIET system.

show abstract

Section: Discussionmentioning

confidence: 99%

“…The method of [16] has also been applied for defect detection [17,18]. However, it was shown in [19] that if basis functions are used to approximate the template then substantial computational gains could be obtained over the FFT-based methods.…”

Section: Introductionmentioning

confidence: 99%

Fast normalized cross correlation for motion tracking using basis functions

Hii

Hann

Chase

et al. 2006

Computer Methods and Programs in Biomedicine

View full text Add to dashboard Cite

show abstract

“…The normalized correlation is then calculated by multiplying the pixels that are overlaid. The maximum values or peaks of the computed correlation values indicate the matches between the template and the original image [9].…”

Section: Theoretical Background 21 Correlationmentioning

confidence: 99%

Automation of Defect Detection in Digital Radiographic Images

Njogu¹,

Maina²,

Mwangi³

2016

IJCA

View full text Add to dashboard Cite

Conventionally, it is well-known that diagnosis of defects in an object depends on experience, capability and concentration of the operator. But this process is error prone and liable to subjective considerations such as fatigue, boredom and lapses in operator concentration. This reduces the reliability and consistency of the process thus precluding the undertaking of preventive maintenance with confidence. Also, the process is time consuming and expensive. In this paper, a new automatic defect detection algorithm has been developed in order to identify defects in digital radiographic images. Percolation and Otsu's thresholding and segmentation algorithms have been used and a new procedure for displaying defects on a screen has been developed. Computer simulation based experiments have been used to demonstrate the effectiveness of the proposed algorithm. The performance of the proposed algorithm is found to be better than the existing defect detection algorithms as the results obtained are impressive with respect to the defect detection rate.

show abstract

“…Alternative ways of detecting defects can be based on globally or locally calculated correlations and entropy (Tsai et al, 2003;Skubalska-Rafajłowicz, 2008), but these approaches require further studies before trying to apply them to hot metals.…”

Section: Introductionmentioning

confidence: 99%

Local Detection Of Defects From Image Sequences

Rafajłowicz

Wnuk

2008

International Journal of Applied Mathematics and Computer Science

View full text Add to dashboard Cite

Our aim is to discuss three approaches to the detection of defects in continuous production processes, which are based on local methods of processing image sequences. These approaches are motivated by and applicable to images of hot metals or other surfaces, which are uniform at a macroscopic level, when defects are not present. The first of them is based on the estimation of fractal dimensions of image cross-sections. The second and third approaches are compositions of known techniques, which are selected and tuned to our goal. We discuss their advantages and disadvantages, since they provide different information on defects. The results of their testing on 12 industrial images are also summarized.

show abstract

The evaluation of normalized cross correlations for defect detection

Cited by 96 publications

References 30 publications

Fast normalized cross correlation for motion tracking using basis functions

Fast normalized cross correlation for motion tracking using basis functions

Automation of Defect Detection in Digital Radiographic Images

Local Detection Of Defects From Image Sequences

Contact Info

Product

Resources

About