ScienceDirect® Home Skip Main Navigation Links
  
 
Home
Browse
Search
My Settings
Alerts
Help
 Quick Search
 Search tips (Opens new window)     Clear all fields          Advanced Search
Advertisement
Result list |  previous  < 1 of 1 >  next 
Font Size: Decrease Font Size  Increase Font Size
Related Articles
View More Related Articles
Advertisement
Thumbnails | Full-Size Images - selected
Article - selected
Figures/Tables - selected
References - selected
Focus your view on this article
Signal Processing
Volume 90, Issue 7, July 2010, Pages 2319-2326

doi:10.1016/j.sigpro.2010.02.012 | How to Cite or Link Using DOI
Copyright © 2010 Elsevier B.V. All rights reserved.
  Cited By in Scopus (0)
  Permissions & Reprints

Fast communication

Applying target maneuver onset detection algorithms to defects detection in aluminum foil

Ming Zhainext terma, Corresponding Author Contact Information, E-mail The Corresponding Author, E-mail The Corresponding Author and Shan Fub, E-mail The Corresponding Author

a School of Electronic, Information and Electrical Engineering, Shanghai Jiao Tong University, Shanhai, PR China

b School of Aeronautics and Astronautics, Shanghai Jiao Tong University, Shanhai, PR China

Received 2 June 2009; 
revised 27 January 2010; 
accepted 10 February 2010. 
Available online 16 February 2010.

Abstract

Quality inspection of aluminum foil products plays an important role for aluminum foil manufactures, but it is an arduous work for human. In our work, the target maneuver onset detection algorithms are applied to defect detection in aluminum foil images and the results are inspiring. It is assumed that the intensity of aluminum foil images is Gaussian distributed and the distribution of defect intensity is different from the normal. Under these assumptions Kalman filters with constant velocity (CV) model are used to filter defect images. During the filter process the maneuver onset detection algorithms are used to detect defects. The three maneuver onset detection algorithms, the measurement based chi-square detector (MR), the input estimate based chi-square detector (IE) and the input estimate based Gaussian significance detector (IEG) are tried respectively and the performance of the three algorithms are compared.

Keywords: Kalman filter; Input estimation; Measurement residual; Defects detection

Article Outline

1. Introduction
2. Preliminary
2.1. The Kalman filter and constant velocity model
2.2. The measurement residual based Chi-square detector (MR)
2.2. The input estimation based Chi-square detector (IE)
2.3. The input estimate based Gaussian significance detector (IEG)
3. Implementation
4. Performance comparison
4.1. Performance of the three detectors
4.2. Computation complexity
5. Conclusion
References

1. Introduction

Optical devices have been incorporated into mechatronic systems and many machine-vision based techniques have been used for quality control of products equipped with intelligence. In product quality control of aluminum foil manufacturing, quality inspection has to resort to machine-vision-based techniques for rigorous manufacture conditions. There are many machine-vision based quality control techniques. In Ref. [1], edges in images are used to detect defects in ceramic tiles. In the textile industry, Fourier analysis technique [2], morphology-based technique [3] and [8], wavelet-based technique [4] and [9], co-occurrence matrices and garbo-filter based technique [5] and [10] can be used to detect defects in fabric surface. In leather industry, oriented texture analysis is used to detect defects in leather [6]. In [7], the infrared light reflected by the metal sheets is used to analyze the defects of metal sheet. However, each defect detecting technique is designed for a special target, so those techniques are not suit for defects detection in aluminum foil. The defects detection in aluminum foil is an arduous work for human because defects often are small and similar to normal areas. Moreover the output of product is huge, sampled quality inspection cannot well satisfy the quality control demands. The real-time and automatic defect detection methods are urgently needed.

The technique suitable for defect detection in aluminum foil should be designed according to the property of the aluminum foil product line. In our case the foil goes through the product line at nearly five meters per second. It means high resolution planar array cameras cannot be used, because high resolution planar cameras often have low frame rate and the redundant information in the image sequence will affect image processing speed. Therefore, a line scan camera is used. There are many types of defects in aluminum foil, some of which are shown in Fig. 1. Some defects have no apparent edges and the intensity of some defects is similar to normal areas (e.g. Fig. 1(A, D, E). Moreover some are very small (e.g. Fig. 1(C, E, G). So the edge-based technique and threshold-based binarization methods may not perform well. The texture-based frequency domain analysis methods cannot be used because there is no apparent texture information in aluminum foil images. It is more important that the speed of detecting process should be fast enough to satisfy the real time application. Furthermore the intensity of normal areas may vary (e.g. Fig. 1(E, H, K, M) and the sizes of defects are different (e.g. Fig. 1(B, C, F, I, L), these will bring troubles. Moreover, it must be considered that different types of defects often appear in one image. All these make defect detection difficult.




Fig. 1. Defect images.

We collect a large number of foil images from the product line, and from these images the histogram of intensity is obtained. The histogram shows that the intensity of these images approximately obeys Gaussian distribution. Then we collect images with labeled defects and compute the histogram only using the pixels labeled as defects. The two histograms show that the defect intensity is different from the normal. The property can be used to detect defects in aluminum foil. Our contribution is that we apply the target maneuver onset detection algorithms in maneuver target tracking (MTT) field to solve the defect detecting problem. Three maneuver detectors, the measurement based chi-square detector (MR), the input estimate based chi-square detector (IE) and the input estimate based Gaussian significance detector (IEG), are tried and we obtain inspiring results. Our technique is that we assume the intensity of aluminum foil images is Gaussian distributed; Kalman filters with constant velocity (CV) model are used to filter defect images; defects are determined by the maneuver onset detectors during the filter process. Experiments show that our technique is effective for most types of defects and the processing speed can satisfy the real time applications.

This work is organized as follows: Section 1 the introduction; some basic notions are reviewed in Section 2; Section 3 the implementation; Section 4 performance comparison; Section 5 the conclusions.

2. Preliminary

In this section, we review some basic notions from the theory of Kalman filter, the constant velocity (CV) model, as well as the three target maneuver onset detectors, the measurement based chi-square detector (MR), the input estimate based chi-square detector (IE) and the input estimate based Gaussian significance detector (IEG), which we need in the sequel.

2.1. The Kalman filter and constant velocity model

The Kalman filter is a linear estimator based on the minimum mean squared error (MMSE) [11] and [12], for the sake of less computation and better performance it has been widely used since it is introduced. Here is a brief review of a Kalman filter.

Given a system equation and measurement equation as follows:



where x and z are state and measurement vectors respectively; v and w are process and measurement noise and are assumed to be Gaussian distributed with zero mean and covariance Q and R; u is the known input vector; F, H, and G are state, measurement and input matrixes respectively. F, G, H, Q and R are assumed known and possibly time-varying. The two noise sequences and the initial state are assumed mutually independent. The previous constituted the linear Gaussian (LG) assumption.

The main equations of a Kalman filter are as follows:

View the MathML source


View the MathML source


View the MathML source






View the MathML source




where the expression View the MathML source denotes the estimate of A at time k+1 estimated at time k; x and z are the state and measurement vectors; P and S are the state covariance and the innovation covariance matrixes; W and μ are the filter gain and the innovation (measurement residual).

In the Kalman filter some kinetic models are often used to describe the kinetic property of the target, like the constant velocity (CV) model and the constant acceleration (CA) model [12]. Consider a target moving with constant velocity, the CV model is suitable to describe the kinetic property of the target. In the CV model, the state vector is x=(X,X)T where X is displacement, X is the differential of X, i.e., velocity. If the measurement is displacement then the measurement matrix is View the MathML source. Otherwise if the measurement is velocity then the measurement matrix is View the MathML source. In the CV model the state matrix is

View the MathML source
where T is a time interval. Unlike the target tracking, in our experiments we assume the intensity of foil images is the measurement of velocity in the state of Kalman filter. The intensity is approximately constant and with Gaussian noise so the measurement matrix View the MathML source is used.

2.2. The measurement residual based Chi-square detector (MR)

The measurement residual based chi-square detector is often used to detect target maneuver in maneuver target tracking (MTT) applications [12], [13], [14], [15], [16] and [17]. With the linear-Gaussian assumption, the measurement residuals of a Kalman Filter are zero mean, Gaussian distributed and white; i.e., μ(k)not, vert, similarN(0,S(k)) and

where P and S are the state covariance and the innovation covariance; μ is the innovation (measurement residual); H is the measurement matrix; R is the covariance of the measurement noise;. Furthermore

is a chi-square distributed variable, that is View the MathML source where nz=dim(μ) is the dimension of vector μ. If

(5)
View the MathML source
then decide a maneuver occurs, where 1−α is the confidence level. The decision which is based on a single sampling time in Eq. (4), can be replaced by a moving average (or moving sum) of the normalized innovations squared over a sliding window of s sampling times

(6)
View the MathML source
The above is chi-square distributed with snz degrees of freedom. Alternatively, a fading memory average (also called exponentially discounted average)

where 0<β<1 and with initial condition ξβ(0)=0, can be used. The variable ξβ is approximately distributed as View the MathML source with nβ=(1+β/1−β)nz. Its effective window length s is 1/1−β, and e.g. for β=0.95 one has s=20.

2.2. The input estimation based Chi-square detector (IE)

The input estimation based chi-square detector is an algorithm to detect target maneuver in maneuver target tracking (MTT) applications [12], [13], [14], [15], [16] and [17]. The detector consists of input estimation and chi-square significance test. In the input estimation process two models are used, one is the nonmaneuvering model (Eq. (8)) the other is the maneuvering model (Eq. (9)) with input u.



From the nonmaneuvering filter the input u can be detected and estimated. Denote the present time by k and assume that the target started maneuvering at time ks, that is, the maneuver onset time is ks. The unknown inputs during the interval [ks,…, k] are u(i), i=ks,…, k−1. The state from the mismatched nonmaneuvering filter based on Eq. (3) will be denoted by an asterisk:

(10)
View the MathML source
with the initial condition View the MathML source, where W is the filter gain and Φ(i)=F[IW(i)H].

If the inputs are known, the hypothetical correct filter based on Eq. (9) will yield estimates according to the recursion

(11)
View the MathML source
The innovations corresponding to the hypothetical correct filter (Eq. (11)) is

(12)
View the MathML source
The innovations corresponding to the nonmaneuvering filter (Eq. (10)) is

(13)
View the MathML source
Combining Eqs. (10), (11), (12) and (13) yielding

(14)
View the MathML source
Assuming the input to be constant over the interval [ks,…,k−1], that is, u(j)=u, j=ks,…, k−1, s is the window length, yielding

where

(16)
View the MathML source
Based on Eq. (15) the input could be estimated via LS from

(17)
View the MathML source
where View the MathML source is the estimate of the input u and

(18)
View the MathML source


(19)
View the MathML source
and ε, whose components are innovations (Eq. (13)), is zero mean with block-diagonal covariance matrix

The input estimate in batch form is

(21)
View the MathML source
where the covariance matrix of View the MathML source is

The chi-square significance test is used to test the significance of the estimation of input. A maneuver detection is declared if and only if Eq. (21) is statistically significant. The significance test for the input is

(23)
View the MathML source
It is a chi-square distributed variable, that is View the MathML source where View the MathML source is the dimension of vector View the MathML source. If

(24)
View the MathML source
then decide a maneuver occurred, where 1−α is the confidence level.

2.3. The input estimate based Gaussian significance detector (IEG)

The input estimate based Gaussian significance detector also is a target maneuver onset detection algorithm [18], [19] and [20]. It is different from the input estimate based chi-square detector that it tests the significance of the input estimate by another statistical significance test, the Gaussian significance test. When the input u is estimated using the method mentioned in Section 2.2, a maneuver detection can be declared if and only if a component View the MathML source of View the MathML source is statistically significant, that is

(25)
View the MathML source
where View the MathML source is the estimate of the input u, View the MathML source is the variance of View the MathML source, n is the dimension of View the MathML source and [−λ,λ] is the confidence interval. Eq. (25) is the Gaussian significance test of input u and is supposed to be normally distributed. The value of λ can be determined by inspecting the cumulative normal distribution table for a preset confidence coefficient parameter [21].

3. Implementation

The experiment setup is shown in Fig. 2. The lighting system is made of LED. The camera works at about 12 kHz with resolution 1024 in gray mode. A rotary encoder is used to generate grabbing signals for the frame grabber in order to keep the line-to-line scanning spacing at about 0.42 mm. The foil goes through the camera at about 5 m/s and its width is no more than 1550 mm.




Fig. 2. The experiment setup.

The line scan camera scans the foil and in our case we constitute a image with every 768 scan line. Denote the image as I and denote the width and height of image I as M and N. In our case M=1024 and N=768. From our statistics the intensity of the pixel in the images approximately obeys Gaussian distribution. The distribution of the defect intensity is different from the normal, so the defect area can be detected by these maneuver onset detectors. Unlike the target tracking, in our case image intensity of every row (column) is considered as the measurement time sequence z in the measurement equation (Eq. (1)). The measurement is considered as velocity and to be Gaussian distributed. Under these conditions, CV model is used with measurement matrix View the MathML source, state matrix

View the MathML source

where T is a time interval. Since every column (row) is considered as a time sequence of the measurement of velocity in CV model, the Kalman filter can be used to filter the column from up to down. There are the N columns in image I so N Kalman filters are used respectively. Each column relates to one filter. In the filtering process of each column (row), the position where a maneuver occurs is considered to be a defect position. The defect position can be detected by any one of the three target maneuver onset detectors. The detection result is stored in the defect mask Σ, Σ is an M×N matrix, if the (i,j)th point in image I is detected to be a defect point by some detector then label the (i,j)th element of Σ with 1 otherwise label it with zero. Some defect masks obtained by MR detector are shown in Fig. 3. Moreover, some false detection results are shown in Fig. 4. In fact the false detection can be correctly detected by altering the parameters of the proposed method. The false detection do not often occur and the parameters should be set properly to make the proposed method cover most common defects so we choose the parameters suitable for most defects instead of the parameters suitable for a few defects.




Fig. 3. Defect images and the defect masks obtained by the MR detector.


Fig. 4. Some false detection results. (In A and B, the foil is crinkled and the crinkled area are detected as many small defects by the proposed method. In C, one defect is detected as four defects. In D, the defect area is enlarged.)

If using MR detector to detect defects, during the filter process of every column (row) the measurement residual μ is calculated and tested by chi-square significance test to detect defects. If using IE or IEG detector, the input u should be estimated during the filter process and then the input estimate is tested by chi-square significance test or Gaussian significance test to detect defects.

It is found that the position of the defect areas detected by each of the detectors will deviate from the correct position of defects due to the detection delay of the detectors so it will lead to imprecise location of defects. To solve the problem, we detect image I from the four directions: up to down; down to up; left to right; and right to left. So 2M+2N filters are used. Denote Σup, Σdown, Σleft, Σright as the defect masks come from the detecting results of the four directions. Computed the logical OR of the four defect masks,

where the operator “|” is logical OR, Σ(i,j) is the (i,j)th element of Σ. The defect mask Σ is the final defect mask and the defect area of image I is labeled in Σ.

In the filter process, Kalman filter is used with measurement matrix View the MathML source and state matrix

View the MathML source
where T=1/f0, f0 is the working frequency of the line scan camera. Kalman filter needs initialization to determine the first state vector x(0) and the first state covariance P(0|0). We set View the MathML source, where View the MathML source is the average intensity of the image I and set the first state covariance

View the MathML source
where R is the variance of measurement noise. R should be set a bit larger than the variance of the intensity of the image I to obtain better performance. In our case we set R=1.2RI where RI is the intensity variance of image I. We assume there is no process noise, that is, Q is zero and experimental results prove this assumption is proper. In the MR detector, G is assumed to be zero, that is, no input is considered and in the other two detectors we set

View the MathML source

4. Performance comparison

4.1. Performance of the three detectors

Define the correct detection rate (CDR), the fake alarm rate (FAR) and the missed detection rate (MDR) as follows:

View the MathML source


(27)
View the MathML source


View the MathML source

Firstly we detect the defects in the defect image database which contained 10 types of defects with the three detectors with the same initial parameters respectively. In the experiments the fading memory average window is used. The CDR, FAR and MDR of the detection result of the three detectors are presented in Table 1 respectively. And then we test the three detectors in the real images obtained from the foil product line respectively and compared the detecting results with the results obtained by the skilled quality inspectors. The CDR, FAR and MDR of the results are similar to Table 1. Table 1 presents that the three detectors are all effective for defects detection and the difference of their performance are small.

Table 1.

The CDR, FAR and MDR of the three detectors at different window length.

Detection methodWindow length(s)
s=1s=3s=5s=7
MR
 CDR0.9320.9290.9270.919
 FAR0.0520.0490.0440.043
 MDR0.0680.0710.0730.081

IE
 CDR0.9370.9330.9300.923
 FAR0.0490.0440.0400.037
 MDR0.0630.0670.0700.077

IEG
 CDR0.9350.9340.9310.920
 FAR0.0510.0450.0420.036
 MDR0.0950.0660.0690.080

4.2. Computation complexity

Because no serious attempt is made to optimize each detector beyond the obvious (for example, caching matrix inversion results, vectorizing operations and caching recurring information from sample to sample), we carry out the three detectors to detect defects in the images with size of 1024×768 at different window length on a PC with Intel E4500 CPU (2.2 GHz) and calculated the average processing time as an indicator of relative computational complexity of the three detector. The results are shown in Fig. 5.




Fig. 5. The average CPU processing time of the three detectors at different window length.

Due to the simplicity of MR, it is least computationally intensive. The IE and IEG detectors require almost the same processing time, it is because the two detectors need the same input estimate process and the significance test functions are similar. The computation complexity of the MR detector is independent of the window length while the computation complexity of IE and IEG detector will increase with the window length. Due to noise it will increase false alarm to detect defect from one sample so a window is needed to obtain a moving sum to against noise. Small window length has less ability against noise while large window length will increase miss detection. So we compare the performance of different window lengths and find that it is proper to set the window length at 3 or 5 in our system.

5. Conclusion

We try the three target maneuver onset detectors, the MR, IE and IEG detectors, to detect defects in aluminum foil and experiments show that all the three detectors are effective for defects detection in aluminum foil. We also compare the computation complexity of the three methods on a PC with Intel E4500 CPU. Of the three detectors, the MR detector is least computationally intensive. The IE and IEG detectors have almost the same computation complexity. In Section 3, we detect the image from the four directions, the four detecting processes of the four directions are mutually independent, so the four processes can be carried our in parallel. If in parallel model, the process time can reduce three quarters and therefore it makes our technique practicable for real time applications. In our experiment the parameters are set to be suitable for detecting the defect more than five pixels and the defect less than 5 pixels will be ignored. If the parameters are set to be suitable for the defect less than 5 pixels and then the false alarm will burst due to noise. Fortunately the defects more than 5 pixels take up a major proportion in our case so the proposed method is applicable. The system is designed to work at 5 m/s. When the speed of foil exceeds 7 m/s, for the computation limit of the hardware, the detecting system will halt. It is a problem we will face in the future because our product line will be updated soon and we plan to solve this problem by using more powerful computer or using parallel computing methods. The defect detection is only the first step of our quality inspection system. After the defects are detected, it is required to recognize the detected defects and it will be our future work.

References

[1] S. Vasilic, Z. Hocenski, The edge detecting methods in ceramic tiles defects detection, in: Proceedings of the 2006 IEEE International Symposium on Industrial Electronics, vol. 1, Montreal, Canada, July 2006, pp. 469–472.

[2] C. Chan and G.K.H. Pang, Fabric defect detection by fourier analysis, IEEE Transaction Industry Applications 36 (5) (September to October 2000), pp. 1267–1276. View Record in Scopus | Cited By in Scopus (93)

[3] J.K. Chandra, P.K. Banerjee, A.K. Datta, Morphological reconstruction operation for the detection of defects in woven fabric, in: Proceedings of the 2008 IEEE Region 10 Colloquium and the Third ICIIS, Kharagpur, India, December 2008, pp. 1–5. Full Text via CrossRef

[4] H. Fujiwara, Z. Zhang, Visual inspection of textile surfaces with translation invariant wavelet shrinkage, in: Proceedings of the 30th Annual Conference of IEEE Industrial Electronics Society, vol. 2, November 2004, pp. 1252–1257. View Record in Scopus | Cited By in Scopus (1)

[5] I.C. Baykal, G.A. Jullien, In-camera defection of fabric defects, in: Proceedings of the International Symposium on Circuits and Systems, vol. 3, May 2004, pp. 933–936.

[6] F.P. Lovergine, A. Branca, G. Attolico, A. Distante, Leather inspection by oriented texture analysis with a morphological, in: Proceedings of the 1997 International Conference on Image Processing, vol. 2, Washington, October 1997, pp. 669–671. Full Text via CrossRef | View Record in Scopus | Cited By in Scopus (4)

[7] H. Chen, U.K. Madawala, J. Tham, A low cost sensing technique for detecting on defects metal sheets, in: Proceedings of the IEEE International Conference on Industrial Technology, Mumbai, India, December 2006, pp. 2286–2291. Full Text via CrossRef

[8] K.L. Mak, P. Peng, K.F.C. Yiu, Fabric defect detection using morphological filters, Image and Vision Computing, 5 April, 2009.

[9] Y. Han and P. Shi, An adaptive level-selecting wavelet transform for texture defect detection, Image and Vision Computing 25 (8) (August 2007), pp. 1239–1248. Article | PDF (2294 K) | View Record in Scopus | Cited By in Scopus (9)

[10] A. Latif-Amet, An efficient method for texture defect detection: sub-band domain co-occurrence matrices, Image and Vision Computing 18 (6–7) (May 2000), pp. 543–553. Article | PDF (1932 K) | View Record in Scopus | Cited By in Scopus (56)

[11] R.E. Kalman, A new approach to linear filtering and prediction problems, Transactions of the ASME—Journal of Basic Engineering (1960), pp. 35–45.

[12] Y. Bar-Shalom and X.R. Li, Estimation with Applications to Tracking and Navigation: Theory, Algorithms, and Software, Wiley, New York (2001).

[13] J. Ru, A. Bashi, X.R. Li, Performance comparison of target maneuver onset detection algorithms, in: Proceedings of the SPIE Conference on Signal and Data Processing of Small Targets, vol. 5428, Orlando, USA, 2004, pp. 419–428. Full Text via CrossRef | View Record in Scopus | Cited By in Scopus (9)

[14] Y. Bar-Shalom and K. Birmiwal, Variable dimension filter for maneuvering target tracking, IEEE Transactions on Aerospace and Electronic Systems AES-18 (5) (September 1982), pp. 621–629. Full Text via CrossRef | View Record in Scopus | Cited By in Scopus (105)

[15] S.S. Blackman, Multiple Target Tracking with Radar Applications, Artech House, Norwood, MA (1986).

[16] J.R. Cloutier and C.F. Lin, Maneuvering target tracking via smoothing and filtering through measurement concatenation, AIAA Journal of Guidance, Control, and Dynamics 16 (2) (March to April 1993), pp. 377–384. Full Text via CrossRef | View Record in Scopus | Cited By in Scopus (8)

[17] X.R. Li, V.P. Jilkov, A survey of maneuvering target tracking—Part IV: decision-based methods, in: Proceedings of the 2002 SPIE Conference on Signal and Data Processing of Small Targets, vol. 4728, Orlando, USA, April 2002, pp. 511–534. Full Text via CrossRef | View Record in Scopus | Cited By in Scopus (26)

[18] S.C. Lee and C.Y. Liu, Trajectory estimation of reentry vehicle by use of on-line input estimator, Journal of Guidance, Control, and Dynamics 22 (6) (1999).

[19] E. Bekir, Adaptive Kalman filter for tracking maneuvering targets, AIAA Journal of Guidance 6 (5) (September 1983), pp. 414–416. Full Text via CrossRef | View Record in Scopus | Cited By in Scopus (5)

[20] S.S. Blackmanand and R.F. Popoli, Design and Analysis of Modern Tracking Systems, ArtechHouse, Norwood, MA (1999).

[21] C. Liu, H. Wang and P.C. Tuan, Input estimation algorithms for reentry vehicle trajectory estimation, Defense Science Journal 55 (4) (October 2005), pp. 361–375. View Record in Scopus | Cited By in Scopus (4)


Corresponding Author Contact InformationCorresponding author.

Signal Processing
Volume 90, Issue 7, July 2010, Pages 2319-2326
Result list | previous < 1 of 1 > next 
 
Home
Browse
Search
- selected
My Settings
Alerts
Help
Elsevier.com (Opens new window)
About ScienceDirect  |  Contact Us  |  Information for Advertisers  |  Terms & Conditions  |  Privacy Policy
Copyright © 2010 Elsevier B.V. All rights reserved. ScienceDirect® is a registered trademark of Elsevier B.V.