In order to improve the strip surface defect recognition and classification accuracy and efficiency, Rough Set (RS) attribute reduction algorithm based on Particle Swarm Optimization (PSO) algorithm was used on the optimal selection of strip surface defect image decision features, which removed redundant attributes, provided reduction data for the follow-up Support Vector Machine (SVM) model, reduced vector machine learning time, and constructed the SVM classifier, which uses Second-Order Cone Programming (SOCP) and multikernel Support Vector Machine classification model. Six kinds of typical defects such as rust, scratch, orange peel, bubble, surface crack, and rolled-in scale are recognized and classification is made using this classifier. The experimental results show that the classification accuracy of the proposed algorithm is 99.5%, which is higher than that of SVM algorithm and Relevance Vector Machine (RVM) algorithm. And because of using the Rough Set attribute reduction algorithm based on PSO algorithm, the learning time of SVM is reduced, and the average time of the classification and recognition model is 58.3 ms. In summary, the PSO-RS&SOCP-SVM evaluation model is not only more efficient in time, but also more worthy of popularization and application in the accuracy.
Strip surface defect recognition is a kind of pattern recognition problem with multifeatures and multitypes, which is quite complicated. The features of different types of image will have some overlap, which will cause some dimension of image features in a certain correlation. Some distortion of image description leads to mismatch of subsequent recognition. And high dimensional feature data is not conducive to the computational process of image feature clustering recognition, resulting in low efficiency, and cannot meet the rapidity and effectiveness of recognition.
In recent years, the methods used for feature selection and dimension reduction include exhaustive method, branch and bound method, TaBu search algorithm and simulated annealing algorithm, self-organizing neural network method, Principal Component Analysis (PCA) method, Genetic Algorithm (GA), Locally Linear Embedding (LLE) method, and Locality Preserving Mapping (LPM) method. But of these algorithms, some are easy to fall into local optimal solution, and some may damage the topological structure of the data. Genetic Algorithm is an efficient optimization method, but its complex genetic operation makes it difficult to meet the expectations in convergence speed and accuracy. These algorithms cannot take into account the validity of the defect characteristics and reduce the complexity of the computation time when the features of the surface defect of steel are optimized. Relief F series algorithm [
In view of this situation, it is necessary to further study the new feature selection and dimension reduction method, so as to meet the needs of cold strip steel surface defect detection. Pawlak proposed the Rough Set (RS) theory [
Therefore, we study the decision feature selection and classification of the cold rolled strip shape defect images based on Rough Set theory and Support Vector Machine. Firstly, for six kinds of typical defects of strip steel surface such as rust, scratch, orange peel, bubble, surface crack, rolled-in scale, twenty-dimensional feature vectors such as the geometry, gray, and texture features are extracted to construct the decision table of defect recognition, and the RS attribute reduction algorithm is used to eliminate the contradictory, not important, redundant attributes. Then the key indicators that reflected the defects are obtained, which can provide simplified modeling data to the SVM model. This process can reduce the learning time of SVM. Secondly, for the high dimension decision table, the calculation speed of common attribute reduction methods is very slow. We study the attribute reduction algorithm based on evolutionary computation used to deal with the high dimension decision table. Then, the simplified information is used as the modeling data of SVM, and the SVM is used to classify and identify the information. Thirdly, in order to improve the classification accuracy, the design and construction of multikernel SVM classifier is designed, and the multikernel learning is transformed into Second-Order Cone Programming (SOCP) problem. Finally, the proposed model is used to classify and identify the surface defect images of the steel strip, and the effectiveness of the proposed method is verified.
Rough Set theory is a kind of mathematical tools that described the characterization of incomplete and uncertain data, which can effectively analyze and process all kinds of incomplete, imprecise, and inconsistent information and discover the implicit knowledge and reveal the potential rules [
The attribute reduction of RS is used to remove the redundant attributes of the discrete data set, and the classification ability does not change. It is to select the best attributes subset from the entire attributes set. However, finding the optimal subset of attributes has been proved to be NP-hard problem [
The traditional attribute reduction methods, like the differential matrix method, reduction method based on the importance, and so on, can find all reduction in the decision table [
We only introduce some basic concepts of minimal attribute reduction in Rough Set in this paper [
For
Let
If
Suppose the set
The minimum attribute reduction problem can be described as
Generate initial particle swarm. The fitness function is evaluated for each particle in the population. For each particle, if its current adaptation is better than the past, the current value is set to a new Determine whether the termination condition is satisfied: if it is satisfied then transfer to step (5); otherwise go to step (2). The termination conditions can reach a certain number of iterations or can achieve the evaluation function value of the Particle Swarm Optimization, and so on. To test each particle of the end groups by reduction definitions, obtain all candidate reductions in end groups, and then, to delete the redundant attributes, obtain the final reduction set.
Fitness function is the most important part of evolutionary computation, and the goal of attribute reduction is the minimal conditional attribute set with the same dependence as the original condition attribute set. The particle fitness function is designed as follows:
Second-Order Cone Programming (SOCP) is a class of convex programming problem [
The original optimization problem of SVM (soft-margin) is depicted in the following [
The convex linear combination of kernel learning multiple (MKL) kernel matrix is as follows [
The Second-Order Cone Programming form of multikernel Support Vector Machine is
The establishment of PSO-RS&SOCP-SVM recognition model is shown in Figure
PSO-RS&SOCP-SVM recognition model.
Steps of feature selection and classification recognition of strip surface defects are as follows.
The hardware conditions of PC in the experimental operation are as follows: CPU is Intel Core i5 760 with 2.8 GHz and 2 GB memory; the software platform is Windows 7 operating system; the simulation software is Matlab 7.0.
The strip defect images in this experiment are collected in a steel plant. The configuration of the image acquisition system is shown in Figure
The image acquisition system.
We choose the most common 6 kinds of defects as the typical research object: rust (100) and scratch (100), orange peel (100), bubble (100), surface crack (100), and rolled-in scale (100); a total of 600 samples are used to carry on the analysis. The defect images are shown in Figures
Strip surface defect image.
Rust
Scratch
Orange peel
Bubble
Surface crack
Rolled-in scale
Twenty-dimensional features are selected: the geometrical features, the gray features, and the texture features, and then the defect images classification is carried on in real-time. Feature parameters are shown in Table
Strip surface defect image characteristic parameters.
Types | Feature parameters |
---|---|
Geometrical features | Elongation, rectangle degree, area, perimeter, invariant moments (from first order to seventh order) |
Gray features | Mean, variance, gray entropy |
Texture features | Energy, inertance, consistency, roughness, contrast, direction |
Firstly, edge extraction of steel strip surface defect images is carried on, as shown in Figure
Edge extraction of strip surface defect images.
Rust
Scratch
Orange peel
Bubble
Surface crack
Rolled-in scale
Specifically, the condition attributes of decision table are set to
Here, a total of 600 samples were used as training samples. The attribute values formed a two-dimensional table, each row describes an object, and each column describes an attribute of the object. So a decision table with
Decision table for feature values.
Samples | Condition attributes | Decision attribute | ||||||
---|---|---|---|---|---|---|---|---|
|
|
|
|
|
|
|
||
1 | 0.9631 | 0.1961 | 1.5854 |
|
48.7209 | 22.9058 | 0.0742 | 1 |
2 | 0.4281 | 0.0248 | 1.6887 |
|
49.2755 | 23.0152 | 0.1722 | 1 |
| ||||||||
101 | 0.9832 | 0.0788 | 1.6161 |
|
47.0690 | 47.9997 | 0.1212 | 2 |
102 | 0.9933 | 0.0257 | 1.7238 |
|
47.7351 | 48.5634 | 0.7985 | 2 |
| ||||||||
201 | 0.5000 | 1.1025 | 1.5535 |
|
48.2467 | 36.7637 | 0.7000 | 3 |
202 | 0.9922 | 1.1279 | 1.6674 |
|
47.2867 | 50.4636 | 0.3560 | 3 |
| ||||||||
301 | 0.4502 | 0.6261 | 1.6462 |
|
48.4786 | 44.2349 | 0.1366 | 4 |
302 | 0.3793 | 0.5713 | 1.7531 |
|
48.7531 | 44.5065 | 0.4497 | 4 |
| ||||||||
401 | 0.9094 | 0.1296 | 1.4291 |
|
51.3118 | 51.0527 | 0.1742 | 5 |
402 | 0.9378 | 0.3306 | 1.5321 |
|
47.6995 | 25.4727 | 0.3737 | 5 |
| ||||||||
599 | 0.8767 | 0.0538 | 2.1107 |
|
48.6042 | 39.7279 | 0.1591 | 6 |
600 | 1.0000 | 0.0921 | 2.0185 |
|
50.0884 | 11.9853 | 0.4944 | 6 |
The discretization intervals of each feature attribute are shown in Table
Discretization interval of each feature attribute.
Condition attribute | Discretization interval |
---|---|
|
[ |
|
[ |
|
|
|
[ |
|
|
According to the discretization interval of Table
Feature attribute after discretization.
Samples | Condition attributes | Decision attribute | ||||
---|---|---|---|---|---|---|
|
|
|
|
| ||
1 | 2 | 1 |
|
1 |
|
1 |
2 | 0 | 0 |
|
1 |
|
1 |
|
|
| ||||
101 | 2 | 0 |
|
0 |
|
2 |
102 | 2 | 0 |
|
0 |
|
2 |
|
|
| ||||
201 | 0 | 1 |
|
0 |
|
3 |
202 | 2 | 1 |
|
0 |
|
3 |
|
|
| ||||
301 | 0 | 1 |
|
1 |
|
4 |
302 | 0 | 1 |
|
1 |
|
4 |
|
|
| ||||
401 | 1 | 1 |
|
1 |
|
5 |
402 | 1 | 1 |
|
0 |
|
5 |
|
|
| ||||
599 | 1 | 0 |
|
1 |
|
6 |
600 | 2 | 0 |
|
1 |
|
6 |
Attribute reduction is carried on the discretization data in Table
Attribute reduction result.
Reduction | Support | Length | |
---|---|---|---|
1 |
|
100 | 8 |
Finally, the attribute values under reduction are input to the SOCP-SVM model to classify and recognize the strip surface defect. Gaussian radial basis functions are chosen as the kernel function, and the classification and recognition results were compared with that of the SVM algorithm and the RVM algorithm. Performance comparison is shown in Table
The classification and recognition performance comparison of SVM, RVM, and PSO-RS&SOCP-SVM.
Defect type | Rust | Scratch | Orange peel | Bubble | Surface crack | Rolled-in scale |
---|---|---|---|---|---|---|
The number of test samples | 100 | 100 | 100 | 100 | 100 | 100 |
SVM | ||||||
Recognition rate (%) | 99 | 97 | 98 | 96 | 100 | 95 |
The average running time (ms) | 63.5 | 67.6 | 78.6 | 80.2 | 69.3 | 68.5 |
RVM | ||||||
Recognition rate (%) | 100 | 98 | 99 | 98 | 100 | 96 |
The average running time (ms) | 78.4 | 82.3 | 82.1 | 88.5 | 79.4 | 77.1 |
PSO-RS&SOCP-SVM | ||||||
Recognition rate (%) | 100 | 100 | 100 | 99 | 100 | 98 |
The average running time (ms) | 52.3 | 60.5 | 55.8 | 62.8 | 60.1 | 58.5 |
From Table
The classified ROC curves, respectively, corresponding to the traditional multikernel SVM algorithm and PSO-RS&SOCP-SVM algorithm are shown in Figure
Classified ROC curve.
The traditional multikernel SVM algorithm
PSO-RS&SOCP-SVM algorithm
From Figure
In summary, the PSO-RS&SOCP-SVM model is feasible and effective in the surface defect feature selection and classification.
In order to improve the strip steel surface defect classification recognition accuracy and reduce the running time of recognition, feature selection of steel strip surface defect images based on RS algorithm and PSO algorithm for attribute reduction method is introduced in this paper. Thereby the sample feature dimensions are reduced and the modeling data are simplified. Then the traditional multikernel SVM model is optimized based on SOCP, which can optimize the parameters of the multikernel SVM model. Experimental results show that its application effect is remarkable, and it is superior to the traditional SVM and RVM algorithm in recognition accuracy and efficiency. In the next step of research, we try to study how to further reduce the time complexity of multikernel learning, so as to meet the real-time requirement.
The authors declare that they have no competing interests.
This work was supported by the National Natural Science Foundation of China (no. 51208168) and Hebei Province Foundation for Returned Scholars (no. C2012003038).