1.

Introduction

The recognition and classification of objects based on their visual similarity has become a central task in current industrial imaging systems. With increasing amounts of real-world image data to be processed and stored, the development of powerful retrieval tools also has become necessary in machine vision applications. Along with texture and color, shape is an essential feature used to describe the objects in the images. Therefore, effective shape description is essential in retrieval systems.

Due to the increasing number of on-line solutions, computational lightness is nowadays considered equally important as classification accuracy. In retrieval, computational efficiency of a particular descriptor is generally dependent on two matters, descriptor dimensionality and matching procedure.

The Fourier descriptor (FD)¹ is probably the best-known boundary-based shape descriptor. It has been proven to outperform most other boundary-based methods in terms of retrieval accuracy and efficiency.² In addition to good retrieval and classification performance, the main advantages of FDs are that (1) they are compact and computationally light, (2) they are easy to implement, (3) their matching is straightforward, (4) they are very easy to normalize to be scale and rotation invariant, and (5) their sensitivity to noise is low.

Wavelet transforms³ have been widely used in multiscale image analysis and also have a few applications in shape description. In Ref. 4, the wavelet descriptors (WDs) are based on zero-crossing points of wavelet approximation of the shape and hence the similarity measurement is dependent on the shape complexity. In Ref. 5, moment invariants are employed in shape description using wavelets. It is also possible to combine wavelets with Fourier descriptors, which yields to rotation and scale invariance. This can be made based on polar coordinates of a shape⁶ or by Fourier transforming the wavelet coefficients obtained from the complex-valued boundary function.⁷ On the other hand, when WDs are formed using several scales, the resulting feature vector is typically high dimensional due to spatial information caused by multiple scales.

In this paper, we present an effective approach to wavelet-based shape representation at single scale. We show that it is possible to form rotation and translational invariant WDs, whose matching is as simple and fast as that of FDs. The proposed approach is applied to a practical industrial image retrieval and classification problem.

2.

Shape Description

The contour-based shape description is based on one-dimensional boundary function (shape signature). Let $(x_k,y_k)$ , $k=0,1,2,\dots ,N-1$ represent the object boundary coordinates, in which $N$ is the boundary length. Complex coordinate function $z\left(k\right)$ (Ref. 2) expresses the boundary points in an object centered coordinate system:

3.

Experiments with Industrial Defect Shapes

The validation presented in this section is twofold. Simple classification experiments are first carried out to show the influence of scale selection on the shape description. The second part of the validation, the retrieval accuracy of the proposed methods, is compared to that of an ordinary FD (contour Fourier). In all the experiments, Euclidean distance and the “leave one out” validation principle are used.

3.1.

Testing Database

For testing purposes, we use defect images that are collected from an industrial process using a paper inspection system.⁹ A reason for collecting defect image databases in process industry is a practical need for controlling the quality of production.⁹ When retrieving images from a database, the defect shape is one essential property describing the defect class. Therefore, effective methods for the shape representation are necessary. The test set consisted of 1204 paper defect shapes, which represented 14 defect classes with each class consisting of 27–103 images (Fig. 1).

Fig. 1

Example contours of each 14-paper defect class in the testing database.

3.2.

Classification and Retrieval

The feature extraction in the testing database was carried out by calculating the descriptors for the images in the database. The dimensionality $\left(L\right)$ was 8 with all the descriptors [Eq. 3]. In the case of the wavelet-based approach, the selected wavelets $\psi$ were first and second order complex Gaussian wavelets that have been implemented in the Matlab wavelet toolbox.⁸ To compare different scales, we made preliminary $k$ -nearest neighbor ( $k$ -NN) classification experiments. Figure 2a presents the average classification rates of the proposed wavelet descriptors at different scales using a 5-NN classifier. In this figure, the classification rate of the contour Fourier descriptor (41.87%) is also presented. The scales that produce the highest classification rates were compared to contour Fourier in the retrieval experiment by calculating average precision versus recall curves for the queries [Fig. 2b].

Fig. 2

(a) The average 5-NN classification rates of the proposed methods using different scales of the first and second order complex Gaussian wavelets. (b) Average precision/recall curves of the queries using proposed descriptors that employ the first and second order complex Gaussian wavelets the scales 16 and 2, respectively.

4.

Discussion

In this paper, we showed that it is possible to overcome the difficulties with shape description using wavelet coefficients (rotational variance and complicated matching) by Fourier transforming the coefficients. The results of the classification and retrieval experiments reveal that the proposed wavelet-based shape description approach clearly outperforms ordinary FDs in defect shape description. It is also essential to note that the proposed descriptors have the same dimensionality and matching procedure as FDs. The computational cost of the feature extraction is somewhat higher than that of FDs due to the wavelet transform. However, the dimensionality of the descriptors is more essential than the feature extraction time, because in retrieval applications the feature extraction is usually an off-line operation. If the computational efficiency of feature extraction is critical, the cost of wavelet transform can be decreased using the algorithm presented in Ref. 10.