Image Detection of Rice Fissures Using Biorthogonal B-Spline Wavelets in Multi-resolution Spaces

An image analysis method was developed with higher detection accuracy for rice fissures compared with using the classical Canny and Sobel methods. The rice images are obtained using a common scanning machine with resolution of 600 dpi. The scanning images are enhanced by the gamma correction and smoothed using the anisotropic nonlinear diffusion PDEs. The diffusion process is stopped when the peak signal to noise ratio is lower than 30 dB or changes slowly. After that the wavelet coefficients of the smoothed images are calculated using continuous wavelet transform with the biorthogonal B-spline wavelets bior1.5 in multi-resolution spaces. The wavelet coefficients in y forward direction are used as the magnitudes. Finally, the magnitudes are standardized and used for the judgment of the fissures as the local maxima. Two different kinds of rice kernels are used for the test of the effectiveness of the proposed algorithm, including 30 long- and 20 medium-cracked grains with 1, 2, 3, or 4 fissures. The results demonstrate a satisfying performance of the fissure detecting systems, and even the faint lines of the fissures can also be detected.