科研之友
微信
新浪微博
Facebook
分享链接
摘要
A novel image enhancement algorithm for faint pavement cracks is proposed, based on the finite ridgelet transform (FRIT). In high-resolution FRIT subbands, typical linear singularities of the image are represented by a few coefficients, while randomly located noisy singularities are unlikely to produce significant coefficients. The parameters of an enhancement function can be determined through analyzing the distribution of the high-resolution FRIT coefficients. Therefore, a scheme based on modifying FRIT coefficients should be very effective in enhancing the linear singularities and suppressing the noise. In general, an entire pavement crack is a curve. A smooth partition method is proposed to divide a pavement crack image into local windows where the crack looks straight. Then the FRIT-based enhancement method can be applied to each piece of the whole crack. Experiments verify that faint crack signals submerged in the complicated background can be displayed efficiently by this algorithm.
