改进的自适应阈值方法用于文字图像边缘检测

Improved Adaptive Threshold Method and Its Application in Character Image Edge Detection

在图像的边缘检测中,利用模角分离的小波变换,结合尺度独立的算法区分了阶梯型边界和跳跃型边界,从而提取了阶梯型边界。上述算法中需选择峰值阈值,将小波变换系数较小的点滤掉,但是一幅图像中边缘的奇异性并不均匀,对变换后的整幅图像取同一阈值,那么微弱边缘将会随着因灰度不均匀、噪声等被滤除。针对这一问题提出了改进的自适应阈值方法,并将此阈值方法代替固定阈值,在文字图像边缘检测中取得了较好的效果。

In the image edge detection, the bounds of step-structure and dirac-structure are distinguished by using modular-angle-separated wavelet transform and the scale-independent algorithm, thus obtaining the bound of the step-structure. The threshold value of the peak value is chosen to filter the points with small wavelet transform coefficients in the scale-independent algorithm. However, the singularity of the edge in an image is not uniform, the faintness edge will be filtered with the non-uniform of gray-scale and noise, etc. when taking the same threshold from the transformed whole image. To solve this problem, the improved adaptive threshold method is presented and the fixed threshold method is substituted. Good effect is achieved in the edge detection of character image. The algorithm is simple and easy to be realized.