تشخيص لبه با استفاده از تبديل ويولت مختلط گسسته

Edge Detection Using Discrete Complex Wavelet Transform

Analysis and interpretation ofmedical images are of clinical importance for medical diagnosis and treatment while they also have technical implications for computer vision and pattern recognition. In this context, one of the most fundamental issues is the detection of object boundaries, wttich is often useful for further processes such as organ/tissue recognition, image registration, motion analysis, measurement ofanatomical and plrysiological parameters, etc. Although one ofthe best methods of edge detection l"i based on wavelet transform, the standard wavelet transform bas its own shortcomings such as lack of shift invariant and lack of directional selectivity ill sub-bands in multidimensional applications. TIre discrete complex wavelet transform, which is bllsed on complex mother wavelet,not onty overcomes these shortcomings hut 1/(0ʹ acceptable redundancy and complexity as well. It is especiatty useful for multidimensional situations and for high accuracy appticatians such as medical image processing. tn thls paper, the shortcomings ofordinary wavelet transform are lnitiatty investigated and comparisons are made between the .ʹilaIJdard wavelet and the comote..x wavelet. rile", tile discrete complex ....avetet domain is appliedfor image enhancement and edge detection of noisy images. The stmatanon results show that our method exhibits a better performance, especiatty in noisy cases, as compared with the standord waveletand spatial methods.