Date of Award
Dr.Dimitrios Charalampidis, Ph.D.
This thesis discusses image processing and ﬁltering techniques with emphasis on Mean ﬁlter, Median ﬁlter, and diﬀerent versions of the Iterative Truncated Arithmetic Mean (ITM) ﬁlter. Speciﬁcally, we review in detail the ITM algorithms (ITM1 and ITM2) proposed by Xudong Jiang. Although ﬁltering is capable of reducing noise in an image, it usually also results in smoothening or some other form of distortion of image edges and ﬁle details. Therefore, maintaining a proper trade oﬀ between noise reduction and edge/detail distortion is key. In this thesis, an improvement over Xudong Jiang’s ITM ﬁlters, namely ITM3, has been proposed and tested for diﬀerent types of noise and for diﬀerent images. Each of the two original ITM ﬁlters performs better than the other under diﬀerent conditions. Experimental results demonstrate that the proposed ﬁlter, ITM3, provides a better trade oﬀ than ITM1 and ITM2 in terms of attenuating diﬀerent types of noise and preserving ﬁne image details and edges.
Surampudi Venkata, Prathyusha, "Improved Iterative Truncated Arithmetic Mean Filter" (2018). University of New Orleans Theses and Dissertations. 2514.