Đang chuẩn bị liên kết để tải về tài liệu:
Biosignal and Biomedical Image Processing MATLAB-Based Applications Muya phần 10

Tham khảo tài liệu 'biosignal and biomedical image processing matlab-based applications muya phần 10', ngoại ngữ, anh văn thương mại phục vụ nhu cầu học tập, nghiên cứu và làm việc hiệu quả | Image Segmentation 359 Isolated Segments Figure 12.13 Isolated segments produced by thresholding the lowpass filtered image in Figure 12.12. The rightmost segment was found by applying logical operations to the other two images. Q Define filters and functions I-D range function range inline max x min x h_lp fspecial gaussian 20 4 Q. Directional nonlinear filter I_nl nlfilter I 91 range I_h imfilter I_nl 2 h_lp Average lowpass filter Q. subplot 2 2 1 imshow Display image and histogram I_nl 2 before lowpass filtering title Modified Image and after lowpass filtering subplot 2 2 2 imhist I_nl title Histogram subplot 2 2 3 imshow I_h 2 Display modified image title Modified Image subplot 2 2 4 imhist I_h title Histogram Q. figure BW1 im2bw I_h .08 Threshold to isolate segments BW2 im2bw I_h .29 BW3 BW1 BW2 Find third image from other two subplot 1 3 1 imshow BW1 Display segments subplot 1 3 2 imshow BW2 subplot 1 3 3 imshow BW3 Copyright Marcel Dekker Inc. All rights reserved. Marcel Dekker Inc. 270 Madison Avenue New York New York 10016 TLFeBOOK 360 Chapter 12 The image produced by the horizontal range operator with and without lowpass filtering is shown in Figure 12.12. Note the improvement in separation produced by the lowpass filtering as indicated by a better defined histogram. The thresholded images are shown in Figure 12.13. As in Example 12.2 the separation is not perfect but is quite good considering the challenges posed by the original image. Multi-Thresholding The results of several different segmentation approaches can be combined either by adding the images together or more commonly by first thresholding the images into separate binary images and then combining them using logical operations. Either the AND or OR operator would be used depending on the characteristics of each segmentation procedure. If each procedure identified all of the segments but also included non-desired areas the AND operator could be used to reduce artifacts. An example of the use of