Image enhancement (Nâng cao chất lượng hình ảnh)

 A histogram is typically plotted as a bar chart where the horizontal axis corresponds to the dynamic range of the image and the height of each bar corresponds to the sample count or th

Image Enhancement

Tr ườ ng Cao Đ ng Nguy n Tấất Thành ẳ ễ

Ngành k thu t y sinh ỹ ậ

Digital subtraction angiography

=

Dual energy

 Nh ng v t li u khác nhau có h sốấ hấấp th tia X khác nhauữ ậ ệ ệ ụ có th t o nh t nhiềều m c ể ạ ả ừ ứ

năng lượng khác nhau

 Đi m bấất l i c a pp này là ch p nhiềều lấền v i kV khác nhauể ợ ủ ụ ớ

Dual energy

 Dùng filter đốềng đ t o ra các m c năng lể ạ ứ ượng khác nhau

 V i tấấm đấều tiền s cho qua toàn b ph tia X nh cách ch p X quang thống thớ ẽ ộ ổ ư ụ ường

 Tấấm th 2 ch cho qua tia X năng lứ ỉ ượng cao

 Xương và các cấấu trúc có canxi hấấp thu tia thành phấền X năng lượng thấấp còn tia X năng

lượng cao có th đi qua nh ng mố có m t đ thấấpể ữ ậ ộ

Dual energy

Gamma correction

 γ = 0.3 1 2

Gamma correction

 γ = 0.3 γ = 1 γ = 2

Gamma correction

1 Tăng c ườ ng đ t ộ ươ ng ph n ả

Thay đ i qua c a s cổ ử ổ ường đ sáng (intensity window)ộ

Histogram

 A histogram is typically plotted as a bar chart where the horizontal axis corresponds to the dynamic range of the image and the height of each bar corresponds to the sample count or the probability

 The spread of the histogram relates directly to image contrast where

 narrow histogram distributions are representative of low contrast images

 wide distributions are representative of higher contrast images

16

Histogram Example

17

Histogram Example

The image is characterized by low contrast This is reflected in the histogram which shows that most samples are in a narrow region of the dynamic range (little information below 40 or above 190).

18

Some Typical Histograms

• The shape of a histogram provides useful information for

contrast enhancement

Dark image

Bright image

Low contrast image

High contrast image

Histogram Equalization

 Histogram equalization is a powerful point processing enhancement technique that seeks to optimize the contrast of an image at all points

 As the name suggests, histogram equalization seeks to improve image contrast by

flattening, or equalizing, the histogram of an image

 In image processing, a histogram is a histogram of sample values

 For an 8-bit image there will be 256 possible samples in the image and the histogram will simply count the number of times that each sample value actually occurs in the image.

23

 Non-linear point processing technique that attempts to flatten the histogram such that there are equal

numbers of each sample value in the image.

24

Example Original image and its histogram

Histogram equalized image and its histogram

Example

Other ways to display Histograms

 Consider an image f The simplest way to plot its histogram is to use imhist with no output specified:

>> imhist (f);

Figure 3.7(a) shows the result.

1 Phấn vùng d a vào s t ự ự ươ ng t vềề c ự ườ ng đ ộ

K thu t 1: ỹ ậ Đ t ng ặ ưỡ ng (thresholding)

 Ngưỡng đ nơ

 Đa ngưỡng

Tài li u tham kh o ệ ả

 Biomedical image analysis