Presentasi sedang didownload. Silahkan tunggu

Presentasi sedang didownload. Silahkan tunggu

Sumber : Cris Salomon, “Fundamental of Digital Image Processing”

Presentasi serupa


Presentasi berjudul: "Sumber : Cris Salomon, “Fundamental of Digital Image Processing”"— Transcript presentasi:

1 Sumber : Cris Salomon, “Fundamental of Digital Image Processing”
PIKSEL Sumber : Cris Salomon, “Fundamental of Digital Image Processing”

2 Pixel adalah singkatan dari “Picture element”
Berisi (x,y)  baris, kolom unsur pokok pembentuk citra digital. Informasi yang dibawa piksel bermacam-macam tergantung type citra yang akan diproses. Operasi pada citra dapat berupa individual pixel (point transforms), atau distribusi piksel (global transforms)

3

4

5 Operasi aritmatik pada citra

6 Secara sederhana suatu citra bisa ditransformasi dengan operasi aritmatik atau logika.
Jika ada 2 citra IA dan IB dan sebuah konstanta C , bisa dilakukan operasi : Ioutput = IA + IB Ioutput = IA + C Jika diberlakukan pada individual pixel (i,j) Ioutput(i,j) = IA(i,j) + IB(i,j) Ioutput = IA(i,j) + C

7 Penjumlahan dan pengurangan pada citra
Figure 2: Image contrast adjustment and blending using arithmetic addition

8 Contrast adjustment, menambahkan nilai konstan posistif C pada masing-masing lokasi piksel.  mencerahkan Blending, menjumlahkan citra pada suatu citra untuk mendapatkan citra gabungan.

9

10 Figure 3 : Image differencing using arithmetic subtraction

11 Ketika gambar A dikurangi gambar B, maka :
Ioutput = │IA - IB │

12 Image multiplication and division

13

14 Logical operations on images
standard logical operations between images such as NOT, OR, XOR and AND NOT : negasi Ioutput (i,j) = MAX - Ioutput (i,j) Where MAX is the maximum possible value in the given image representation. Thus, for an 8-bit grey-scale image (or for 8-bit channels within a colour image), MAX 255.

15 OPERATOR not

16 OPERATOR OR/XOR, AND OR/XOR untuk proses pada citra biner (0,1). Di aplikasikan pada proses thresholding greylevel. AND digunakan untuk mendeteksi perbedaan pada citra, mencerahkan bagian tertentu.

17

18 Thresholding Thresholding produces a binary image from a grey-scale or colour image by setting pixel values to 1 or 0 depending on whether they are above or below the threshold value. This is commonly used to separate or segment a region or object within the image based upon its pixel values

19

20

21

22 The im2bw function automatically converts colour images (such as the input in the example) to grayscale and scales the threshold value supplied (from0 to 1) according to the given quantization range of the image being processed. For grey-scale images, whose pixels contain a single intensity value, a single threshold must be chosen. For colour images, a separate threshold can be defined for each channel. In many applications, colour images are converted to grey scale prior to thresholding for simplicity.

23 Thresholding of a complex image

24 Point-based operations on images
Digunakan untuk memperbaiki citra dengan meningkatkan kontras. The dynamic range of an image is defined as the difference between the smallest and largest pixel values within the image. In general,we will assume an 8-bit (0 to 255) grey-scale range for both input and resulting output images.

25 Logarithmic transform
Berfungsi untuk brightness. The dynamic range of an image can be compressed by replacing each pixel value in a given image with its logarithm: Ioutput (i, j)= ln Iinput (i, j) , where I(i,j )is the value of a pixel at a location (i, j) in image I and the function ln() represents the natural logarithm.

26 The Logarithmic Transform: Varying the parameter σ changes the gradient of the logarithmic function used for input to output.

27 The effect of the logarithmic transformis to increase the dynamic range of dark regions in an image and decrease the dynamic range in the light regions.

28

29 Exponential transform
The exponential transform is the inverse of the logarithmic transform. The mapping function is defined by the given base e raised to the power of the input pixel value: This transform enhances detail in high-value regions of the image (bright) whilst decreasing the dynamic range in low-value regions (dark) – the opposite effect to the logarithmic transform. suitable for photographic image enhancement

30 c constant whilst varying the exponential base parameter α,

31 we see that the contrast of the background in the original image can be improved by applying the exponential transform, but at the expense of contrast in the darker areas of the image. The background is a high-valued area of the image (bright), whilst the darker regions have low pixel values.

32

33 Power-law (gamma) transform
Rumus : a value of γ > 1 enhances the contrast of high-value portions of the image at the expense of low-value regions, whilst we see the reverse for γ < 1.

34

35

36 Application: gamma correction
A common application of the power-law transform is gamma correction. gamma correction on an image in Matlab using the imadjust function

37

38 Pixel distributions: histograms

39 For a simple grey-scale image, the histogram can be constructed by simply counting the number of times each grey-scale value (0–255) occurs within the image. Each ‘bin’ within the histogram is incremented each time its value is encountered thus an image histogram can easily be constructed. where we see a histogram plot with two distinctive peaks: a high peak in the lower range of pixel values corresponds to the background intensity distribution of the image and a lower peak in the higher range of pixel values (bright pixels) corresponds to the foreground objects (coins)

40

41 Artinya : intensitas warna 60 muncul sebanyak 1712

42 Histograms for threshold selection
In Matlab, we can use the image histogram as the basis for calculation of an automatic threshold value. The function graythresh in Example 3.14 exploits the Otsu method, which chooses that threshold value which minimizes the interclass statistical variance of the thresholded black and white pixels.

43 Example 3.14

44 Contrast stretching Image histograms are also used for contrast stretching (also known as normalization)which operates by stretching the range of pixel intensities of the input image to occupy a larger dynamic range in the output image. We can display the histograms before and after contrast stretching a = 255, b = 0 c = nilai max piksel saat ini, d = nilai min piksel saat ini

45

46

47 Histogram equalization
The second contrast enhancement operation based on the manipulation of the image histogram is histogram equalization. This is one of the most commonly used image enhancement techniques.

48

49 Histogram matching Histogram matching in practice Histogram matching extends the principle of histogram equalization by generalizing the form of the target histogram. It is an automatic enhancement technique in which the required transformation is derived from a (user-) specified target histogram distribution.

50

51 Adaptive histogram equalization
Ketika akan meningkatkan kontras pada area tertentu, operasi histogram equalization saja tidak tepat. Harus digunakan operasi adaptive histogram equalization, kemudian berkembang menjadi contrast-limited adaptive histogram equalization (CLAHE). CLAHE berfungsi meningkatkan kontras, tetapi juga meningkatkan noise. The main idea behind the use of contrast limiting is to place a limit l,0 < l < 1, on the overall (normalized) increase in contrast applied to any given region.

52 where we see the differing effects of the specified contrast limit l and target distribution t on the resulting adaptively equalized image. Adaptive histogram equalization can sometimes effect significant improvements in local image contrast.

53 Histogram operations on colour images
To improve the contrast of colour images is a slightly more complex issue than for grey-scale intensity images. At first glance, it is tempting to consider application of histogram equalization or matching independently to each of the three channels (R,G,B) of the true colour image.

54 In order to perform such histogram operations on colour images, we thus
(a) transform the RGB component image to the HSV representation (hue, saturation, variance), (b) apply the histogram operation to the intensity component and finally (c) Convert the result back to the RGB colour space as required.

55

56


Download ppt "Sumber : Cris Salomon, “Fundamental of Digital Image Processing”"

Presentasi serupa


Iklan oleh Google