Week 12: Introduction to image processing

class: center, middle
# Introduction to Image Processing

Eslam Adel

email: `eslam.a.mahmoud@eng1.cu.edu.eg`
---
    
### Fundamental Block Diagram of Image Processing

---

### Image Acquisition

**Digital Camera**

* Matrix of CCD elements (photodiodes)

---

* Each pixel has 4 sensors (1 Red, 1 Blue, 2 Green)

<img src="../../images/pixels.png"  width ="80%" >
---

* Image projection

<img src="../../images/projection.png"  width ="80%" >
---

### Digital Image

---

* Digital image is a matrix of pixels
Color of each pixel is determined by its RGB values

---

* For grayscale images only one channel determine the gray level

---

### Resizing images

**The Original Image**

```python
from scipy.misc import imresize
import matplotlib.pyplot as plt

im = plt.imread('black-dog.png')
```

**Resize the image**

```python
resizeFactors = [1, 0.2, 0.1, 0.05]
for factor in resizeFactors:
    plt.figure()
    plt.imshow(imresize(im, (int(im.shape[0]*factor), int(im.shape[1]*factor))))
    plt.title('Resized image with factor ' + str(factor))
plt.show()
```
---
The output

<img src="../../images/Figure_1.png"  width ="80%" >
---

---

---
<img src="../../images/Figure_4.png"  width ="80%" >
---

### Image Enhancement

Enhancing image contrast

```python 
import cv2 
import numpy as np

img = cv2.imread('PgaNb.png',0)
equ = cv2.equalizeHist(img)
res = np.hstack((img,equ)) #stacking images side-by-side
cv2.imwrite('res.png',res)
```

---

Output

---

### Image Segmentation

Convert the image to segments or isolated objects

---

### Recognition and Interpretation

* Face and eye detection

---

* Person detection

---

* Object detection (car)

---

* Object recognition

---

* Machine learning and classification