From e09aa90e0e388d4c42e38381961bc3fa1771cff3 Mon Sep 17 00:00:00 2001
From: Nguyễn Gia Phong <mcsinyx@disroot.org>
Date: Wed, 8 Jul 2020 14:11:07 +0700
Subject: [usth/ICT2.{5,12}] Process images and base data

---
 usth/ICT2.12/labwork/1             |  55 +++++++++++++++++++++++++++++++++++++
 usth/ICT2.12/labwork/1.pdf         | Bin 0 -> 1376916 bytes
 usth/ICT2.12/labwork/2             |  54 ++++++++++++++++++++++++++++++++++++
 usth/ICT2.12/labwork/2.pdf         | Bin 0 -> 1348500 bytes
 usth/ICT2.12/labwork/dino-gang.jpg | Bin 0 -> 53971 bytes
 5 files changed, 109 insertions(+)
 create mode 100755 usth/ICT2.12/labwork/1
 create mode 100644 usth/ICT2.12/labwork/1.pdf
 create mode 100755 usth/ICT2.12/labwork/2
 create mode 100644 usth/ICT2.12/labwork/2.pdf
 create mode 100644 usth/ICT2.12/labwork/dino-gang.jpg

(limited to 'usth/ICT2.12/labwork')

diff --git a/usth/ICT2.12/labwork/1 b/usth/ICT2.12/labwork/1
new file mode 100755
index 0000000..2590192
--- /dev/null
+++ b/usth/ICT2.12/labwork/1
@@ -0,0 +1,55 @@
+#!/usr/bin/env python3
+from cv2 import (
+    THRESH_BINARY, ADAPTIVE_THRESH_MEAN_C,
+    adaptiveThreshold as adaptive_threshold, calcHist as calc_hist, blur,
+    equalizeHist as equalize_hist, GaussianBlur as gaussian_blur,
+    imread, imshow, Laplacian as laplacian, medianBlur as median_blur,
+    resize, Sobel as sobel, threshold, waitKey as wait_key)
+from numpy import uint8
+
+FILENAME = 'dino-gang.jpg'
+GREYSCALE_COEFF = 0.2126, 0.7152, 0.0722
+THRESHOLD, WHITE = 128, 255
+BLUR_KSIZE = 6, 9
+
+
+def disp(image, name):
+    """Display the given image."""
+    imshow(name, image.astype(uint8))
+    wait_key()
+
+
+# Exercise 1
+image = imread(FILENAME)
+disp(image, 'original')
+
+# Exercise 2
+disp(resize(image, (512, 512)), 'square')
+
+# Exercise 3
+# I'm going to ignore about cv2.IMREAD_GRAYSCALE
+grey_image = uint8(image.dot(GREYSCALE_COEFF))
+disp(grey_image, 'grey')
+
+# Exercise 4
+a, b = 1/2, 1/3
+disp(image*a+b, 'brightness adjusted')
+
+# Exercise 5
+disp(threshold(grey_image, THRESHOLD, WHITE, THRESH_BINARY)[-1],
+     'binary threshold')
+disp(adaptive_threshold(grey_image, WHITE, ADAPTIVE_THRESH_MEAN_C,
+                        THRESH_BINARY, 25, 12), 'adaptive threshold')
+
+# Exercise 6
+hist = calc_hist([grey_image], [0], None, [256], [0, 256])
+disp(equalize_hist(grey_image), 'equalized')
+
+# Exercise 7
+disp(blur(image, BLUR_KSIZE), 'blur')
+disp(gaussian_blur(image, (0, 0), 5), 'Gaussian blur')
+disp(median_blur(image, 7), 'median blur')
+
+# Exercise 8
+disp(laplacian(image, 2), 'Laplacian')
+disp(sobel(image, 2, 1, 1), 'Sobel')
diff --git a/usth/ICT2.12/labwork/1.pdf b/usth/ICT2.12/labwork/1.pdf
new file mode 100644
index 0000000..b7286d0
Binary files /dev/null and b/usth/ICT2.12/labwork/1.pdf differ
diff --git a/usth/ICT2.12/labwork/2 b/usth/ICT2.12/labwork/2
new file mode 100755
index 0000000..af253ed
--- /dev/null
+++ b/usth/ICT2.12/labwork/2
@@ -0,0 +1,54 @@
+#!/usr/bin/env python3
+from cv2 import (
+    COLOR_BGR2GRAY, KMEANS_RANDOM_CENTERS, THRESH_BINARY, TERM_CRITERIA_EPS,
+    TERM_CRITERIA_MAX_ITER, Canny as canny, cvtColor as cvt_color,
+    HoughLines as hough_lines, imread, imshow, inRange as in_range, kmeans,
+    Laplacian as laplacian, line, Sobel as sobel, threshold,
+    waitKey as wait_key)
+from numpy import cos, float32, pi, sin, uint8
+
+FILENAME = 'dino-gang.jpg'
+THRESHOLD, WHITE = 128, 255
+CANNY_THRESH = 69
+
+
+def disp(image, name):
+    """Display the given image."""
+    imshow(name, image.astype(uint8))
+    wait_key()
+
+
+image = imread(FILENAME)
+disp(image, 'original')
+
+# Exercise 1
+# Requiring all three channels to be greater than THRESHOLD
+# using in_range produces a blacker result (fewer white points).
+# The information inferred by human (me) is less clear.
+grey = cvt_color(image, COLOR_BGR2GRAY)
+disp(threshold(grey, THRESHOLD, WHITE, THRESH_BINARY)[-1], 'threshold')
+disp(in_range(image, (THRESHOLD,)*3, (WHITE,)*3), 'in range')
+
+# Exercise 2
+disp(laplacian(image, 2), 'Laplacian')
+disp(sobel(image, 2, 1, 1), 'Sobel')
+# Canny produces a lot visible edge comparing to Laplacian and Sobel.
+edges = canny(image, CANNY_THRESH, CANNY_THRESH*2)
+disp(edges, 'canny')
+
+# Exercise 3
+pixels = float32(image.reshape((-1, 3)))
+criteria = TERM_CRITERIA_EPS|TERM_CRITERIA_MAX_ITER, 10, 1.0
+ret, labels, centers = kmeans(pixels, 3, None, criteria,
+                              10, KMEANS_RANDOM_CENTERS)
+# Compared to global threshold, this has colors.
+# I am unsure how this relate to adaptive threshold though.
+disp(centers[labels.flatten()].reshape(image.shape), 'seg')
+
+# Exercise 4
+for ((rho, theta),) in hough_lines(edges, 1, pi/180, THRESHOLD):
+    a, b = cos(theta), sin(theta)
+    x, y = a*rho, b*rho
+    line(image, (int(x-b*1000), int(y+a*1000)), (int(x+b*1000), int(y-a*1000)),
+         (0, 0, 255), 2)
+disp(image, 'hough')
diff --git a/usth/ICT2.12/labwork/2.pdf b/usth/ICT2.12/labwork/2.pdf
new file mode 100644
index 0000000..2471ca1
Binary files /dev/null and b/usth/ICT2.12/labwork/2.pdf differ
diff --git a/usth/ICT2.12/labwork/dino-gang.jpg b/usth/ICT2.12/labwork/dino-gang.jpg
new file mode 100644
index 0000000..1d8001a
Binary files /dev/null and b/usth/ICT2.12/labwork/dino-gang.jpg differ
-- 
cgit 1.4.1