SponselMa71420/Projekt_Dyschromasie
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Abschwächung der Simulationsstärke

Browse Source 
Durch Anpassungen in den Simulationsmatrizen ergeben sich Abschwächungsmuster. Somit können für verschiedene Probanden unterschiedliche Stärken der Sehschwäche simuliert werden.
This commit is contained in:
Max Sponsel 2020-09-04 11:59:25 +02:00
parent 9980f03bdd
commit a1ebdb827c
1 changed files with 25 additions and 56 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

81
Code/Dyschromasie-Applikation.py
View File

@ -5,17 +5,19 @@ from tkinter import filedialog, messagebox
import cv2 import cv2
import numpy as np import numpy as np
root = tk.Tk()
simGrad = tk.IntVar(root)
class Dyschromasie: class Dyschromasie:
global simGrad
cb_image = np.array([]).astype('float64') cb_image = np.array([]).astype('float64')
sim_image = np.array([]).astype('uint8') sim_image = np.array([]).astype('uint8')
def __init__(self, img_mat=np.array([]), rows=0, cols=0, kanaele=0): def __init__(self, img_mat=np.array([]), rows=0, cols=0, kanaele=0,sim_faktor=0):
self.rows = rows self.rows = rows
self.cols = cols self.cols = cols
self.kanaele = kanaele self.kanaele = kanaele
self.img_mat = img_mat self.img_mat = img_mat
self.sim_faktor = sim_faktor
T = np.array([[0.31399022, 0.63951294, 0.04649755], T = np.array([[0.31399022, 0.63951294, 0.04649755],
[0.15537241, 0.75789446, 0.08670142], [0.15537241, 0.75789446, 0.08670142],
@ -39,11 +41,12 @@ class Dyschromasie:
class Protanopie(Dyschromasie): class Protanopie(Dyschromasie):
sim_mat = np.array([[0, 1.05118294, -0.05116099],
[0, 1, 0],
[0, 0, 1]])
def Simulate(self): def Simulate(self):
sim_mat = np.array([[(1 - self.sim_faktor), 1.05118294 * self.sim_faktor, -0.05116099 * self.sim_faktor],
[0, 1, 0],
[0, 0, 1]])
# Gammakorrektur durchfuehren # Gammakorrektur durchfuehren
self.cb_image = np.copy(self.img_mat).astype('float64') self.cb_image = np.copy(self.img_mat).astype('float64')
for i in range(self.rows): for i in range(self.rows):
@ -55,7 +58,7 @@ class Protanopie(Dyschromasie):
for i in range(self.rows): for i in range(self.rows):
for j in range(self.cols): for j in range(self.cols):
self.cb_image[i, j] = np.flipud( self.cb_image[i, j] = np.flipud(
self.T_reversed.dot(self.sim_mat).dot(self.T).dot(np.flipud(self.cb_image[i, j]))) self.T_reversed.dot(sim_mat).dot(self.T).dot(np.flipud(self.cb_image[i, j])))
self.sim_image = np.copy(self.cb_image) self.sim_image = np.copy(self.cb_image)
self.sim_image = self.sim_image.astype('uint8') self.sim_image = self.sim_image.astype('uint8')
@ -66,25 +69,16 @@ class Protanopie(Dyschromasie):
for x in range(3): for x in range(3):
self.sim_image[i, j, x] = self.reverseGammaCorrection(self.cb_image[i, j, x]) self.sim_image[i, j, x] = self.reverseGammaCorrection(self.cb_image[i, j, x])
# Anpassung fuer den Slider
if(simGrad.get() != 0):
for i in range(rows):
for j in range(cols):
for x in range(3):
if self.sim_image[i, j, x] > img[i, j, x]:
self.sim_image[i, j, x] = img[i, j, x] + abs(self.sim_image[i, j, x] - img[i, j, x])* (simGrad.get()/100)
elif self.sim_image[i, j, x] < img[i, j, x]:
self.sim_image[i, j, x] = self.sim_image[i, j, x] + abs(img[i, j, x] - self.sim_image[i, j, x])* (simGrad.get()/100)
return self.sim_image return self.sim_image
class Deuteranopie(Dyschromasie): class Deuteranopie(Dyschromasie):
sim_mat = np.array([[1, 0, 0],
[0.9513092, 0, 0.04866992],
[0, 0, 1]])
def Simulate(self): def Simulate(self):
sim_mat = np.array([[1, 0, 0],
[0.9513092 * self.sim_faktor, (1 - self.sim_faktor), 0.04866992 * self.sim_faktor],
[0, 0, 1]])
# Gammakorrektur durchfuehren # Gammakorrektur durchfuehren
self.cb_image = np.copy(self.img_mat).astype('float64') self.cb_image = np.copy(self.img_mat).astype('float64')
for i in range(self.rows): for i in range(self.rows):
@ -96,7 +90,7 @@ class Deuteranopie(Dyschromasie):
for i in range(self.rows): for i in range(self.rows):
for j in range(self.cols): for j in range(self.cols):
self.cb_image[i, j] = np.flipud( self.cb_image[i, j] = np.flipud(
self.T_reversed.dot(self.sim_mat).dot(self.T).dot(np.flipud(self.cb_image[i, j]))) self.T_reversed.dot(sim_mat).dot(self.T).dot(np.flipud(self.cb_image[i, j])))
self.sim_image = np.copy(self.cb_image) self.sim_image = np.copy(self.cb_image)
self.sim_image = self.sim_image.astype('uint8') self.sim_image = self.sim_image.astype('uint8')
@ -107,26 +101,16 @@ class Deuteranopie(Dyschromasie):
for x in range(3): for x in range(3):
self.sim_image[i, j, x] = self.reverseGammaCorrection(self.cb_image[i, j, x]) self.sim_image[i, j, x] = self.reverseGammaCorrection(self.cb_image[i, j, x])
# Anpassung fuer den Slider
if (simGrad.get() != 0):
for i in range(rows):
for j in range(cols):
for x in range(3):
if self.sim_image[i, j, x] > img[i, j, x]:
self.sim_image[i, j, x] = img[i, j, x] + abs(self.sim_image[i, j, x] - img[i, j, x]) * (simGrad.get() / 100)
elif self.sim_image[i, j, x] < img[i, j, x]:
self.sim_image[i, j, x] = self.sim_image[i, j, x] + abs(img[i, j, x] - self.sim_image[i, j, x]) * (simGrad.get() / 100)
return self.sim_image return self.sim_image
class Tritanopie(Dyschromasie): class Tritanopie(Dyschromasie):
sim_mat = np.array([[1, 0, 0],
[0, 1, 0],
[-0.86744736, 1.86727089, 0]])
def Simulate(self): def Simulate(self):
sim_mat = np.array([[1, 0, 0],
[0, 1, 0],
[-0.86744736 * self.sim_faktor, 1.86727089 * self.sim_faktor, (1 - self.sim_faktor)]])
# Gammakorrektur durchfuehren # Gammakorrektur durchfuehren
self.cb_image = np.copy(self.img_mat).astype('float64') self.cb_image = np.copy(self.img_mat).astype('float64')
for i in range(self.rows): for i in range(self.rows):
@ -138,7 +122,7 @@ class Tritanopie(Dyschromasie):
for i in range(self.rows): for i in range(self.rows):
for j in range(self.cols): for j in range(self.cols):
self.cb_image[i, j] = np.flipud( self.cb_image[i, j] = np.flipud(
self.T_reversed.dot(self.sim_mat).dot(self.T).dot(np.flipud(self.cb_image[i, j]))) self.T_reversed.dot(sim_mat).dot(self.T).dot(np.flipud(self.cb_image[i, j])))
self.sim_image = np.copy(self.cb_image) self.sim_image = np.copy(self.cb_image)
self.sim_image = self.sim_image.astype('uint8') self.sim_image = self.sim_image.astype('uint8')
@ -149,17 +133,6 @@ class Tritanopie(Dyschromasie):
for x in range(3): for x in range(3):
self.sim_image[i, j, x] = self.reverseGammaCorrection(self.cb_image[i, j, x]) self.sim_image[i, j, x] = self.reverseGammaCorrection(self.cb_image[i, j, x])
# Anpassung fuer den Slider
if (simGrad.get() != 0):
for i in range(rows):
for j in range(cols):
for x in range(3):
if self.sim_image[i, j, x] > img[i, j, x]:
self.sim_image[i, j, x] = img[i, j, x] + abs(self.sim_image[i, j, x] - img[i, j, x]) * (simGrad.get() / 100)
elif self.sim_image[i, j, x] < img[i, j, x]:
self.sim_image[i, j, x] = self.sim_image[i, j, x] + abs(img[i, j, x] - self.sim_image[i, j, x]) * (simGrad.get() / 100)
return self.sim_image return self.sim_image
class AutoScrollbar(tk.Scrollbar): class AutoScrollbar(tk.Scrollbar):
@ -220,8 +193,6 @@ class ScrollFrame:
self.canvas.config(height = self.frame.winfo_reqheight()) self.canvas.config(height = self.frame.winfo_reqheight())
root = tk.Tk()
root.title("Projekt Dyschromasie") root.title("Projekt Dyschromasie")
SB = ScrollFrame(root) SB = ScrollFrame(root)
@ -234,7 +205,6 @@ kanaele = 0
sim_pro = tk.IntVar(root) sim_pro = tk.IntVar(root)
sim_deut = tk.IntVar(root) sim_deut = tk.IntVar(root)
sim_tri = tk.IntVar(root) sim_tri = tk.IntVar(root)
simGrad = tk.IntVar(root)
simulationsGradient = tk.Scale(SB.frame, from_=0, to_=100, variable=simGrad, orient='horizontal') simulationsGradient = tk.Scale(SB.frame, from_=0, to_=100, variable=simGrad, orient='horizontal')
simulationsGradient.grid(column= 0, row = 1, columnspan=10) simulationsGradient.grid(column= 0, row = 1, columnspan=10)
@ -264,9 +234,8 @@ def browse():
def simulate(): def simulate():
global img, rows, cols, kanaele, sim_pro, sim_deut, sim_tri global img, rows, cols, kanaele, sim_pro, sim_deut, sim_tri
if sim_deut.get(): if sim_deut.get():
d = Deuteranopie(img, rows, cols, kanaele) d = Deuteranopie(img, rows, cols, kanaele, simGrad.get()/100)
display_array_deut = cv2.cvtColor(np.copy(d.Simulate()), cv2.COLOR_BGR2RGB) display_array_deut = cv2.cvtColor(np.copy(d.Simulate()), cv2.COLOR_BGR2RGB)
T = tk.Text(SB.frame, height=1, width=15) T = tk.Text(SB.frame, height=1, width=15)
@ -278,7 +247,7 @@ def simulate():
sim_pic_deut.Image = conv_SimulationPic_deut sim_pic_deut.Image = conv_SimulationPic_deut
sim_pic_deut.grid(columnspan=5) sim_pic_deut.grid(columnspan=5)
elif sim_tri.get(): elif sim_tri.get():
t = Tritanopie(img, rows, cols, kanaele) t = Tritanopie(img, rows, cols, kanaele, simGrad.get()/100)
display_array_tri = cv2.cvtColor(np.copy(t.Simulate()), cv2.COLOR_BGR2RGB) display_array_tri = cv2.cvtColor(np.copy(t.Simulate()), cv2.COLOR_BGR2RGB)
T = tk.Text(SB.frame, height=1, width=15) T = tk.Text(SB.frame, height=1, width=15)
@ -290,7 +259,7 @@ def simulate():
sim_pic_tri.Image = conv_SimulationPic_tri sim_pic_tri.Image = conv_SimulationPic_tri
sim_pic_tri.grid(columnspan=5) sim_pic_tri.grid(columnspan=5)
elif sim_pro.get(): elif sim_pro.get():
p = Protanopie(img, rows, cols, kanaele) p = Protanopie(img, rows, cols, kanaele, simGrad.get()/100)
display_array_pro = cv2.cvtColor(np.copy(p.Simulate()), cv2.COLOR_BGR2RGB) display_array_pro = cv2.cvtColor(np.copy(p.Simulate()), cv2.COLOR_BGR2RGB)
T = tk.Text(SB.frame, height=1, width=15) T = tk.Text(SB.frame, height=1, width=15)