This Code for Final Exam in Pattern Recognition

ChiliImageDetection.py

import cv2
import matplotlib.pyplot as plt
import pandas as pd
from sklearn.neighbors import KNeighborsClassifier

# Segmentation using equalize in colorize feature

# Segmentation for green feature
green = []
for i in range(1, 41):
    name = "Hijau " + (("0" + str(i)) if i < 10 else str(i))
    img = cv2.imread("PCD cabai jadi/" + name + ".png")
    gray = cv2.cvtColor(img, cv2.COLOR_BGR2HSV)
    gray[:, :, 0] = cv2.equalizeHist(gray[:, :, 0])
    image = cv2.cvtColor(gray, cv2.COLOR_HSV2RGB)
    green.append(gray)

# Segmentation for red feature
red = []
for i in range(1, 41):
    name = "Rawit " + (("0" + str(i)) if i < 10 else str(i))
    img = cv2.imread("PCD cabai jadi/" + name + ".png")
    gray = cv2.cvtColor(img, cv2.COLOR_BGR2HSV)
    gray[:, :, 0] = cv2.equalizeHist(gray[:, :, 0])
    red.append(gray)

# Feature Extraction

# From the results of segmentation, it can be seen that
# there are characteristics where the red chilies after being
# segmented will produce a higher green value than green chilies.

# Feature Extraction for red
loc_red = []
for i in red:
    total = 0
    for j in i:
        for k in j:
            if k[1] > 200:
                total += 1
    loc_red.append(total)

# Feature Extraction for green
loc_green = []
for i in green:
    total = 0
    for j in i:
        for k in j:
            if k[1] > 200:
                total += 1
                print("Counting")
    loc_green.append(total)

# Before entering the classification, the dataset is split into training data and test data.
dfGreen = pd.DataFrame({
    "pixel": loc_green,
})

dfGreenLabel = pd.DataFrame({
    "color": ["Hijau" for i in range(1, 41)]
})

dfRed = pd.DataFrame({
    "pixel": loc_red,
})

dfRedLabel = pd.DataFrame({
    "color": ["Merah" for i in range(1, 41)]
})

redTrain = dfRed.iloc[:, :30]
greenTrain = dfGreen.iloc[:, :30]
labelRedTrain = dfRedLabel.iloc[:, :30]
labelGreenTrain = dfGreenLabel.iloc[:, :30]

redTest = dfRed.iloc[31:, :]
greenTest = dfGreen.iloc[31:, :]
labelRedTest = dfRedLabel.iloc[31:, :]
labelGreenTest = dfGreenLabel.iloc[31:, :]

# Process classification using KNN. I use library KNN in scikit learn

# Process Training using data training
knn = KNeighborsClassifier(n_neighbors=5)
knn.fit(pd.concat([greenTrain, redTrain]), pd.concat([labelGreenTrain, labelRedTrain]))

# Process Prediction
print("Prediction")
print(knn.predict(pd.concat([greenTest, redTest])))

# Process accuracy calculation
print("Score")
print(knn.score(pd.concat([greenTest, redTest]),pd.concat([labelGreenTest,labelRedTest])))

# Show plot data set from feature extraction
plt.plot(range(1, 41), loc_red, 'o', range(1, 41), loc_green, 'o')
plt.show()