1 前言

Hi，大家好，這里是丹成學長，今天做一個 基于深度學習的水果識別demo

畢設幫助，開題指導，技術解答
🇶746876041

2 開發簡介

深度學習作為機器學習領域內新興并且蓬勃發展的一門學科， 它不僅改變著傳統的機器學習方法， 也影響著我們對人類感知的理解， 已經在影像識別和語音識別等領域取得廣泛的應用， 因此， 本文在深入研究深度學習理論的基礎上， 將深度學習應用到水果影像識別中， 以此來提高了水果影像的識別性能，

3 識別原理

3.1 傳統影像識別原理

傳統的水果影像識別系統的一般程序如下圖所示，主要作業集中在影像預處理和特征提取階段，

在大多數的識別任務中， 實驗所用影像往往是在嚴格限定的環境中采集的， 消除了外界環境對影像的影響， 但是實際環境中影像易受到光照變化、 水果反光、 遮擋等因素的影響， 這在不同程度上影響著水果影像的識別準確率，

在傳統的水果影像識別系統中， 通常是對水果的紋理、 顏色、 形狀等特征進行提取和識別，

3.2 深度學習水果識別

CNN 是一種專門為識別二維特征而設計的多層神經網路， 它的結構如下圖所示，這種結構對平移、 縮放、 旋轉等變形具有高度的不變性，

學長本次采用的 CNN 架構如圖：

4 資料集

• 資料庫分為訓練集(train)和測驗集(test)兩部分

• 訓練集包含四類apple,orange,banana,mixed(多種水果混合)四類237張圖片；測驗集包含每類圖片各兩張，圖片集如下圖所示，

• 圖片類別可由圖片名稱中提取，

訓練集圖片預覽

測驗集預覽

資料集目錄結構

5 部分關鍵代碼

5.1 處理訓練集的資料結構

import os
import pandas as pd

train_dir = './Training/'
test_dir = './Test/'
fruits = []
fruits_image = []

for i in os.listdir(train_dir):
    for image_filename in os.listdir(train_dir + i):
        fruits.append(i) # name of the fruit
        fruits_image.append(i + '/' + image_filename)
train_fruits = pd.DataFrame(fruits, columns=["Fruits"])
train_fruits["Fruits Image"] = fruits_image

print(train_fruits)

5.2 模型網路結構

import matplotlib.pyplot as plt
import seaborn as sns
from keras.preprocessing.image import ImageDataGenerator, img_to_array, load_img
from glob import glob
from keras.models import Sequential
from keras.layers import Conv2D, MaxPooling2D, Activation, Dropout, Flatten, Dense
img = load_img(train_dir + "Cantaloupe 1/r_234_100.jpg")
plt.imshow(img)
plt.axis("off")
plt.show()

array_image = img_to_array(img)

# shape (100,100)
print("Image Shape --> ", array_image.shape)

# 131個類目
fruitCountUnique = glob(train_dir + '/*' )
numberOfClass = len(fruitCountUnique)
print("How many different fruits are there --> ",numberOfClass)

# 構建模型
model = Sequential()
model.add(Conv2D(32,(3,3),input_shape = array_image.shape))
model.add(Activation("relu"))
model.add(MaxPooling2D())
model.add(Conv2D(32,(3,3)))
model.add(Activation("relu"))
model.add(MaxPooling2D())
model.add(Conv2D(64,(3,3)))
model.add(Activation("relu"))
model.add(MaxPooling2D())
model.add(Flatten())
model.add(Dense(1024))
model.add(Activation("relu"))
model.add(Dropout(0.5))

# 區分131類
model.add(Dense(numberOfClass)) # output
model.add(Activation("softmax"))
model.compile(loss = "categorical_crossentropy",

              optimizer = "rmsprop",

              metrics = ["accuracy"])

print("Target Size --> ", array_image.shape[:2])

5.3 訓練模型

train_datagen = ImageDataGenerator(rescale= 1./255,
                                   shear_range = 0.3,
                                   horizontal_flip=True,
                                   zoom_range = 0.3)

test_datagen = ImageDataGenerator(rescale= 1./255)
epochs = 100
batch_size = 32
train_generator = train_datagen.flow_from_directory(
                train_dir,
                target_size= array_image.shape[:2],
                batch_size = batch_size,
                color_mode= "rgb",
                class_mode= "categorical")

test_generator = test_datagen.flow_from_directory(
                test_dir,
                target_size= array_image.shape[:2],
                batch_size = batch_size,
                color_mode= "rgb",
                class_mode= "categorical")

for data_batch, labels_batch in train_generator:
    print("data_batch shape --> ",data_batch.shape)
    print("labels_batch shape --> ",labels_batch.shape)
    break

hist = model.fit_generator(
        generator = train_generator,
        steps_per_epoch = 1600 // batch_size,
        epochs=epochs,
        validation_data = test_generator,
        validation_steps = 800 // batch_size)

#保存模型 model_fruits.h5
model.save('model_fruits.h5')

順便輸出訓練曲線

#展示損失模型結果
plt.figure()
plt.plot(hist.history["loss"],label = "Train Loss", color = "black")
plt.plot(hist.history["val_loss"],label = "Validation Loss", color = "darkred", linestyle="dashed",markeredgecolor = "purple", markeredgewidth = 2)
plt.title("Model Loss", color = "darkred", size = 13)
plt.legend()
plt.show()

#展示精確模型結果
plt.figure()
plt.plot(hist.history["accuracy"],label = "Train Accuracy", color = "black")
plt.plot(hist.history["val_accuracy"],label = "Validation Accuracy", color = "darkred", linestyle="dashed",markeredgecolor = "purple", markeredgewidth = 2)
plt.title("Model Accuracy", color = "darkred", size = 13)
plt.legend()
plt.show()

6 識別效果

from tensorflow.keras.models import load_model
import os
import pandas as pd

from keras.preprocessing.image import ImageDataGenerator,img_to_array, load_img
import cv2,matplotlib.pyplot as plt,numpy as np
from keras.preprocessing import image

train_datagen = ImageDataGenerator(rescale= 1./255,
                                    shear_range = 0.3,
                                    horizontal_flip=True,
                                    zoom_range = 0.3)

model = load_model('model_fruits.h5')
batch_size = 32
img = load_img("./Test/Apricot/3_100.jpg",target_size=(100,100))
plt.imshow(img)
plt.show()

array_image = img_to_array(img)
array_image = array_image * 1./255
x = np.expand_dims(array_image, axis=0)
images = np.vstack([x])
classes = model.predict_classes(images, batch_size=10)
print(classes)
train_dir = './Training/'

train_generator = train_datagen.flow_from_directory(
        train_dir,
        target_size= array_image.shape[:2],
        batch_size = batch_size,
        color_mode= "rgb",
        class_mode= "categorical”)
print(train_generator.class_indices)

fig = plt.figure(figsize=(16, 16))
axes = []
files = []
predictions = []
true_labels = []
rows = 5
cols = 2

# 隨機選擇幾個圖片
def getRandomImage(path, img_width, img_height):
    """function loads a random image from a random folder in our test path"""
    folders = list(filter(lambda x: os.path.isdir(os.path.join(path, x)), os.listdir(path)))
    random_directory = np.random.randint(0, len(folders))
    path_class = folders[random_directory]
    file_path = os.path.join(path, path_class)
    file_names = [f for f in os.listdir(file_path) if os.path.isfile(os.path.join(file_path, f))]
    random_file_index = np.random.randint(0, len(file_names))
    image_name = file_names[random_file_index]
    final_path = os.path.join(file_path, image_name)
    return image.load_img(final_path, target_size = (img_width, img_height)), final_path, path_class

def draw_test(name, pred, im, true_label):
    BLACK = [0, 0, 0]
    expanded_image = cv2.copyMakeBorder(im, 160, 0, 0, 300, cv2.BORDER_CONSTANT, value=BLACK)
    cv2.putText(expanded_image, "predicted: " + pred, (20, 60), cv2.FONT_HERSHEY_SIMPLEX,
        0.85, (255, 0, 0), 2)
    cv2.putText(expanded_image, "true: " + true_label, (20, 120), cv2.FONT_HERSHEY_SIMPLEX,
        0.85, (0, 255, 0), 2)
    return expanded_image
IMG_ROWS, IMG_COLS = 100, 100

# predicting images
for i in range(0, 10):
    path = "./Test"
    img, final_path, true_label = getRandomImage(path, IMG_ROWS, IMG_COLS)
    files.append(final_path)
    true_labels.append(true_label)
    x = image.img_to_array(img)
    x = x * 1./255
    x = np.expand_dims(x, axis=0)
    images = np.vstack([x])
    classes = model.predict_classes(images, batch_size=10)
    predictions.append(classes)

class_labels = train_generator.class_indices
class_labels = {v: k for k, v in class_labels.items()}
class_list = list(class_labels.values())

for i in range(0, len(files)):
    image = cv2.imread(files[i])
    image = draw_test("Prediction", class_labels[predictions[i][0]], image, true_labels[i])
    axes.append(fig.add_subplot(rows, cols, i+1))
    plt.imshow(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))
    plt.grid(False)
    plt.axis('off')
plt.show()

7 最后-畢設幫助

畢設幫助，開題指導，技術解答
🇶746876041