Image classification using Convolutional Neural Networks (CNN) has revolutionized computer vision tasks by enabling automated and accurate recognition of objects within images. Consequently, this technology has significantly advanced fields such as medical imaging, autonomous driving, and industrial automation. CNN for image classification image classification algorithms have gained immense popularity due to their ability to learn and extract intricate features from raw image data automatically. This article will explore the principles, techniques, and applications of image classification using CNNs. Additionally, we will delve into the architecture, training process, and CNN image classification evaluation metrics. By comprehending the workings of CNNs for image classification, we can unlock many possibilities for object recognition, scene understanding, and visual data analysis.ALos, you will get to know about cnn model for image classification.
This article was published as a part of the Data Science Blogathon.
Image classification using CNN involves the extraction of features from the image to observe some patterns in the dataset. Using an ANN for the purpose of image classification would end up being very costly in terms of computation since the trainable parameters become extremely large.
For example, if we have a 50 X 50 image of a cat, and we want to train our traditional ANN on that image to classify it into a dog or a cat the trainable parameters become –
(50*50) * 100 image pixels multiplied by hidden layer + 100 bias + 2 * 100 output neurons + 2 bias = 2,50,302
We use filters when using CNN for image classification. Filters exist of many different types according to their purpose.
Filters help us exploit the spatial locality of a particular image by enforcing a local connectivity pattern between neurons. Additionally, these filters enable the model to capture intricate details and spatial relationships within the image.
Convolution basically means a pointwise multiplication of two functions to produce a third function. Here one function is our image pixels matrix and another is our filter. We slide the filter over the image and get the dot product of the two matrices. The resulting matrix is called an “Activation Map” or “Feature Map”.
Image classification involves assigning labels or classes to input images. Additionally, it is a supervised learning task where a model is trained on labeled image data to predict the class of unseen images. CNN algorithm steps are commonly used for image classification as they can learn hierarchical features like edges, textures, and shapes, enabling accurate object recognition in images. CNNs excel in this task because they can automatically extract meaningful spatial features from images. Here are different layers involved in the process:
The input layer of a CNN takes in the raw image data as input. The images are typically represented as matrices of pixel values. The dimensions of the input layer correspond to the size of the input images (e.g., height, width, and color channels).
Convolutional layers are responsible for feature extraction. Optionally convert to active voice: Filters (also known as kernels) convolve with the input images to capture relevant patterns and features. These layers learn to detect edges, textures, shapes, and more importantly, other important visual elements.
Pooling layers, however, reduce the spatial dimensions of the feature maps produced by the convolutional layers. They perform downsampling operations (e.g., max pooling) to retain the most salient information while discarding unnecessary details. This helps in achieving translation invariance and reducing computational complexity.
One or more fully connected layers flatten the output of the last pooling layer and connect to it.These layers function as traditional neural network layers and classify the extracted features. The fully connected layers learn complex relationships between features and output class probabilities or predictions.
The output layer represents the final layer of the CNN algorithm steps. Additionally, it consists of neurons equal to the number of distinct classes in the classification task. This layer provides each class’s classification probabilities or predictions. Consequently, it indicates the likelihood of the input image belonging to a particular class.
I will be working on Google Colab and have connected the dataset through Google Drive, so the provided code should work if you use the same setup. Remember to make appropriate changes according to your setup.
Choose a dataset of your interest or you can also create your own image dataset for solving your own image classification problem. An easy place to choose a dataset is on kaggle.com.
The dataset I’m going with can be found here.
This dataset contains 12,500 augmented images of blood cells (JPEG) with accompanying cell type labels (CSV). Additionally, each of the 4 different cell types has approximately 3,000 images grouped into 4 different folders according to cell type. These cell types are Eosinophil, Lymphocyte, Monocyte, and Neutrophil.
Here are all the libraries that we would require and the code for importing them:
from keras.models import Sequential
import tensorflow as tf
import tensorflow_datasets as tfds
tf.enable_eager_execution()
from keras.layers.core import Dense, Activation, Dropout, Flatten
from keras.layers.convolutional import Convolution2D, MaxPooling2D
from keras.optimizers import SGD, RMSprop, adam
from keras.utils import np_utils
from sklearn.tree import DecisionTreeClassifier # Import Decision Tree Classifier
from sklearn import metricsfrom sklearn.utils import shuffle
from sklearn.model_selection import train_test_splitimport matplotlib.image as mpimg
import matplotlib.pyplot as plt
import numpy as np
import os
import cv2
import randomfrom numpy import *
from PIL import Image
import theano
Preparing our dataset for training will involve several steps. Initially, we will assign paths and create categories (labels). Next, we will resize our images to ensure uniformity and optimal processing during training.
Resizing images into 200 X 200
path_test = "/content/drive/My Drive/semester 5 - ai ml/datasetHomeAssign/TRAIN"
CATEGORIES = ["EOSINOPHIL", "LYMPHOCYTE", "MONOCYTE", "NEUTROPHIL"]
print(img_array.shape)IMG_SIZE =200
new_array = cv2.resize(img_array, (IMG_SIZE, IMG_SIZE))
Training is an array that will contain image pixel values and the index at which the image in the CATEGORIES list.
training = []def createTrainingData():
for category in CATEGORIES:
path = os.path.join(path_test, category)
class_num = CATEGORIES.index(category)
for img in os.listdir(path):
img_array = cv2.imread(os.path.join(path,img))
new_array = cv2.resize(img_array, (IMG_SIZE, IMG_SIZE))
training.append([new_array, class_num])createTrainingData()
random.shuffle(training)
Optionally, we will use this shape of both lists in Classification using NEURAL NETWORKS.
X =[]
y =[]for features, label in training:
X.append(features)
y.append(label)
X = np.array(X).reshape(-1, IMG_SIZE, IMG_SIZE, 3)
X = X.astype('float32')
X /= 255
from keras.utils import np_utils
Y = np_utils.to_categorical(y, 4)
print(Y[100])
print(shape(Y))
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 4)
batch_size = 16
nb_classes =4
nb_epochs = 5
img_rows, img_columns = 200, 200
img_channel = 3
nb_filters = 32
nb_pool = 2
nb_conv = 3
model = tf.keras.Sequential([
tf.keras.layers.Conv2D(32, (3,3), padding='same', activation=tf.nn.relu,
input_shape=(200, 200, 3)),
tf.keras.layers.MaxPooling2D((2, 2), strides=2),
tf.keras.layers.Conv2D(32, (3,3), padding='same', activation=tf.nn.relu),
tf.keras.layers.MaxPooling2D((2, 2), strides=2),
tf.keras.layers.Dropout(0.5),
tf.keras.layers.Flatten(),
tf.keras.layers.Dense(128, activation=tf.nn.relu),
tf.keras.layers.Dense(4, activation=tf.nn.softmax)
])
model.compile(optimizer='adam',loss='sparse_categorical_crossentropy',metrics=['accuracy'])
model.fit(X_train, y_train, batch_size = batch_size, epochs = nb_epochs, verbose = 1, validation_data = (X_test, y_test))
score = model.evaluate(X_test, y_test, verbose = 0 )
print("Test Score: ", score[0])
print("Test accuracy: ", score[1])
Also Read: 20 Questions to Test your CNN Skills
In these 9 simple steps, you would be ready to train your own Convolutional Neural Networks model and solve real-world problems using these skills. Moreover, you can practice these skills on platforms like Analytics Vidhya and Kaggle. You can also play around by changing different parameters and discovering how you would get the best accuracy and score. Try changing the batch_size, the number of epochs or even adding/removing layers in the CNN model, and have fun!
In conclusion, image classification using CNN for image classification has revolutionized the field of computer vision, enabling accurate recognition of objects within images. With its ability to automatically learn and extract complex features, CNNs have become a powerful tool for various applications. To further enhance your understanding and skills in image classification using CNN algorithm steps and other advanced data science techniques, consider enrolling in our Blackbelt Program. This comprehensive program offers in-depth knowledge and practical experience. Consequently, it empowers you to become a proficient data scientist. Ready to take the next step? Explore the possibilities of our Blackbelt Program today!
Hope you like this article and understanding of Cnn model for image classification and also you get understand for CNN image classification.
A. To use CNNs for image classification, first, you need to define the architecture of the CNN. Next, preprocess the input images to enhance data quality. Then, train the model on labeled data to optimize its performance. Finally, assess its performance on test images to evaluate its effectiveness. Afterward, the trained CNN can classify new images based on the learned features.
A. Optially converts a CNN classifier for image classification into a CNN-based model specifically designed to classify images into different predefined classes. It learns to extract relevant features from input images and map them to the corresponding classes, enabling accurate image classification.
A. CNN in image captioning refers to using Convolutional Neural Networks as a component in the image captioning pipeline. These networks employ CNNs to extract visual features from input images, subsequently combining them with text-based models to generate descriptive captions for the images.
A. You can train a CNN-based model on a dataset of noisy and corresponding clean images to denoise an image using CNN. The model learns to map the noisy images to their corresponding denoised versions. Once trained, the CNN can denoise new images by passing them through the network and obtaining the reconstructed clean images.
The media shown in this article are not owned by Analytics Vidhya and is used at the Author’s discretion.
Hello. Thank you so much for the step to step guide to implement this. I have a question to ask. I hope to hear from you soon. I can not understand how was 'img_array' initialized in your work? What does img_array contain and how did you do that?
"print(img_array.shape)" when is try to run this line in colab I get error like "print(img_array.shape)" please help me to rectify this
Hello! I was just wondering, in Step 2: Prepare Dataset for Training, where does the img_array variable come from? Is this just the path_test?
please kindly correct your codes!
Review on code structure would make this post better, imports and declared variables are everywhere, reduces clarity.