Convolutional Neural Network for Image Classification - Versionsgeschichte

Ajay.paul@stud.hshl.de am 11. März 2026 um 15:06 Uhr

2026-03-11T15:06:58Z

← Nächstältere Version		Version vom 11. März 2026, 15:06 Uhr
Zeile 77:		Zeile 77:
	predictions = model.predict(img_array)		predictions = model.predict(img_array)
	</source>		</source>

			'''SVN Repository:'''<br>
			https://svn.hshl.de/svn/MATLAB_Vorkurs/trunk/Signalverarbeitung_mit_Kuenstlicher_Intelligenz/Image%20Processing%20with%20MATLAB%20and%20AI/CNN_Image_Classification/


	== References ==		== References ==
	<references />		<references />

Ajay.paul@stud.hshl.de am 10. Februar 2026 um 12:05 Uhr

2026-02-10T12:05:07Z

← Nächstältere Version		Version vom 10. Februar 2026, 12:05 Uhr
Zeile 8:		Zeile 8:
	Convolutional Neural Networks are the most common deep learning models used for computer vision. Unlike fully connected networks that see the image like a long list of numbers, CNNs keep the shape and position of the image parts.<ref>Prinzi, F., Currieri, T., Gaglio, S. and Vitabile, S. (2024) ‘Shallow and deep learning classifiers in medical image analysis’, European Radiology Experimental, 8(1), p. 26. doi:10.1186/s41747-024-00428-2.</ref>		Convolutional Neural Networks are the most common deep learning models used for computer vision. Unlike fully connected networks that see the image like a long list of numbers, CNNs keep the shape and position of the image parts.<ref>Prinzi, F., Currieri, T., Gaglio, S. and Vitabile, S. (2024) ‘Shallow and deep learning classifiers in medical image analysis’, European Radiology Experimental, 8(1), p. 26. doi:10.1186/s41747-024-00428-2.</ref>

	~~== References ==~~
	~~<references />~~

	== Dataset ==		== Dataset ==
Zeile 79:		Zeile 77:
	predictions = model.predict(img_array)		predictions = model.predict(img_array)
	</source>		</source>

			== References ==
			<references />

Ajay.paul@stud.hshl.de: /* Overview */

2026-02-10T12:04:44Z

Overview

← Nächstältere Version		Version vom 10. Februar 2026, 12:04 Uhr
Zeile 4:		Zeile 4:

	== Overview ==		== Overview ==
	The model described herein is designed to classify low-resolution color images (<math ~~display="inline"~~>32 \times 32 </math> pixels) into one of ten distinct classes (e.g., airplanes, automobiles, birds, cats). The implementation utilizes a sequential architecture consisting of a convolutional base for feature extraction followed by a dense network for classification.		The model described herein is designed to classify low-resolution color images (<math>32 \times 32</math> pixels) into one of ten distinct classes (e.g., airplanes, automobiles, birds, cats). The implementation utilizes a sequential architecture consisting of a convolutional base for feature extraction followed by a dense network for classification.

			Convolutional Neural Networks are the most common deep learning models used for computer vision. Unlike fully connected networks that see the image like a long list of numbers, CNNs keep the shape and position of the image parts.<ref>Prinzi, F., Currieri, T., Gaglio, S. and Vitabile, S. (2024) ‘Shallow and deep learning classifiers in medical image analysis’, European Radiology Experimental, 8(1), p. 26. doi:10.1186/s41747-024-00428-2.</ref>

			== References ==
			<references />

	== Dataset ==		== Dataset ==

Ajay.paul@stud.hshl.de: /* Overview */

2026-02-06T07:35:11Z

Overview

← Nächstältere Version		Version vom 6. Februar 2026, 07:35 Uhr
Zeile 4:		Zeile 4:

	== Overview ==		== Overview ==
	The model described herein is designed to classify low-resolution color images ($32 \times 32$ pixels) into one of ten distinct classes (e.g., airplanes, automobiles, birds, cats). The implementation utilizes a sequential architecture consisting of a convolutional base for feature extraction followed by a dense network for classification.		The model described herein is designed to classify low-resolution color images (<math display="inline">32 \times 32 </math> pixels) into one of ten distinct classes (e.g., airplanes, automobiles, birds, cats). The implementation utilizes a sequential architecture consisting of a convolutional base for feature extraction followed by a dense network for classification.

	== Dataset ==		== Dataset ==

Ajay.paul@stud.hshl.de: Die Seite wurde neu angelegt: „= Convolutional Neural Network for Image Classification = A '''Convolutional Neural Network''' (CNN) is a class of deep neural networks, most commonly applied to analyzing visual imagery. This article describes a specific implementation of a CNN using the TensorFlow and Keras libraries to classify images from the '''CIFAR-10''' dataset. == Overview == The model described herein is designed to classify low-resolution color images ($32 \times 32$…“

2026-02-06T07:32:29Z

Die Seite wurde neu angelegt: „= Convolutional Neural Network for Image Classification = A '''Convolutional Neural Network''' (CNN) is a class of deep neural networks, most commonly applied to analyzing visual imagery. This article describes a specific implementation of a CNN using the TensorFlow and Keras libraries to classify images from the '''CIFAR-10''' dataset. == Overview == The model described herein is designed to classify low-resolution color images ($32 \times 32$…“

Neue Seite

= Convolutional Neural Network for Image Classification =

A '''Convolutional Neural Network''' (CNN) is a class of deep neural networks, most commonly applied to analyzing visual imagery. This article describes a specific implementation of a CNN using the [[TensorFlow]] and [[Keras]] libraries to classify images from the '''CIFAR-10''' dataset.

== Overview ==
The model described herein is designed to classify low-resolution color images ($32 \times 32$ pixels) into one of ten distinct classes (e.g., airplanes, automobiles, birds, cats). The implementation utilizes a sequential architecture consisting of a convolutional base for feature extraction followed by a dense network for classification.

== Dataset ==
The system is trained on the '''CIFAR-10''' dataset, which consists of 60,000 $32 \times 32$ color images in 10 classes, with 6,000 images per class.
* '''Training set:''' 50,000 images
* '''Test set:''' 10,000 images
* '''Preprocessing:''' Pixel values are normalized to the range [0, 1] by dividing by 255.0 to accelerate convergence during gradient descent.

[[File:Dataset_Example.png|thumb|center|Dataset example used for CNN image classification]]

== Network Architecture ==
The architecture follows a sequential pattern: <tt>Conv2D</tt> $\rightarrow$ <tt>MaxPooling</tt> $\rightarrow$ <tt>Dense</tt>. The specific layer configuration and parameter counts are detailed below:

'''Model: "sequential"'''
{| class="wikitable" style="text-align:center; width:60%;"
! style="text-align:left;" | Layer (type) !! Output Shape !! Param #
|-
| style="text-align:left;" | conv2d (Conv2D) || (None, 30, 30, 32) || 896
|-
| style="text-align:left;" | max_pooling2d (MaxPooling2D) || (None, 15, 15, 32) || 0
|-
| style="text-align:left;" | conv2d_1 (Conv2D) || (None, 13, 13, 64) || 18,496
|-
| style="text-align:left;" | max_pooling2d_1 (MaxPooling2D) || (None, 6, 6, 64) || 0
|-
| style="text-align:left;" | conv2d_2 (Conv2D) || (None, 4, 4, 64) || 36,928
|-
| style="text-align:left;" | flatten (Flatten) || (None, 1024) || 0
|-
| style="text-align:left;" | dense (Dense) || (None, 64) || 65,600
|-
| style="text-align:left;" | dense_1 (Dense) || (None, 10) || 650
|-
| style="font-weight:bold; background-color:#eaecf0; text-align:left;" colspan="3" | Total params: 122,570 (478.79 KB)
|-
| style="font-weight:bold; background-color:#eaecf0; text-align:left;" colspan="3" | Trainable params: 122,570 (478.79 KB)
|-
| style="font-weight:bold; background-color:#eaecf0; text-align:left;" colspan="3" | Non-trainable params: 0 (0.00 B)
|}

== Implementation Details ==

=== Training Configuration ===
The model is compiled with the following hyperparameters:
* '''Optimizer:''' Adam (Adaptive Moment Estimation).
* '''Loss Function:''' Sparse Categorical Crossentropy (<tt>from_logits=True</tt>).
* '''Metrics:''' Accuracy.
* '''Epochs:''' 10 iterations over the entire dataset.

=== Performance ===
Upon training for 10 epochs, the model typically achieves:
* '''Training Accuracy:''' High (variable based on initialization).
* '''Test Accuracy:''' Approximately 70% – 75%.
* '''Overfitting:''' A divergence between training accuracy and validation accuracy suggests the model may memorize training data. Techniques such as Dropout or Data Augmentation are recommended to mitigate this.

=== Result ===

{| style="border:none;"
|-
| [[Datei:Calssification.png|mini]]
| [[Datei:Classification new data.png|mini]]
|}

=== Inference on Custom Images ===
To test the model on high-quality external images, the input must be resized to match the network's input constraints ($32 \times 32$ pixels).
<source lang="python">
img = image.load_img(path, target_size=(32, 32))
img_array = image.img_to_array(img) / 255.0
predictions = model.predict(img_array)
</source>