<![CDATA[Digital image processing is rapidly evolving along with advances in artificial intelligence technology, particularly in the field of deep learning. In this context, the use of Artificial Neural Network (ANN) architecture has proven effective in improving image classification performance. The main objective of this study is to integrate autoencoder techniques into the ANN structure to improve accuracy in the image classification process. Autoencoders, which are unsupervised learning methods, function to extract important and representative features from a given image. These features are then used as input for the classification layer in a neural network. In this experiment, a carefully curated image dataset was used to train the model. After training, the model was tested and evaluated based on several performance metrics, including accuracy, precision, and recall. The test results significantly showed that the addition of autoencoders in the ANN architecture provided a significant increase in classification accuracy compared to conventional approaches that did not use this technique. These findings prove that autoencoders can play a significant role in improving the quality of deep learning-based classification systems, especially in applications that require more accurate and efficient image analysis.]]>
Copyrights © 2025
