<![CDATA[Advances in machine learning have brought great impact on image recognition through Artificial Neural Network (ANN) and Convolutional Neural Network (CNN) approaches. This study compares the performance of both algorithms in image classification with a dataset of two classes, namely Green and Red Keychains. The dataset consists of 100 images processed through augmentation and data division of 65% for training and 35% for testing. The evaluation results show that CNN has higher accuracy, which is 88.24% to 93.94%, compared to ANN which reaches 62.12% to 67.65%. CNN is also more efficient in training time. The advantage of CNN lies in its ability to extract spatial features through convolution layers, while ANN is more suitable for simple data. This study concludes that CNN is superior for color-based image classification, although further research is needed with larger datasets.]]>
Copyrights © 2025
