International Journal of Scientific Research and Engineering Development

One of the basic problems has been identified as image classification and has applications in a variety of fields in the real world such as surveillance, health care, agriculture etc. This paper proposes Convolutional Neural Networks (CNN) as the method to use in deep learning approach to classify images. The following classification model aims to serve as a platform for image classification and is done by learning about convolution and pooling layers followed by fully connected layers. Data involved in this classification is a set of images classified into binary classes and this is a typical example of binary classification. The images are subsequently processed through several algorithms which guarantee that the classification is efficient and is well converging. The results of the classification model are then analyzed using various measures, such as classification accuracy, precision, recall and other performance statistics. The confusion matrix is also used to determine the performance of the classification model. Through the results obtained, it is observed that the CNN model is efficient and converges very well. The results indicate that deep learning methods are effective for image classification problems, and they have the potential to be used in real-world applications.

Dr. Deepti Goyal, Dr. Svav Prasad, "Deep Learning-Based Image Classification Using Convolutional Neural Networks" International Journal of Scientific Research and Engineering Development, V9(5): Page(192-196) September - October 2026. ISSN: 2581-7175. www.ijsred.com. Published by Scientific and Academic Research Publishing.