DEVELOPMENT OF A CONVOLUTIONAL NEURAL NETWORK FOR BINARY IMAGE CLASSIFICATION OF BEARS AND PANDAS WITH APPLICATIONS IN DIGITAL IMAGE PROCESSING

Abstract: The study investigates the design, application, and evaluation of a CNN model that is trained to perform binary classification based on bear and panda images. The use of an open-source dataset allows integrating certain basic ideas behind digital image processing together with deep learning techniques, which can be applied during image preprocessing and classification. The proposed CNN model comprises convolution and pooling layers followed by fully connected layers that can be used for binary classification. The Adam optimizer along with the binary cross entropy loss function were used, whereas accuracy for training the model, precision, and recall were used to measure the performance of the developed model.

Keywords: Image Processing, Binary Image Classification, Convulutional Neural Network