Advertisement image classification using convolutional neural network

Image classification is critical and significant research problems in computer vision applications such as facial expression classification, satellite image classification, plant (fruits, flowers, leaf…) classification base on images. This paper proposes the image classification model applied for identifying the display of the online advertisement. The proposal model uses Convolutional Neural Network with two parameters (n, m) where n is a number of layers and m is number of filters in Conv layer. The proposed model is called nLmF-CNN. The suitable values of parameters (n, m) for advertisement image classification are identified by experiments. The input data of the proposed model are online captured images. The processing components of nLmF-CNN are developed as deep neural networks using ConvNetJs library. The output of the proposed model is YES/NO. YES means that the advertisements display clearly. NO means that the advertisements do not display or not clear. The experimental results 86% in our normalizing dataset showed the feasibility of a proposed model nLmF-CNN.