Published Paper Details:

Deep learning has evolved into a powerful machine learning technology that incorporates multiple layers of features or representations of data to get cutting-edge results. Deep learning has demonstrated outstanding performance in a variety of fields, including picture classification, segmentation, and object detection. Deep learning approaches have recently made significant progress in fine-grained picture categorization, which tries to discriminate subordinate-level categories. Due to strong intra-class and low inter-class variance, this task is highly difficult. Object detection and the identification of pedestrians is critical in autonomous driving applications. In real-time applications, approaches based on Convolutional Neural Networks have shown significant increases in accuracy and decision speed. In this research, authors present various state of the art deep learning algorithms i.e., VGG-16, VGG19, DenseNet-121, InceptionV3 and customized 3 layers CNN model for object detection. Model adopted is trained and validated on self-made five class of furniture dataset. After extensive experiments, highest accuracy obtained was 99.89% with VGG-19.