Detection of human body parts on the image using the neural networks and the attention model

Human body parts detection is a challenging task, which has lot of applications. In this paper, we propose an algorithm to detect human on images using the OpenPose neural network and attention model. The novelty proposed that it based convolutional uses non-parametric representation associate with people in image combination model learns focus specific regions input image. part Smart Cropping system developed by authors aim cut necessary pieces clothing prepare e-commerce catalogues.