Human pose detection from images using deep learning

Human pose prediction has made significant progress in recent years. However, the available datasets are limited in terms of covering common exposure estimation challenges. Yet these serve as common resources to evaluate, educate, and compare different models on it. In this article, we introduce a new "MPII Human Pose", a contribution that we think is necessary for future developments in human body models, making a significant advance in diversity and difficulty. Deep learning models are widely used in many fields of science and engineering and reach high performance levels. With the widespread use of open source software such as Opencv and Keras, its use in applications has been simplified. In the study, deep learning models were applied using open source Opencv, Keras library and Python programming. Deep learning models were created using the MPII data set. The created deep learning model was divided into two as training and test data set and used. Training and test data sets will be obtained by using original images. The performance of the model will be measured by the correct classification rate of the test sets