Metal additive manufacturing (MAM) has gained increasing attention over the past decade, owing to its ability to offer flexibility and freedom in design. Despite the advantages, there is still a need to enhance the quality of the manufactured parts, as they can be susceptible to various types of defects and failures, such as porosity and cracking. This article focuses on the melt pool as one of the critical aspects of the process. In the process of Laser Metal Deposition, a machine-integrated coaxial camera captures images of the melt pool during the process. Using imaging and segmentation techniques, the features of the melt pool, such as its area, width, intensity, and peripheral melt pool particles are analyzed. The data was utilized to develop a Recurrent Neural Network (RNN) model capable of distinguishing between various quality grades in components.