Recognizing text in images poses significant challenges, particularly in the presence of complex backgrounds. This technology plays a crucial role in assisting visually impaired individuals and interpreting semantic content. This survey explores various techniques developed over the past decade to address text recognition in complex images. It provides an overview and analysis of accumulated works and evaluates the performance of these recognition methods. While image complexity is difficult to quantify, it can be described using parameters such as background details, noise levels, lighting conditions, textures, and fonts. Furthermore, the survey highlights several benchmark datasets employed in the reviewed studies. By examining these works, challenges in the field are identified and compared.