Recognizing text in images presents significant challenges, particularly in complex backgrounds. This technology is essential for aiding visually impaired individuals and interpreting semantic content. This survey examines various techniques developed in recent years for handling text recognition in complex images. The paper provides an analysis of related works and evaluates the performance of these recognition methods. Although image complexity is not easily defined, it can be described through parameters like background details, noise levels, lighting conditions, textures, and fonts. Additionally, this survey discusses several benchmark datasets used in the reviewed studies. By reviewing these works, we can identify and compare the challenges faced in this area. Background images being complex limits the accuracy achieved. For the accuracy increase, convolutional neural network is employed. In short, the proposed method comprises three parts. At first, the text is from a complex background detected. Next, the text is extracted from the image with Tesseract. Lastly, all the identified words are kept in a text file. Then the audio file is made from the text. The proposed system reads the text from the image with the aim to provide assistance to the visually impaired persons.