Food is one of the basic needs of human life. Computer vision-based automated identification of food from images offers multitude benefits including enhancing diet tracking, managing health conditions, and ensuring food safety and quality. It also optimizes restaurant operations, supply chain management, and agricultural practices while driving advancements in AI and IoT integration, ultimately promoting healthier and more efficient lifestyles. Food recognition utilizing Artificial Intelligence (AI) has been a field of interest for the researchers for the past few decades. Computer aided food recognition is particularly challenging due to cross-cultural culinary diversity, as foods from different nationalities have unique appearances, preparation styles, and presentations. This diversity complicates the creation of standardized datasets and accurate recognition models. Additionally, varying environmental factors and lighting conditions, frequent occlusion of food items, and the lack of standardized datasets further add to the complexity, making accurate identification difficult. This study focuses specifically on AI-based Bengali food recognition systems and presents a comprehensive literature review of deep learning, machine learning, and transfer learning-based approaches employed in this domain. The aim of this study is three-fold. Our primary goal is to report how different machine and deep learning algorithms have evolved, discuss state-of-the-art strategies, condense their results obtained using different datasets and examine their pros and cons. Second, this paper is intended to be a detailed reference of the research activity in AI for food image analysis. In the last section, we have discussed current challenges and the future recommendations.