Anemia is a blood disorder characterized by morphological or structural changes in red blood cells (RBCs) or hemoglobin. To manage it effectively, an accurate and in-time diagnosis is required. The conventional methods are time-consuming, labor-intensive, and prone to human error. To overcome these challenges, this research presents an AI-powered web-based online system for anemia detection through RBC image analysis. The proposed system uses state-of-the-art deep convolutional neural networks (CNNs) which utilize EfficientNet, MobileNet, and ResNet for rapid and accurate red blood cell morphology diagnostics. Additionally, an anemic RBC-based dataset is also developed named, AneRBC. The dataset comprises a total of 1000 RBC images, 500 each for both anemic and healthy RBC images. The developed web-based system provides a user-friendly interface for image analysis. At backend, the TensorFlow framework is integrated for efficient model execution. The proposed system is deployed on AWS to ensure scalability and reliability, providing an average response time of 2.5 s per image. Evaluation results show high performance with EfficientNet, achieving an accuracy of 95.4% and an AUC of 0.98.