Augmented Reality (AR) superimposes virtual information on real-world data, such as displaying useful information on videos/images of a scene. This dissertation presents an Enhanced AR (EAR) framework for displaying useful information on images of a sports game. The challenge in such applications is robust object detection and recognition. This is even more challenging when there is strong sunlight. We address the phenomenon where a captured image is degraded by strong sunlight. The developed framework consists of an image enhancement technique to improve the accuracy of subsequent player and face detection. The image enhancement is followed by player detection, face detection, recognition of players, and display of personal information of players. First, an algorithm based on Multi-Scale Retinex (MSR) is proposed for image enhancement. For the tasks of player and face detection, we use adaptive boosting algorithm with Haar-like features for both feature selection and classification. The player face recognition algorithm uses adaptive boosting with the LDA for feature selection and nearest neighbor classifier for classification. The framework can be deployed in any sports where a viewer captures images. Display of players-specific information enhances the end-user experience. Detailed experiments are performed on 2096 diverse images captured using a digital camera and smartphone. The images contain players in different poses, expressions, and illuminations. Player face recognition module requires players faces to be frontal or up to ±350 of pose variation. The work demonstrates the great potential of computer vision based approaches for future development of AR applications.