Sport type classi¯cation and posture identi¯cation based on visual meaning of posture semantic in still images are challenging tasks. The di±culty of these tasks comes from the complex image content consisting of a player's posture, the color and texture of a player's clothes as well as complexity of the background. Player detection is one of the most important tasks in posture identi¯cation. For sport type classi¯cation without object segmentation, the new set of features, based on 64-bins color histogram, DCT coe±cients, and Cb and Cr components, is introduced. To achieve high accuracy, an appropriate feature extraction technique should be also realized. For posture identi¯cation, three algorithms, concerning player region detection and suitable features for posture identi¯cation, are proposed namely blurred background elimination, irrelevant region elimination, and trimming players region. The DFT coe±cients, based on image resizing and slicing techniques, are used as signi¯cant features in posture identi¯cation. Our proposed features were compared with Edge Histogram and Region-based Shape (EH and RS), two of MPEG-7 descriptors. The experimental results showed that our proposed features yielded better performance with 85.76% of accuracy in sport classi¯cation and 86.66% of accuracy in posture identi¯cation.