Face Entity Analysis Essay

III. Face Entity Recognition:

Based on the scene segmentation results, we can compute the face occurrence matrix O face =[oik ] m×n on each scene, where m is the number of faces, and n is the number of scenes. Here Oface has the same size with Oname because the number of face clusters is set the same as the number of distinct names in the script. Finally, the face affinity network which is represented by a matrix R face =[rij ]m×n. Table II demonstrates the face affinity matrix of some face clusters derived from the video of the film “Notting Hill”. All the values are normalized into the interval [0,1].

IV.Graph Matching

The generated affinity matrix of name and face have some statistic properties of the characters which are relatively

The partitioned face graph has the same vertex number with the name graph. The partitioned face affinity matrix by p, Rface (P) is calculated as,

RESULT

Trainig is done on the 3 scenes of 12 angry men movie which has total 8 characters. In training phase of face classification module, user has to give training images as input then he has to give images for clustering as input i.e. the path of particular folders. Cluster names are shown in one panel in the interface. Figure 3 shows the name ordinal affinity matrix and face ordinal affinity maricx for training video.Figure 4 shows the result for movie “12 angry man” which identified the characters and mapped them with their names.

Figure 4. Snapshot of Identification of characters and name Module.

CONCLUSION: We have implemented the scheme which is useful to improve results for clustering and identification of the face tracks, extracted from feature-length movie videos. This scheme may have better robustness to the noises in constructing affinity graphs than the traditional methods. We have mined the relationship between characters and provided a platform for character centered film