ROBUST FACE NAME GRAPH MATCHING FOR MOVIE CHARACTER IDENTIFICATION

AGENDA Abstract Existing system Proposed system System architecture List of modules Module description Screen shot Conclusion Future Enhancement

ABSTRACT Automatic face identification of characters in movies become a challenging problem due to the huge variation of each characters. In this paper, we present two schemes of global face name matching based frame work for robust character identification. A noise insensitive character relationship representation is incorporated. We introduce an edit operation based graph matching algorithm.

EXISTING SYSTEM DISADVANTAGES During face tracking and face clustering process, the noises has been generated. The performance are limited at the time of noise generation. DISADVANTAGES The time taken for detecting the face is too long. The detected face cannot be more accurate.

PROPOSED SYSTEM TECHNOLOGY USED By using clustering mechanism, the face of the movie character is detected more accurately. TECHNOLOGY USED Two schemes considered in robust face name graph matching algorithm First, External script resources are utilized in both schemes belong to the global matching based category.

Second, The original graph is employed for face name graph representation. ADVANTAGES In the proposed system, the face detection is performed in a minute process. The faces are identified easily in low resolution, complex background also.

SYSTEM ARCHITECTURE

HARDWARE REQUIREMENTS System : Pentium IV 2.4 GHz. Hard Disk : 40 GB. Monitor : 15 VGA Colour. Mouse : Logitech. Ram : 512 Mb.

SOFTWARE REQUIREMENTS Operating System : Windows XP Front End : Visual Studio 2008 Back End : Ms-Sql Server

LIST OF MODULES Login and authentication module Detection module Training module Recognition module

Login & Authentication Module The Robust Face-Name Graph Matching for Movie Character Identification designing and how we going to do face detection and recognition in the project. The images will explain about the facial fetching details. After that admin going to login with the details which needed for the login page.

Detection Module In this module, the face of the movie character is detected. We are using the emgucv library for detection and it is installed for adding references. When you will complete the references you will get the emgu controls in the toolbox.

Training Module In this module, I’m going to train the faces which are detected in the earlier module. The user can train the system by adding the names of the user. The name of the training data set is stored in image format with the graph name.

Recognition Module This module going to recognize the face of the movie characters which is we previously stored on the face database. We just found that the give the real name of it. This is going to be done here. Here we are using the With the help of these eigenObjectRecognizer we are going to recognize the face.

DATA FLOW DIAGRAM

SCREEN SHOTS DESIGN PAGE

DESIGN PAGE

LOGIN PAGE

IMAGE INSERTION

TRAINING DATASET

TRAINING AND RECOGNITION

DETECTION MODULE

CONCLUSION The proposed two schemes are useful to improve results for clustering and identification of the face tracks extracted from uncontrolled movie videos. From the sensitivity analysis, also shown that to some degree, such schemes have better robustness to the noises in constructing affinity graphs than the traditional methods. A third conclusion is a principle for developing robust character identification method intensity alike noises must be emphasized more than the coverage alike noises.

FUTURE ENHANCEMENT In the future, we will extend our work to investigate the optimal functions for different movie genres. Another goal of future work is to exploit more character relationships, e.g., the sequential statistics for the speakers, to build affinity graphs and improve the robustness.

REFERENCE PAPER J. Sang, C. Liang, C. Xu, and J. Cheng, “Robust movie character identification and the sensitivity analysis,” in ICME, 2011, pp. 1–6. H. Bunke, “On a relation between graph edit distance and maximum common sub graph,” Pattern Recognition Letters, vol. 18, pp. 689–694

REFERENCE PAPER - Contd M. Everingham and A. Zisserman, “Identifying individuals in video by combining ”generative” and discriminative head models,” in ICCV,2005, pp. 1103–1110.

QUERIES