For Project Enquiry +91 9962 067 067

EXISTING SYSTEM

PROPOSED SYSTEM

EXISTING CONCEPT:

         Existing methods for performing face recognition in the presence of blur are based on the convolution model and cannot handle non-uniform blurring situations that frequently arise from tilts and rotations in hand-held cameras.

          Blurring due to camera shake has been modeled as a convolution with a single blur kernel, and the blur is assumed to be uniform across the image.

PROPOSED CONCEPT:

          We propose a methodology for face recognition in the presence of space-varying motion blur comprising of arbitrarily-shaped kernels. We model the blurred face as a convex combination of geometrically transformed instances of the focused gallery face, and show that the set of all images obtained by non-uniformly blurring a given image forms a convex set.

EXISTING  TECHNIQUE :

          DIRECT RECOGNITION OF BLURRED FACES (DRBF)

PROPOSED ALGORITHM:

          SPACE-INVARIANT BLUR

TECHNIQUE DEFINITION:

          A pixel in a blurred image is a weighted average of the pixel’s neighborhood in the original sharp image.

          Thus, blur is modeled as a convolution operation between the original image and a blur filter kernel which represents the weights.

          The blur kernel may possess additional structure depending on the type of blur (such as circular-symmetry for out-of focus blurs), and these structures could be exploited during recognition.

ALGORITHM DEFINITION:

          In order to demonstrate the weakness of the convolution model in handling images blurred due to camera shake, we synthetically blur the focused gallery image to generate a probe, and provide both the gallery image and the blurred probe image as input to two algorithms- the convolution model which assumes space invariant blur, and the non-uniform motion blur model which represents the space-variant blurred image as a weighted average of geometrically warped instances of the gallery.

DRAWBACKS:

          A sparse minimization technique for recognizing faces across illumination and occlusion has been proposed, which is based on similar principles, additionally offers robustness to alignment and pose. But these works do not deal with blurred images.

          In an uncontrolled environment, illumination and pose could also vary along with blur, at same time is the problem which cannot solve by using the existing methods.

ADVANTAGES:

         The benefits this technology provides for law enforcement agencies in an investigation.

          Powerful 2D to 3D Transformation of Video or Photo Facial Images

          Fast, Accurate and Analytical Comparison of Multiple Facial Images for Precise Facial Recognition and Criminal Screening

          Advanced 3D Facial Recognition and Identity Verification

         Mobile and Video Identity Resolution and Surveillance Applications.