Description

ABSTRACT

The detection of human face from images plays a vital role in Computer vision, cognitive science and Forensic Science. The various computational and mathematical models, for classifying face including Scale Invariant Feature transform (SIFT) and Dominant Rotated Local Binary Pattern (DRLBP) have been proposed yields better performance. This paper proposes a novel method of classifying the human face using Artificial Neural Network. This is done by pre-processing the face image at first and then extracting the face features using SIFT. Then the detection of human faces is done using Back Propagation Network (BPN). The process of combining SIFT and DRLBP perform better rather using separately.

DEMO VIDEO

EXISTING METHOD

• Appearance based methods involves LDA
• Geometric methods.

DRAWBACKS

• In appearance based methods, less accurate of features description because of whole image consideration
• In geometric based methods, the geometric features like distance between eyes, face length and width, etc., are considered which not provides optimal results

PROPOSED METHOD

Human Face recognition using combined Scale Invariant feature transform (SIFT) and Dominant Rotated Local Binary Pattern (DRLBP)

BLOCK DIAGRAM

METHODOLOGIES

• Preprocessing and Normalization
• Dominant Rotated Local Binary Pattern(DRLBP)
• Scale invariant Feature Transform(SIFT)
• Histogram and GLCM
• ANN-Back Propagation Network

ADVANTAGES

• Detecting accuracy is high due to extracting local features of the image
• The geometric features like distance between eyes, face length and width, etc., are considered which provides high optimal results

APPLICATIONS

• Queue forming
• People counting

SOFTWARE REQUIREMENTS

• Python
• Opencv
• Numpy

RESULT

By the use of artificial neural network we canable to recognise the human face and identify it, SIFT and DRLBP gives the accuracy for this system.