Scribd
Upload
14 views1 page

Facial Expression Recognition Algorithm Based On KNN Classifier

The document outlines a facial expression recognition system utilizing a KNN classifier, which includes steps such as pre-processing, face detection, Curvelet transform, DLBP, RLBP, and classification. Pre-processing involves converting images to grayscale and noise removal, while face detection focuses on localizing and extracting facial regions from backgrounds. The proposed method applies these techniques to both test and database images for effective classification.

Uploaded by

interviewsecretss
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
14 views1 page

Facial Expression Recognition Algorithm Based On KNN Classifier

The document outlines a facial expression recognition system utilizing a KNN classifier, which includes steps such as pre-processing, face detection, Curvelet transform, DLBP, RLBP, and classification. Pre-processing involves converting images to grayscale and noise removal, while face detection focuses on localizing and extracting facial regions from backgrounds. The proposed method applies these techniques to both test and database images for effective classification.

Uploaded by

interviewsecretss
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd

Facial Expression Recognition Algorithm Based On KNN Classifier

Proposed Method The proposed system is divided into: Pre-processing, Face detection, Curvelet
transform (CT), DLBP, RLBP and K-NN Classifier. Initially we had applied pre processing on test image
like rgb to gray conversion, filtering and face detection, later we had applied Curvelet transform
after applying curvelet transform we will get four sub bands like Low and High. In that we had taken
Low frequency for applying DLBP and RLBP, at last we had used KNN classifier for classification. Same
process is applied for database images.

Fig.1 block diagram of proposed method

3.1 Preprocessing In Preprocessing Gray scale conversion and Noise removal is involved. In
computing, an image in which the value of each pixel is a single sample is called as a gray scale digital
image, it carries only intensity information. They also known as black-and-white images and are
composed exclusively of gray shades, varying from black at the weakest intensity to white at the
strongest. Gray scale images are distinct from one-bit bi-tonal black-and-white images, which in the
context of computer imaging are images with only the two colors, black and Gray scale images have
many shades of gray in between. Gray scale images are often the result of measuring the intensity of
light at each pixel in a single band of the electromagnetic spectrum, and in such cases they are
monochromatic proper when only a given frequency is captured. And the gray scale conversion of
image is given by [17]. gray (i, j) = {0.29∗rgb (:,:, 1) +0.59∗rgb (:,:,2) +0.11∗rgb :,:,3} Generally to
suppress the noise we are using median filter. First arrange matrix pixel value in the form of
ascending order. Find the median value of that matrix. And finally replace that value into that noisy
pixel location [3].

3.2 Face Detection Face Detection is the process of localizing and extracting the face region from
the background. Segmentation, extraction, and verification of faces as well as facial features from an
uncontrolled background are involved in face detection. There are two ways for face detection, one
is detection from still images and other is from images acquired from a video [1] [4]. To get better
framing actual image is cropped in which the

You might also like