Local Directional Number Pattern for Face

Analysis: Face and Expression Recognition

ABSTRACT

This paper proposes a novel local feature descriptor, local directional number pattern

(LDN), for face analysis, i.e., face and expression recognition. LDN encodes the directional

information of the face’s textures (i.e., the texture’s structure) in a compact way, producing a

more discriminative code than current methods. We compute the structure of each micro-

pattern with the aid of a compass mask that extracts directional information, and we encode

such information using the prominent direction indices (directional numbers) and sign—

which allows us to distinguish among similar structural patterns that have different intensity

transitions. We divide the face into several regions, and extract the distribution of the LDN

features from them. Then, we concatenate these features into a feature vector, and we use it

as a face descriptor. We perform several experiments in which our descriptor performs

consistently under illumination, noise, expression, and time lapse variations. Moreover, we

test our descriptor with different masks to analyze its performance in different face analysis

tasks.

ARCHITECTURE

Existing System

In this Existing System, This recognition problem is made difficult by the great

variability in head rotation and tilt, lighting intensity and angle, facial expression, aging, etc.

Some other attempts at facial recognition by machine have allowed for little or no variability

in these quantities. Yet the method of correlation (or pattern matching) of unprocessed optical

data, which is often used by some researchers, is certain to fail in cases where the variability

is great. In particular, the correlation is very low between two pictures of the same person

with two different head rotations.

Disadvantage

Where face recognition does not work well include poor lighting, sunglasses, long

hair, or other objects partially covering the subject’s face, and low resolution images. Another

serious disadvantage is that many systems are less effective if facial expressions vary. Even a

big smile can render the system less effective.

Proposed System

In this Proposed System, we propose a face descriptor, Local Directional Number

Pattern (LDN), for robust face recognition that encodes the structural information and the

intensity variations of the face’s texture. LDN encodes the structure of a local neighbourhood

by analyzing its directional information. Consequently, we compute the edge responses in the

neighbourhood, in eight different directions with a compass mask. Then, from all the

directions, we choose the top positive and negative directions to produce a meaningful

descriptor for different textures with similar structural patterns. This approach allows us to

distinguish intensity changes.

Advantage

1. Robust against illumination changes

2. Performance Better

3. Compact Mode

ALGORITHM - PRINCIPAL COMPONENT ANALYSIS

PCA finds a linear projection of high dimensional data into a lower dimensional

subspace such as:

The variance retained is maximized.

The least square reconstruction error is minimized.

LSI: Latent Semantic Indexing.

Kleinberg/Hits algorithm (compute hubs and authority scores for nodes).

Google/Page Rank algorithm (random walk with restart).

Image compression (Eigen faces)

Data visualization (by projecting the data on 2D).

Modules

1. Local Direction Number Pattern (LDN)

2. Face Expression

a. Eigen Faces

b. Fisher Faces

3. Results between Eigen and Fisher Faces

Modules Description

1. Local Direction Number Pattern

In this module, LDN is a six bit binary code assigned to each pixel of an input image

that represents the structure of the texture and its intensity transitions. we create our pattern

by computing the edge response of the neighbourhood using a compass mask, and by taking

the top directional numbers, that is, the most positive and negative directions of those edge

responses.

2. Face Expression

In this Module, each face is represented by a LDN histogram (LH). The LH contains fine

to coarse information of an image, such as edges, spots, corners and other local texture

features. Given that the histogram only encodes the occurrence of certain micro-patterns

without location information, to aggregate the location information to the descriptor.

a. Eigen Faces

In this module, facial recognition is discriminating input signals (image data) into

several classes (persons). The input signals are highly noisy (e.g. the noise is caused by

differing lighting conditions, pose etc.), yet the input images are not completely random and

in spite of their differences there are patterns which occur in any input signal. Such patterns,

which can be observed in all signals could be - in the domain of facial recognition - the

presence of some objects (eyes, nose, mouth) in any face as well as relative distances

between these objects. These characteristic features are called eigenfaces in the facial

recognition domain (or principal components generally). They can be extracted out of

original image data by means of a mathematical tool called Principal Component Analysis

(PCA). By means of PCA one can transform each original image of the training set into a

corresponding eigenfaces. An important feature of PCA is that one can reconstruct any

original image from the training set by combining the eigenfaces. Remember that eigenfaces

are nothing less than characteristic features of the faces. Therefore one could say that the

original face image can be reconstructed from eigenfaces if one adds up all the eigenfaces

(features) in the right proportion.

b. Fisher Faces

In this Module, bit harder to explain, because they identify regions of a face that

separate faces best from each other. None of them seems to encode particular light settings; at

least it's not as obvious as in the Eigenfaces method. If I could only guess which component

describes which features? So we leave the interpretation up to the reader. What we lose with

the Fisher faces method for sure, is the ability to reconstruct faces. If I want to reconstruct

faces, just like in the Eigenfaces section.

3. Results between Eigen and Fisher Faces

Fisher faces Eigen Faces

Computational

complexity

Slightly more

complex

Simple

Effectiveness

across pose

Good, even with

limited data

Some with enough

data

Sensitivity to

lighting

Little very

HARDWARE REQUIREMENTS

System    :   Pentium IV 2.4 GHz.

Hard Disk  :   80 GB.

Monitor   :   15 VGA Colour.

Mouse    :   Logitech.

Ram    :   512 MB.

SOFTWARE REQUIREMENTS 

Operating system   : Windows 8 (32-Bit)

Front End : Visual Studio 2010

Coding Language  : C#.NET