Face Identification Based on Contrast Limited Adaptive Histogram

Equalization (CLAHE).

Gibran Benitez-Garcia, Jesus Olivares-Mercado, Gualberto Aguilar-Torres,

Gabriel Sanchez-Perez and Hector Perez-Meana

Mechanical and Electrical Engineering School of National Polytechnic

Institute of Mexico. Mexico, Mexico D.F.

Introduction

This paper proposes a face identification method based on Contrast Limited Adaptive Histogram Equalization (CLAHE) robust to facial expressions, occlusion (නිරෝධනය) and especially to illumination (ආලෝකය) changes.

Approach

This is based on Eigenphases algorithm for feature extraction, the Principal Components Analysis (PCA) and the Phase Spectrum was used as feature extraction stage, and Support Vector Machine (SVM) as a classifier.

Method

• Capture: - Capture the pattern (data acquisition of this method consists in taking a picture).
• Feature Extraction: - Extract the feature of captured pattern (Pattern is converted into vector feature).
• Classification: - Generate template based on vector feature (SVM).

Strengthes

• The results were obtained using a database that includes face images of 120 subjects (60 males and 60 females) with illumination changes, facial expressions and partial occlusion. The proposed method provides results with a correct recognition up to 97%.
•  Result obtained are greater than 90% and in the best cases obtained a 97.36% which is acceptable for a face recognition system.

Advantages

• The proposed system shown to be robust to changes in the database used, which are illumination changes and partial occlusion by using sunglasses.

Download Research Paper

http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.217.8286&rep=rep1&type=pdf

Mood Detection: Implementing a facial expression recognition system

 Neeraj Agrawal, Rob Cosgriff and Ritvik Mudur

Introduction

The purpose of this research is to develop a mood detection system which can achieve high recognition rates of facial expression across multiple databases.

Approach

An approach using eigenface masks was developed and implemented to classify facial expressions across publicly available databases. These learned masks along with feature vectors of the image were used to train the SVM (Support Vector Machines).

Method

• Pre-processing image data by normalizing and applying a simple mask.
• Extracting certain (facial) features using PCA (Principal Component Analysis) and Gabor filters.
• Using SVMs for classification and recognition of expressions.

Feature extraction

a.     Normalized pixel intensities (Every image in training set normalized by subtracting the mean of all training set images. The masked region is then converted to a column vector which forms the feature vector).

b.     Gabor filter representations (Gabor filters are often used in image processing and are based on physiological studies of the human visual cortex. The use of Gabor filtered facial images has been shown to result in improved accuracy for facial expression recognition).

Eigenface masks (eigenfaces are used to generate a mask that eliminates pixels that vary little across training samples in different labels. In this system, they modify the approach to generate a separate mask for each expression class).

Strength

When apply Eigenface mask the results were similar for both the normalized pixel value and the gabor filtered feature vectors.

Advantages

• This approach works reasonably well in capturing expression-relevant facial information across all databases.

Conclusion

The results were similar for both the normalized pixel value and the gabor filtered feature vectors, with neither representation being clearly superior to the other. The performance across databases is indicative of the method’s robustness to variations in facial structure and skin tone when recognizing the expression.

However, both representations of the feature vectors end up being very high dimensional. This hurts the run time of the algorithm hampering the ability to use it in real time, as well as leading to possible over fitting of the data during training. Increasing the number of available training images would help to compensate for over fitting.

Download Research Paper

http://cs229.stanford.edu/proj2009/AgrawalCosgriffMudur.pdf

Facial Expression recognition using Fuzzy Inference System

Maedeh Rasoulzadeh

Rasoulzade.m@gmail.com

Introduction

This paper proposes a novel fuzzy method for facial expression recognition on still images of the face.

Approach

The new technique involves in extracting mathematical data from some special regions of the face and fed them to a fuzzy rule-based system. Fuzzification operation uses triangular membership functions for both input and output.

Method

1. Input image is preprocessed by wiener filter for smoothing and more distinction between face and background.
2. 5 basic regions were extracted on face area of the preprocessed image by defining 10 lines.
3. Feature extraction is performed (image energy, mean and variance, were calculated and considered as features that are fed to mamdani-type fuzzy system for expression recognition).

Strengths

·        Average recognition rate of expression is 92.3%.

·        Superiority of proposed system to existing ones.

 

Advantages

• This system is capable of recognizing 6 basic human facial expressions that are happiness, surprise, anger, fear, disgust and sadness.
• System is simple & highly accurate.
•  Experimental results on JAFFEE database indicate good performance of the developed technique.

Disadvantages

•  It needs static image as input for giving expression as the output.

Future work

Will include emotion recognition based on considering more facial regions, improving rules and combining other classifiers to the fuzzy system and for better performance.

Download Research Paper

http://www.ijeit.com/vol%201/Issue%204/IJEIT1412201204_50.pdf

FACIAL EXPRESSION RECOGNITION SYSTEM USING

WEIGHT-BASED APPROACH

Srinivasa K G, Inchara Shivalingaiah, Lisa Gracias, and Nischit Ranganath

M.S Ramaiah Institute of Technology, India

http://www.msrit.edu

Introduction:

This paper present a method to identify the facial expressions of a user by processing images taken from a webcam. This is done by passing the image through 3 stages -face detection, feature extraction, and expression recognition. Face detection is accomplished by implementing the concept of Haar-like features to prioritize reduction in detection time over accuracy.

Problems:

• Presence or absence of structural components like facial hair, glasses, etc., affects the accuracy of detection.
• The orientation of the face affects the feature detection. The face must not be tilted, and must be directed straight at the camera.
• Webcam images captured under improper lighting.

Approach:

Facial features are extracted from their respective regions of interest using Gabor filters and classified based on facial ratios and symmetry. They plotted a minimal number of facial points (12 points) and compared the positions of these points on the neutral expression image and the current expression image. This allowed them to recognize 8 expressions based on the facial movements made as opposed to identifying just the 6 basic expressions as done by research papers previously.

Strength:

They were able to reach an accuracy level of approximately 92% for expression recognition when tested with the JAFFE database. This is a considerably high performance when taking into account the simplicity of the algorithm involved.

Functional Requirements:

• Face localization: To detect the face present in an image taken from the webcam.
• Region of Interest Detection: To divide the face into regions of interest for feature extraction in each region.
• Feature Extraction: To detect the features present in each region of interest.
• Feature Classification: To classify the features detected based on their relative and absolute distances on the face.
• Expression Recognition: To identify the expression made based on the feature movements.

Method:

• Use 3 algorithms to Face Detection, Feature Extraction & Expression Recognition.
•  Functional architecture
•  Face Detection: The input image is scanned across location and scale. At each location, an independent decision is made regarding the presence of a face.
•  Region of Interest (ROI) Detection: Determine the ROI for each point, that is, to define a large region which contains the point that we want to detect.
• Feature Extraction: Predict whether the current point represents a certain facial point or not.
• Feature Classification: Detect correct feature for particular feature point.
•  Expression Recognition: A database of 50 people making 8 expressions

Future work:

 Investigate effects of using a reduced number of features for classification. Also, we plan to conduct extensive experimental studies using other publicly available face databases.

Download Research Paper:

https://drive.google.com/file/d/0B3VmCeqDC7SDSzZxMXQzLVJieFE/view?usp=sharing

Analysis of Facial Expressions from Video

Images using PCA

Praseeda Lekshmi V., Dr.M.Sasikumar, Naveen S.

Introduction:

In this paper they present a method to analyze facial expression from video images (Video frames are extracted from image sequences.) by focusing on the regions such as eyes, mouth etc. whose geometries are mostly affected by variation in facial expressions. Face regions are extracted from video images. Skin color detection is used for identifying skin region and recognized using Principal Component Analysis (PCA) method. Face images are projected on to a feature space and the weight vectors are compared to get minimum variation.

Problems:

There are several problems in analyzing facial expressions by a computer because expressions are not always universal. It varies with ethnicity.

Approach:

Geometric based method for facial expression analysis from the recognized face. The feature points are located and their coordinates are extracted (geometric coordinates of highly expression reflected areas are extracted for analyzing facial expressions)

Advantages:

• Good performance ratio for both face identification and expression analysis individually.
• The results are still good when do Analysis of Facial Expressions from Video Images using PCA combined the identification and expression parts.
• The computational time and complexity was also very small.

Background & Related Study:

Most face recognition methods fall into two categories: Feature based and Holistic

In feature based method, face recognition relies on localization and detection of facial features such as eyes, nose, mouth and their geometrical relationships.

In holistic approach, entire facial image is encoded into a point on high dimensional space.

Method:

As a first step, images are projected to PCA space for recognizing face regions. After recognizing the face, their system could efficiently identify the expression from the face.

Feature Work:

It is also proposed to extend the work to identify the face and it’s expressions from 3D images.

Conclusion:

In this paper, face recognition and expression classification from video image sequences are explained. Frames were extracted from image sequences. Skin color detection method is applied to detect face regions. A holistic based approach in which whole face was considered for the construction of Eigen space. Our logic performs well for recognition of expressions from face sequences. Use FG-NET consortium database .

Download Research Paper : https://drive.google.com/file/d/0B3VmCeqDC7SDdTE4LXVZUDZfZ3c/view?usp=sharing