Detect and Analyze Face Parts Information using

2011

This paper proposes an automatic method of detection of facial features - eyes and mouth, based on color and on the symmetry map. The improvement of the quality of the image and the application of the correction techniques, such as the re-escalation of the image, the ellipsoidal vignetting or related processing lead to a detection rate of the facial features of up to 82.21%, as compared to 56.18% the value that was obtained initially.

Face recognition presents a challenging problem in the field of image analysis and computer vision. Face recognition system should be able to automatically detect a face in an image. This involves extracts its features and then recognize it, regardless of lighting, expression, illumination, ageing, transformations (translate, rotate and scale image) and pose, which is a difficult task. This paper presents a framework for component- based face alignment and representation that demonstrates improvement in matching performance over the more common holistic approach to face alignment and representation. Active shape model (ASM) technique that has been used often for locating facial features in face images. The proposed scheme selects robust landmark points where relevant facial features are found and assigns higher weights to their corresponding features in the face classification stage. For alignment and cropping Procrutes analysis is used. Multi-scale local binary pattern is used for matching automated face image. In MLBP per-component measurement of facial similarity and fusion of per-component similarities is used. The proposed work is more robust to changes in facial pose and improves recognition accuracy on occluded face images in forensic scenarios. Keywords:- Active shape model, Multi-scale local binary pattern, Procrutes analysis, holistic method. http://sites.google.com/site/ijcsis/ ISSN 1947-5500

This paper proposes a method to extract the feature points from faces automatically. It provides a feasible way to locate the positions of two eyeballs, nose & lips. This approach would help to extract useful features on human face automatically and improve the accuracy of face recognition. The experiments show that the method presented in this pa per could locate feature points from faces exactly and quickly.

IJCER, 2012

This paper proposes the extraction of geometric and texture feature of face automatically from front view. For extracting the geometric feature cumulative histogram approach is used and co-occurrence matrices are used to extract the texture feature of face. From the input image, face location is detected using the viola-Jones algorithm, from the structure of human face, 4 relevant regions such as left eye, right eye, nose and mouth regions are cropped named as object. For extracting the geometric feature histogram of each Object is computed and its cumulative histogram values are employed by varying different threshold values to create a new filtered binary image of each Object, then the corner end-point of each object (binary image) is detected using the linear search technique. For extracting the texture feature co-occurrence matrices of each object is determined, using this matrix, angular second moment, entropy, maximum probability of occurrence pixels, inverse difference, inverse difference moment , mean, contrast of each object is detected.

2009

This project presents the facial feature extraction system and face recognition system. The test image that used for this project contain various type. There are ten different images of each of 40 disntinct subjects. For some subjects, the images were taken at different times, varying the lighting, facial expressions; open or closed eyes, smiling or not smiling, and facial details; glasses or no glasses. All the images were taken against a dark homogeneous background with the subjects in an upright, frontal position with tolerance for some side movement. For the facial feature extraction system, it is more focus on eye extraction. The eye will extracted from the face by finding the centroid of the eye region using threshold technique. For the recognition system, Principle Component Analysis (PCA) is used to match the test image with the database image. The system will find which database image has a maximum percentage based on similarity of the pattern of the image

Iraqi Journal of Science

Face detection systems are based on the assumption that each individual has a unique face structure and that computerized face matching is possible using facial symmetry. Face recognition technology has been employed for security purposes in many organizations and businesses throughout the world. This research examines the classifications in machine learning approaches using feature extraction for the facial image detection system. Due to its high level of accuracy and speed, the Viola-Jones method is utilized for facial detection using the MUCT database. The LDA feature extraction method is applied as an input to three algorithms of machine learning approaches, which are the J48, OneR, and JRip classifiers. The experiment’s result indicates that the J48 classifier with LDA achieves the highest performance with 96.0001% accuracy.

International Journal of Engineering and Advanced Technology

Face recognition has become relevant in recent years because of its potential applications. The aim of this paper is to find out the relevant techniques which give not only better accuracy also the efficient speed. There are several techniques available for face detection which give much better accuracy but the execution speed is not efficient. In this paper, a normalized cross-correlation template matching technique is used to solve this problem. According to the proposed algorithm, first different facial parts are detected likes mouth, eyes, and nose. If any of the two facial parts are found successfully then the face can be detected. For matching the templates with the target image, the template rotates at a certain angle interval.

As we have already seen a splendid growth in multimedia and technology, and considerably higher scale of social issues and crimes, face recognition plays a vital role in taking actions regarding all of these. Face as an object consists of variety of features for detection and recognition, therefore, it is still the most challenging research area for students in the field of computer vision and image processing. In this survey paper, I have tried to put in few most endeavouring face features such as, various poses, age, partial occlusion etc. All this information contributes more and more during identification. However the most important is to reject the outliers of facial points. But this task has become more challenging and it becomes tough to recognize faces due to various external and the internal factors such as ageing, variations in poses, emotions variations, uncontrolled environmental conditions etc. There are various techniques which have been developed and used. Each technique has its own characteristics, advantages, disadvantages, performance, representative work etc. This paper also states face detection techniques, approaches, as Eigenface, Artificial Neural Networks (ANN), Support Vector Machines (SVM), Principal Component Analysis (PCA), Independent Component Analysis (ICA), Elastic Bunch Graph Matching etc. However, I just aim to provide a comprehensive review over face recognition along with its applications. And after the deep dive, some major outcomes are given in conclusion.

1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258), 1999

The computerized process of locating human facial features such as the eyes, nose and mouth in a head and shoulders image is crucial to such applications as automatic face identification and model-based video coding. In this paper, a new model-based algorithm for locating these major features is developed. The algorithm estimates the parameters of the ellipse which best fits the head view in the image and uses these parameters to calculate the estimated locations of the facial features. It then refines the estimated coordinates of the eyes, mouth, and nose by exploiting the vertical and horizontal projections of the pixels in windows around the estimated locations of the features. The algorithm has been implemented and tested with over twelve hundred images, and simulation results indicate that the algorithm is robust to variations in subject head shape, eye shape, age, and motion such as tilting and nodding of the head.

2016

Automatic detection of facial feature points plays<br> an important role in applications such as facial feature tracking,<br> human-machine interaction and face recognition. The majority of<br> facial feature points detection methods using two-dimensional or<br> three-dimensional data are covered in existing survey papers. In<br> this article chosen approaches to the facial features detection have<br> been gathered and described. This overview focuses on the class<br> of researches exploiting facial feature points detection to represent<br> facial surface for two-dimensional or three-dimensional face. In<br> the conclusion, we discusses advantages and disadvantages of the<br> presented algorithms.