07-07-2014, 01:37 PM
Face Recognition
Face Recognition.doc (Size: 63.99 KB / Downloads: 16)
INTRODUCTION
Face detection is the essential front end of any face recognition system, which locates and segregates face regions from cluttered images, either obtained from video or still image.
It also has numerous applications in areas like surveillance and security control systems, content-based image retrieval, video conferencing and intelligent human-computer interfaces.
Most of the current face recognition systems presume that faces are readily available for processing. However, in reality, we do not get images with just faces. We need a system, which will detect, locate and segregate faces in cluttered images, so that these segregated faces can be given as input to face recognition systems. Given an image, the goal of a face detection algorithm is to identify the location and scale of all the faces in the image. The task of face detection is so trivial for the human brain, yet it still remains a challenging and difficult problem to enable a computer to do face detection. This is because the human face changes with respect to internal factors like facial expression, beard and mustache, glasses etc and it is also affected by external factors like scale, lightning conditions, contrast between face and background and orientation of the face.
The current evolution of computer technologies has envisaged an advanced machinery world, where human life is enhanced by artificial intelligence. Indeed, this trend is already prompted an active development in machine intelligence. Face detection is one of the visual task which humans can do effortlessly. However, in computer vision terms, this task is not easy. Traditionally, computer vision systems have been used in specific task such as performing tedious and repetitive visual task of assembly line inspection. Current development in this area is moving towards more generalized vision applications such as face detection and recognization.
2. Joint Photographic Experts Group
JPEG (Joint Photographic Experts Group) files are (in most cases) a lossy format; the DOS filename extension is JPG (other operating systems may use JPEG). Nearly every digital camera can save images in the JPEG format, which supports 8 bits per color (red, green, blue) for a 24-bit total, producing relatively small files.The compression does not noticeably detract from the image's quality, but JPEG files suffer generational degradation when repeatedly edited and saved..
3. Exchangeable image file format
Exif (Exchangeable image file format) is an algorithm incorporated in the JPEG software used in most cameras. Its purpose is to record and to standardize the exchange of data between digital cameras and editing and viewing software. The data is recorded for individual images and includes such things as: camera settings, time and date, shutter speed, exposure, image size, compression, name of camera, color information, etc.
4. Tagged Image File Format The TIFF (Tagged Image File Format) is a flexible format that normally saves 8 bits or 16 bits per color (red, green, blue) for 24-bit and 48-bit totals, respectively, using either the TIFF or the TIF filenames.
5. Raw image format
RAW refers to a family of raw image formats that are options available on some digital cameras. These formats usually use a lossless or nearly-lossless compression, and produce file sizes much smaller than the TIFF formats of full-size processed images from the same cameras.
6. Graphics Interchange Format
GIF (Graphics Interchange Format) is limited to an 8-bit palette, or 256 colors. This makes the GIF format suitable for storing graphics with relatively few colors such as simple diagrams, shapes, logos and cartoon style images. The GIF format supports animation and is still widely used to provide image animation effects.
7. BMP file format
The BMP file format (Windows bitmap) handles graphics files within the Microsoft Windows OS. Typically, BMP files are uncompressed, hence they are large; the advantage is their simplicity and wide acceptance in Windows programs.
8. Portable Network Graphics
PNG (Portable Network Graphics) file format was created as the free, open-source successor to the GIF. The PNG file format supports truecolor (16 million colors) while the GIF supports only 256 colors. The lossless PNG format is best suited for editing pictures, and the lossy formats, like JPG, are best for the final distribution of photographic images.
Proposed Work
Face Recognition will have three modules. First module, Enrollment, will take the input face of the person and store it as an image file. The second module will extract the various parameters related to the stored file. In the third module that is verification, a face sample is compared with the database image files.
The parameters of the face will be extracted with the help of tools available in MATLAB and will be stored in different files.
For verification, again MATLAB tools will be used to compare the face sample against images present in database. After verification, if the match is found, access of the system will be granted otherwise the access will be denied.
1. Principal Component Analysis
Principal Component Analysis (or Karhunen-Loeve expansion) is a suitable strategy for face recognition because it identifies variability between human faces, which may not be immediately obvious. Principal Component Analysis (hereafter PCA) does not attempt to categorise faces using familiar geometrical differences, such as nose length or eyebrow width. Instead, a set of human faces is analysed using PCA to determine which 'variables' account for the variance of faces. In face recognition, these variables are called eigenfaces because when plotted they display an eerie resemblance to human faces.
2. AdaBoost
AdaBoost, short for Adaptive Boosting, is a machine learning algorithm, formulated by Yoav Freund and Robert Schapire. It is a meta-algorithm, and can be used in conjunction with many other learning algorithms to improve their performance. AdaBoost is adaptive in the sense that subsequent classifiers built are tweaked in favor of those instances misclassified by previous classifiers. AdaBoost is sensitive to noisy data and outliers. Otherwise, it is less susceptible to the overfitting problem than most learning algorithms.