April 22, 2013
Brian Uldall, Ph.D.
As people age, they want to remember things from his or her past. The mind ages as the body does. As one grows older, the physical and mental changes start to appear. This paper will evaluate face recognition, identification, and classification on it. The second part will explain the role of concepts and categories in face recognition. The paper will evaluate the role of encoding and retrieval using long-term memory and the effects of face recognition. Finally, the possibly of errors can happen with race recognition. Face Recognition, Identification, and Classification
Over the past decade or so face recognition has become a popular area of research in computers and using most successful applications to develop further. Computer applications are available for face recognition. Other programs used are voice recognition, handwriting recognition, intelligent tutoring systems, writing, and computer supported learning. Voice recognition is an important tool for student’s developmental disabilities that no other standard teaching methods work. Hand writing recognition is the software that interprets the writing down on an electronic tablet. Intelligent tutoring systems are computer applications that let students answer questions. Writing assessment can read a student’s essay. Computer supported collaborative learning is to work with groups in a classroom. Faces are important because people are social creatures. Faces help people deal with social interactions that are parts of his or her lives. As people, we gather information about identity, gender, age, ethnicity, and emotions. It helps to read information on faces as a component, understand a person’s perception, and is sensitive to the differences between visual patterns. “Our face recognition skills are particularly impressive and our ability to discriminate thousands of faces has often been attributed to expertise acquired through extensive experience discriminating faces,” (Jeffery & Rhodes, 2011, p. 799). Face recognition is to find any face in any given images based on his or her facial features using elements of distinction. Correlation method is the first thought to begin with face recognition. “The two important approaches for face recognition are: geometric (feature based) and photometric (view based),” (Mishna, Swain, & Dash, 2012, p. 143). Researchers developed Principal Components Analysis (PCA), Linear Discriminant Analysis (LDA), and Elastic Bunch Graph Matching (EBGM). PCA uses images that are the same size and line-up the eyes and mouth. PCA uses eigenfaces. LDA “approach maximizes the variance across users called the between-class variance and minimizes the variance within classes called within class variance,” (Mishna, Swain, & Dash, 2012, p. 144). EBGM relies on real face images using variations in illumination, pose, and expressions. Concepts and Categories in Face Recognition
It appears face recognition wants to identity facial features. Trying to verify new face images belongs to one whose image is stored aims to identity in case recognition. A person is comparing others stored in a database, classifying as a well-known or as unknown. Face techniques describes in three categories template-based, featured-based, and appearance-based. Temple-based method uses two-dimensional along with facial borders and organs. “Feature-based method considers the positions and sizes of the facial organs, nose, mouth, etc., in the face representation,” (Mishra, Swain, & Dash, 2012, p. 146). Appearance-based puts the image in a low dimensional to obtain representation. Eigen faces approach uses approximate the face in lower dimension. Algorithm collects images, define, calculate distribution, face recognition, input, calculate key, classification of image, and face recognition. “Our face recognition skills...
Please join StudyMode to read the full document