Fisherface Research Papers - Academia.edu (original) (raw)

Face Recognition begins with extracting the coordinates of features such as width of mouth, width of eyes, pupil, and compare the result with the measurements stored inthe database and return the closest record (facial metrics).Nowadays,... more

Face Recognition begins with extracting the coordinates of features such as width of mouth, width of eyes, pupil, and compare the result with the measurements stored inthe database and return the closest record (facial metrics).Nowadays, there are a lot of face recognition techniques and algorithms found and developed around the world. Facial recognition becomes an interesting research topic. It is proven by numerous number of published papers related with facial recognition including facial feature extraction, facial algorithm improvements, and facial recognition implementations. Main purposes of this research are to get the best facial recognition algorithm (Eigenface and Fisherface) provided by the Open CV 2.4.8 by comparing the ROC (Receiver Operating Characteristics) curve and implement it in the attendance system as the main case study. Based on the experiments, the ROC curve proves that using the current training set, Eigenface achieves better result than Fisherface. Eigenface implemented inside the Attendance System returns between 70% to 90% similarity for genuine face images.

The facial recognition process can be defined as an almost instinctive process for the human being where the same can recognize other individuals normally by patterns o the face of the same. Due to technological advances there are studies... more

The facial recognition process can be defined as an almost instinctive process for the human being where the same can recognize other individuals normally by patterns o the face of the same. Due to technological advances there are studies and technologies that aim to take this process from the human vision of recognition to the computer vision where the same seeks to accomplish this same process faster than a common human performing, in a process similar to human recognition, the system is presented to an image it identifies patterns in it and searches in its training base. Through the use of biometrics, people can be recognized and authenticated, for example by choosing which people will be able to access certain places or resources. However, biometrics not only focuses on monitoring people's access, it also has the competence to conduct extensive support in the forensic field, surveillance, identification of missing persons, Those are just some possible applications. The process of recognizing an image or a face has been applied in several areas, either in information security where an algorithm has the function of allowing access to data from the moment the user is recognized and varying the amount of information that the same receives, public security where the algorithm would have the function of finding areas of risk and even identify fugitives. The objective of this work is to clearly evaluate the concept of face recognition, its use and its applicability, through an application for recognition developed in the C# language to meet the needs of the Ministry of the Environment that needs an application for identification and authentication biometric model that restricts access to a network with data bank, which has information about large properties that use pollutants that cause great impact on the environment. The work was qualitative, based on works published by expert scholars, who have already pointed out the concepts, uses, applications, performance and failures of certain types of recognition algorithms.

Within the past decade, major advances have occurred in face recognition. Many systems have emerged that are capable of achieving recognition rates in excess of 90% accuracy under controlled conditions. In field settings, face images are... more

Within the past decade, major advances have occurred in face recognition. Many systems have emerged that are capable of achieving recognition rates in excess of 90% accuracy under controlled conditions. In field settings, face images are subject to a wide range of variation that includes viewing, illumination, occlusion, facial expression, time delay between acquisition of gallery and probe images, and individual differences. The scalability of face recognition systems to such factors is not well understood. We quantified the influence of these factors, individually and in combination, on face recognition algorithms that included Eigenfaces, Fisherfaces, and FaceIt. Image data consisted of over 37,000 images from 3 publicly available databases that systematically vary in multiple factors individually and in combination: CMU PIE, Cohn-Kanade, and AR databases. Our main findings are: 1) pose variations beyond Æ head rotation substantially depressed recognition rate, 2) time delay: pic...