Wyniki wyszukiwania - BazTech

1

An attempt to improve Eigenface algorithm efficiency for colour images

Orczyk T., Porwik P.

Journal of Medical Informatics & Technologies

|

2010

|

Vol. 16

201--207

EN

This article presents an attempt to improve Eigenface algorithm efficiency by using image pre–filtering in order to eliminate background areas of the picture and illumination influence. The background is treated as noise, so when noise is present then efficiency of the algorithm decreases. In order to eliminating this inconvenience, analysed image is pre–filtered by means of the colour classifier. The classifier eliminates pixels which have different colour than an average human skin colour on a digital photo. This causes that the Eigenface algorithm is less sensitive to background noise. The illumination influence was minimized by using hue information instead of traditionally used luminance. The main advantage of the proposed approach is possibility of using in environments where diverse image background texture and scene illumination appears. The eigenfaces technique can be applied in handwriting analysis, voice recognition, hand gestures interpretation and medical imaging.

2

Sparse Bayesian learning in classifying face feature vectors

Momot A., Kawulok M.

Journal of Medical Informatics & Technologies

|

2005

|

Vol. 9

151--158

EN

The Relevance Vector Machine (RVM), a Bayesian treatment of generalized linear model of identical functional form to the Support Vector Machine (SVM), is the recently developed machine learning framework capable of building simple models from large sets of candidate features. The paper describes the application of the RVM to a classification algorithm of face feature vectors, obtained by Eigenfaces method. Moreover, the results of the RVM classification are compared with those obtained by using both the Support Vector Machine method and the method based on the Euclidean distance.

3

Application of Support Vector Machines in automatic human face recognition

Kawulok M.

Journal of Medical Informatics & Technologies

|

2005

|

Vol. 9

143--150

EN

This paper presents the possibilities of applying the Support Vector Machines (SVM) in the process of automatic human face recognition. It is described how the existing methods of face recognition can be improved by the SVM. Moreover, a new approach to the multi-method fusion utilising the SVM is proposed. Usefulness of all the methods described in the paper improving the face recognition effectiveness by the SVM is confirmed by the experimental results.

4

Automatic human face recognition method based on geometrical face features

Makieła M., Kotarski W., Lisowska A.

Journal of Medical Informatics & Technologies

|

2003

|

Vol. 5

MI47--56

EN

There are many ways to describe and recognize the human face. The paper shows one of them - the feature based method. It also considers usefulness of the face geometrical measurements in recognition and also the geometrical dependence on the features. The paper treats on the feature points detection and takes into consideration six of them, which are: two eyes, two eyebrows, nose and lips. It shows a detailed algorithm of the proposed method and describes its advantages and disadvantages. It also describes a filtering, feature points extraction and gives formulas for calculation of a face likeness coordinates. At the very end it concludes with experiments and examples of the proposed method.

5

Lokalna analiza składowych głównych drugiego rzędu w rozpoznawaniu twarzy

Pietrowcew A., Skarbek W.

Elektronizacja : podzespoły i zastosowania elektroniki

|

2003

|

Vol. 23, nr 4

29-31

PL

Lokalna analiza składowych głównych, tj. analiza składowych głównych wykonana w klastrach danych, jest rozważana jako narzędzie algorytmiczne w problematyce rozpoznawania twarzy. Stosuje się ją w celu znalezienia lokalnych, liniowych modeli danych zapewniających zwartą reprezentację obrazów twarzy. Wstępne wyniki badań pokazują, że wspomniana technika umożliwia uzyskanie współczynnika rozpoznawania na poziomie ok. 97% dla niepełnych klastrów danych.

EN

Local second order principal component analysis, e. g. principal component analysis in data cluster, is used as the algorithmic tool in the field of face recognition. It finds local linear models for specific face poses and lighting conditions independently and guarantees compact face image representation. Experimental results show that proposed method allows to achieve high recognition rate, to the level of 97,5% for incomplete data clusters.

6

Identyfikacja biometryczna - blaski i cienie

Swarcewicz R.

Logistyka

|

2002

|

R. 32, nr 4

44-47