Wyniki wyszukiwania - BazTech

1

Sketch generation from photo to create test databases

Kukharev G., Buda K., Nadegda S.

Przegląd Elektrotechniczny

|

2014

|

R. 90, nr 2

97--100

PL

Artykuł przedstawia stan wiedzy z zadań porównania portretów pamięciowych (szkic) i odpowiednich im portretów fotograficznych. Zaproponowano nowatorskie metody automatycznego generowania szkicu z portretów fotograficznych popularnych baz obrazów twarzy. Przedstawiono, że wysoką jakość rozpoznawania szkiców można osiągnąc w ramach prostych systemów rozpoznawania.

EN

Article proposed novel method of automatic sketch synthesis, that can be used for creating test databases and sketch recognition tasks research and retrieval of corresponding photo. These methods were applied to two popular benchmark face databases. It was shown that for recognition of sketches very simple systems can be used.

2

An algorithm of face recognition under difficult lighting conditions

Forczmański P., Kukharev G., Shchegoleva N. L.

Przegląd Elektrotechniczny

|

2012

|

R. 88, nr 10b

201-204

EN

The paper addresses the problem of face recognition for images with lighting problems – flashes, shadows and very low brightness level. Presented algorithm, allowing to eliminate above problems, is based on 2DDCT (two-dimensional Discrete Cosine Transform) supported by brightness gradient reduction, reduction of spatial low frequency spectral components and fusion of spectral features conditioned on average intensities. Presented experiments were conducted on image databases Yale B and Yale B+.

PL

W artykule zaprezentowano zadanie rozpoznawania twarzy na podstawie obrazów uzyskanych w trudnych warunkach oświetleniowych, posiadających odbłyski, cienie i niski poziom jasności. Zaprezentowany algorytm pozwala na wyeliminowanie wymienionych problemów i bazuje na dwuwymiarowej dyskretnej transformacie kosinusowej połączonej z redukcją gradientu jasności, eliminację niskoczęstotliwościowych komponentów widma i fuzji komponentów widma zależnej od średniej jasności obrazu. Jako uzupełnienie, przedstawiono eksperymenty przeprowadzone na bazach Yale B i Yale B+.

3

Application of cascading two-dimensional canonical correlation analysis to image matching

Forczmański P., Kukharev G., Kamenskaya E.

Control and Cybernetics

|

2011

|

Vol. 40, no 3

833-848

EN

The paper presents a novel approach to Canonical Correlation Analysis (CCA) applied to visible and thermal infrared spectrum facial images. In the typical CCA framework biometrical information is transformed from original feature space into the space of canonical variates, and further processing takes place in this space. Extracted features are maximally correlated in canonical variates space, making it possible to expose, investigate and model latent relationships between measured variables. In the paper the CCA is implemented along two directions (along rows and columns of pixel matrix of dimension M x N) using a cascade scheme. The first stage of transformation proceeds along rows of data matrices. Its results are reorganized by transposition. These reorganized matrices are inputs to the second processing stage, namely basic CCA procedure performed along the rows of reorganized matrices, resulting in fact in proceeding along the columns of input data matrix. The so called cascading 2DCCA method also solves the Small Sample Size problem, because instead of the images of size MxN pixels in fact we are using N images of size M x 1 pixels and M images of size 1 x N pixels. In the paper several numerical experiments performed on FERET and Equinox databases are presented.

4

Two-dimensional principal component analysis for face image representation and recognition

Kukharev G., Shchegoleva N.

Metody Informatyki Stosowanej

|

2010

|

nr 3 (23)

149-168

EN

Paper presents two-dimensional principal component analysis (2D PCA) applications for face image analysis. The method is based on representation of an image as a collection of its rows and columns, and application of PCA to these collections. Two versions of 2D PCA implementation called parallel and cascade forms and their specific characteristics are presented. In experiments both forms are applied to representation and recognition of face images using two standard databases ORL and FERET.

5

Facial portraits matching by means of two-dimensional CCA and PLS

Kukharev G., Tujaka A., Formaczyński P.

Metody Informatyki Stosowanej

|

2010

|

nr 1 (22)

69-86

EN

Paper presents implementation of the method of two-dimensional canonical correlation analysis and two-dimensional partial least squares applied to image matching. Both methods are based on representing the image as the sets of its rows and columns and implementation of CCA using these sets (hence we named the methods as CCArc and PLSrc). CCArc and PLSrc features simple implementation and lesser complexity than other known approaches. In applications to biometrics, CCArc and PLSrc are suitable to solving the problems when dimension of images (dimension of feature space) is greater than number of images, i.e. Small Sample Size problem (SSS). The paper demonstrates high efficiency of CCArc and PLSrc for a number of computer experiments using benchmark image databases.

6

Metoda ekstrakcji cech orientowana na sprzętową realizację w zadaniach rozpoznawania obrazów

Kukharev G., Sałuda R., Mikłasz M., Kawka G.

Pomiary Automatyka Kontrola

|

2009

|

R. 55, nr 8

563-565

PL

Rozpoznawanie obrazów to zadanie realizowane najczęściej przez skomplikowane i złożone metody. Jednak wykorzystanie zestawu prostych i szybkich metod pozwala na dorównanie skutecznością systemom używającym skomplikowanych podejść. Rozwiązanie to ma dodatkowy plus - łatwość implementacji sprzętowej. W artykule przedstawiono podejście analizujące lokalną symetryczność obrazu, które pomimo swojej prostoty, wykazało się dużą skutecznością. Przeprowadzone eksperymenty pokazały, że omawiana metoda ekstrakcji cech z obrazu może mieć bezpośrednie zastosowanie w systemach rozpoznawania, a jej prostota pozwala na sprzętową realizację. Dodatkową zaletą prezentowanej metody jest jej inwariantność od oświetlenia twarzy. Dzięki temu istnieje możliwość znaczącej poprawy wydajności całego systemu rozpoznawania.

EN

The paper presents the results of investigations concerning face recognition systems based on a simple, fast and efficient feature extractor method. It is based on analysis of the local image symmetry. An additional advantage of the described method is the fact that it is light invariant feature extractor - so it is called LIFE. This benefit (robust on the light conditions) makes it possible to use the method practically as the hardware implementation in real monitoring systems. The idea of LIFE operation is described in Section 2 of the paper. The performed experiments, presented in Section 3 show that LIFE is very efficient in comparison with other simple feature extractor methods - the results of recognition are given in Table 1. In spite of the method simplicity, the proposed approach proved high effectiveness which may be further increased by joining LIFE into a parallel structure with another simple feature extractor (it is described in Section 4). The presented feature extractor enables implementation in hardware system (simplicity and efficiency) such as cameras of the monitoring system. This idea is discussed in the conclusions.

7

Two-dimensional canonical correlation analysis for face image processing and recognition

Kukharev G., Kamenskaya E.

Metody Informatyki Stosowanej

|

2009

|

nr 3 (20)

103-112

EN

Paper presents the method of two-dimensional canonical correlation analysis (2DCCA) as applied to image processing and biometrics. Method is based on representing the image as the sets of its rows (r) and columns (c) and implementation of CCA using these sets (for these reason we named the method as CCArc). CCArc features simple implementation and lesser complexity than other known approaches. In applications to biometrics CCArc is suitable to solving the problems when dimension of images (dimension of feature space) is greater than number of images, i.e. Small Sample Size problem (SSS). Demonstrated high efficiency of CCArc method for a number of computer experiments. Experiments itself are described with compact notation allowing to use its results in the framework of meta-analysis.

8

Method of clones generation from the digital images

Kukharev G., Tujaka A.

Metody Informatyki Stosowanej

|

2009

|

nr 1 (18)

53-68

EN

Paper addresses the problem of cloning the input image, especially for frontal face image recognition. Presented are two methods of cloning, one based on procedure of downsampling, and other based on modified wavelet transform. Implementations of both procedures are described as well as salient features of "clone-images ", making it useful for image recognition. Cloning enables application of strong classification methods, e.g. linear discriminant analysis (LDA) by avoiding the small sample size problem. Application of "cloning + LDA" is illustrated by face recognition problem with one training image per person.

9

System of face recognition using LDA with one training image per person

Kukharev G., Tujaka A., Binh N.T

Metody Informatyki Stosowanej

|

2008

|

nr 3 (Tom 16)

167--185

EN

The paper addresses the problem of face recognition, using matrix description of original face images. Reduced dimensionality matrix representation of face image is obtained with linear discriminant analysis (LDA) applied simultaneously to rows and columns of original image matrix, called LDArc. We have extended the applicability of LDA to a case of one training image per person, using simple methods of training image “replication” with so called “down-sampling” procedure. Developed method is applied with success to a few well known face database, like ORL, FERET and Face94.

10

Some aspects of automated psychological characteristics recognition from the facial image

Kamenskaya E., Kukharev G.

Metody Informatyki Stosowanej

|

2008

|

nr 2 (Tom 15)

29-37

EN

Identification of psychological characteristics is a task widely used in theoretical and practical psychological research, education, coaching, career guidance and hiring process, business and political affairs, psychotherapeutic diagnostics, self-exploration and awareness, etc. The. paper contains some, consideration of the computer system of automated psychological characteristics recognition from the facial image, such as a basic schema of its operation, image processing and analysts methods which can be applied, holistic and feature-based approaches, image databases for experiments, etc.

11

Recognition of Psychological Characteristics from Face

Kamenskaya E., Kukharev G.

Metody Informatyki Stosowanej

|

2008

|

nr 1 (Tom 13)

59-73

EN

Tht nature of computer vision causes the fact that not only computer science researchers are interested in it, but neuroscientists and psychologists, too. Ont of the main interests for psychology is identification of person's psychological traits and personality types which can be accomplished by different means of psychological testing: questionnaires, interviews, direct observations, etc. Though that is a general tendency of people to read character into a person's physical form, especially face. in relation to psychological characteristics recognition, face provides researchers and psychologists with instrument of obtaining information about personality and psychological traits that would be much more, objective than questionnaires and in iiropsychological tests and could be obtained remotely using person's facial portrait, with no need for personal, involvement The paper describes approaches to psychological characteristics recognition from facial image such us physiognomy, phase facial portrait, ophthalmogeometry, and explains the need in automating it.

12

Strategia budowy systemów klasy "Face Retrieval"

Kukharev G., Mikłasz M., Binh N.T

Metody Informatyki Stosowanej

|

2007

|

nr 2(Tom 12)

61-72

PL

W artykule przedstawiono strukturę i model specyficznego FaRetSys. Przedstawiono sposoby działania oraz zastosowania FaRetSys. Ocena skuteczności wyszukiwania podobnych do QF obrazów twarzy, została uzasadniona teoretycznie i udowodniona drogą eksperymentów na standardowych bazach obrazów twarzy: FERET i ORL.

EN

In this article, the problem of retrieval faces similar to the pattern from large, national and international face databases it addressed. The mam assumptions of face database and appropriate strategies in forming face retrieval system are described. The article also presents the idea of specialized FaRetSys working in the cascade structure. High efficiency of the proposed system was proved in the theoretical and experimental way on the standard face images databases: ORL and FERET.

13

Facial images dimensionality reduction and recognition by means of 2DKLT

Kukharev G., Forczmański P.

Machine Graphics and Vision

|

2007

|

Vol. 16, No. 3/4

401-425

EN

Paper presents an efficient dimensionality reduction method for images (e.g. human faces databases). It does not require any usual pre-processing stage (like down-scaling or filtering). Its main advantage is associated with efficient representation of images leading to accurate recognition. Analysis is performed using two-dimensional Principal Component Analysis and Linear Discriminant Analysis and reduction by means of two-dimensional Karhunen-Loeve Transform. The paper presents mathematical principles together with some results of recognition experiments on popular facial databases. The experiments performed on several facial image databases (BioID [11], ORL/AT&T [3], FERET [8], Face94 [4] and Face95 [5]) showed that face recognition using this type of feature space dimensionality reduction is particularly convenient and efficient, giving high recognition performance.

14

Wykorzystanie prostych ekstraktorów cech obrazu w programowosprzętowych systemach biometrycznych

Kukharev G., Forczmański P., Nowosielski A.

Pomiary Automatyka Kontrola

|

2006

|

R. 52, nr 7 bis

77--79

PL

W artykule przedstawiono wyniki badań nad systemami rozpoznawania twarzy bazującymi na stosunkowo prostych cechach obrazu cyfrowego wynikających ze skalowania, pseudo-losowego wyboru punktów, histogramu jasności oraz transformacji obrazu (DFT, DCT). Proponowane podejście, pomimo swojej prostoty, wykazało się dużą skutecznością, która może być dalej poprawiona poprzez zastosowanie kaskadowego łączenia deskryptorów obrazów (co również zostało opisane w pracy). Przeprowadzone eksperymenty pokazały, że omawiane ekstraktory cech mogą mieć bezpośrednie zastosowanie w biometrycznych systemach identyfikacji osób bazujących w dużej mierze na rozwiązaniach sprzętowych (prostota i wydajność).

EN

It the article we present results of our investigations on face recognition systems based on features resulted from relatively simple operations: scale, random selection of points, histogram and image transforms (DFT, DCT). In spite of its simplicity, the proposed approach proved high effectiveness which may be further increased by joining these simple feature extractors into a parallel structure (also described in the paper). Performed experiments demonstrated that described feature extractors may have straightforward implementation in biometric hardware system (simplicity and efficiency).

15

Two-dimensional LDA approach to image compression and recognition

Kukharev G., Forczmański P.

Computing, Multimedia and Intelligent Techniques

|

2006

|

Vol. 2, nr 1

45-53

EN

The paper presents a novel method of reducing the dimensionality of large datasets (e.g. human faces databases). It does not incorporate any usual pre-processing stage (like down-scaling or filtering). Its main advantage is associated with efficient representation of images leading to the accurate recognition. The reduction is realized by modified Linear Discriminant Analysis. In the paper, the authors present its mathematical principles together with some results of practical recognition experiments on popular facial databases (ORL, BioID).

16

Structure and characteristics of face recognition

Kukharev G., Kuźmiński A., Nowosielski A.

Computing, Multimedia and Intelligent Techniques

|

2005

|

Vol. 1 nr 1

111-124

EN

In this paper we describe structures and properties of face recognition systems (FaReS) and present example solutions to Name-It, Visitor Identification and Access Control problems.

17

Face recognition using the histogram of the face image

Kukharev G., Kuźmiński A.

Computing, Multimedia and Intelligent Techniques

|

2005

|

Vol. 1 nr 1

61-71

EN

In this paper we describe the feature extractor assigned to face recognition systems. The extraction is based on the histogram calculation for face images. With the help of this feature extractor the face recognition becomes very fast and efficient. Moreover, the recognition process can be performed under conditions, where other approaches fail.

18

Face based identification of people from a video stream

Kukharev G., Nowosielski A.

Computing, Multimedia and Intelligent Techniques

|

2005

|

Vol. 1 nr 1

99-110

EN

This paper presents an analysis of the problem of people identification based on the images of their faces received from a video stream. Considering a single scene image, the task of the identification consists of detection of faces and then the process of recognition follows. In a real-life face recognition system we have a sequence of consecutive images where the number of faces, their localizations, their sizes and orientations are unknown. Considering a video stream all those parameters listed above change with time but not significantly from frame to frame. By tracking a face in a sequence and aggregating individual results of face recognition, a much stable and reliable final recognition result may be obtained. Based on the analysis of the problem the algorithm for people identification from a video stream is developed.

19

Fast and efficient algorithm for face detection in colour images

Kukharev G., Nowosielski A.

Machine Graphics and Vision

|

2004

|

Vol. 13, No. 4

377-399

EN

Detecting human faces automatically is an indispensable step in any system that exploits information content in a face. The surveillance systems are of particular interest in that field. To correctly recognize a person from an input image, presence and location of the head must be determined in the first step. If the face detection subsystems fails, the performance of the whole system suffers. In the article a scheme for detecting faces in colour images is proposed. It utilizes the skin colour method with a new approach to detecting skin colour pixels in the RGB colour space. The edge information is used to increase the distinction between the skin-coloured face patches and the background. It is followed by a scan line candidate determination algorithm. A new method (combining profiles, geometrical moments, the use of the R-B colour subspace and grey level images) for eyes localization is presented. The verification is finally made based on a well-known template matching approach. After new methods and modifications were evaluated, a system based on the proposed scheme was built and tested.

20

Data dimensionality reduction for face recognition

Kukharev G., Forczmański P.

Machine Graphics and Vision

|

2004

|

Vol. 13, No. 1/2

99-121

EN

In the process of image recognition in most of the applications there is a problem with gathering, processing and storing large amounts of data. A possible solution for reducing this amounts and speeding--up computations is to use some sort of data reduction. Efficient reduction of the stored data without losing any important part of it requires an adaptive method, which works without any supervision. In this article we discuss a few variants of a two--step approach, which involves Karhunen--Loeve Transform (KLT) and Linear Discriminant Analysis (LDA). The KLT gives a good approximation of the input data, however it requires a large number of eigenvalues. The second step reduces data dimensionality futher using LDA. The efficiency of KLT depends on the quality and quantity of the input data. In the case when only one image in a class is given as input, its features are not stable in comparison with other images in other classes. In this article we present a few methods for solving this problem, which improve on the ideas presented in [6, 9].