Wyniki wyszukiwania - Biblioteka Nauki

1

Image retrieval based on hierarchical Gabor filters

100%

Andrysiak T. , Choraś M.

International Journal of Applied Mathematics and Computer Science

|

2005

|

tom 15

|

nr 4

471-480

EN

Content Based Image Retrieval (CBIR) is now a widely investigated issue that aims at allowing users of multimedia information systems to automatically retrieve images coherent with a sample image. A way to achieve this goal is the computation of image features such as the color, texture, shape, and position of objects within images, and the use of those features as query terms. We propose to use Gabor filtration properties in order to find such appropriate features. The article presents multichannel Gabor filtering and a hierarchical image representation. Then a salient (characteristic) point detection algorithm is presented so that texture parameters are computed only in a neighborhood of salient points. We use Gabor texture features as image content descriptors and efficiently emply them to retrieve images.

2

Forearm vein pattern recognition using features from visible and NIR images

88%

Choraś R. S.

Studia Informatica : systems and information technology

|

2024

|

tom vol. 1 (30)

5--19

EN

Forearm vein recognition is one of many available methods used for iden-tification. However, forearm veins can be considered more secure compared to otherbiometric traits because the veins are inside the human body and therefore not easilymanipulated. Veins possess several properties that make a good biometric feature forpersonal identification: 1) they are difficult to damage and modify; 2) they are difficultto simulate using a fake template; and 3) vein information can represent the liveness ofperson. Features were extracted from each pair of visible and NIR images. For the visibleimages, feature extraction was done using the Gabor filter. For the NIR forearm images,a crossing number was used to extract properties of the veins e.g. bifurcation. We presentthe results of the recognition of forearm veins patterns that show the suitability of themethod for biometric identification purposes.

3

Image retrieval based on hierarchical Gabor filters

63%

Andrysiak T. , Choraś M.

International Journal of Applied Mathematics and Computer Science

|

2005

|

tom Vol. 15, no 4

471-480

EN

Content Based Image Retrieval (CBIR) is now a widely investigated issue that aims at allowing users of multimedia information systems to automatically retrieve images coherent with a sample image. A way to achieve this goal is the computation of image features such as the color, texture, shape, and position of objects within images, and the use of those features as query terms. We propose to use Gabor filtration properties in order to find such appropriate features. The article presents multichannel Gabor filtering and a hierarchical image representation. Then a salient (characteristic) point detection algorithm is presented so that texture parameters are computed only in a neighborhood of salient points. We use Gabor texture features as image content descriptors and efficiently emply them to retrieve images.

4

Wykorzystanie filtrów Gabora do identyfikacji obrazów pisma odręcznego

63%

Niedziela T. , Hołyst B.

Prawo i Bezpieczeństwo

|

2024

|

tom 2(3)/2024

222-263

EN

The aim of the article is to assess the effectiveness of the use of Gabor filters in the identification and classification of images depicting handwriting, in particular in the context of recognition of letters, numbers or whole words. The article presents an optoelectronic method of identifying the characteristics of handwriting images based on the Gabor wavelet transform. This method has not been published anywhere before, but it opens up new perspectives for the study of handwriting. The research problem was formulated: Does the use of Gabor filters allow for effective feature extraction from handwriting images, enabling accurate identification and classification of characters compared to other feature extraction methods? Accordingly to the research problem posed, a research hypothesis was formulated, which assumes that Gabor filters, thanks to their ability to detect local patterns in images (such as edges, textures and directional structures), are an effective method of extracting features in tasks related to the identification of handwriting images, surpassing other commonly used methods in terms of classification accuracy. In the article, the authors proposed a simple algorithm for recognizing images in the diffraction space for forensic purposes. The question remains, can this method be used in practice? In order to obtain an answer to the research problem and verify the research hypothesis, research methods such as analysis of both domestic and foreign literature, comparative analysis, as well as mathematical modeling were used.

PL

Celem artykułu jest ocena efektywności zastosowania filtrów Gabora w identyfikacji oraz klasyfikacji obrazów przedstawiających pismo odręczne, w szczególności w kontekście rozpoznawania liter, cyfr lub całych słów. W artykule przedstawiono optoelektroniczną metodę identyfikacji cech charakterystycznych obrazów pisma odręcznego bazującą na transformacie falkowej Gabora. Metoda ta nie była nigdzie dotychczas publikowana a otwiera nowe perspektywy badania pisma ręcznego. Problem badawczy sformułowano: Czy zastosowanie filtrów Gabora pozwala na efektywną ekstrakcję cech z obrazów pisma odręcznego, umożliwiającą dokładną identyfikację i klasyfikację znaków w porównaniu do innych metod ekstrakcji cech? Odpowiednio do postawionego problemu badawczego sformułowano hipotezę badawczą, która zakłada, iż filtry Gabora, dzięki swojej zdolności do wykrywania wzorców lokalnych w obrazach (takich jak krawędzie, tekstury i struktury kierunkowe), są skuteczną metodą ekstrakcji cech w zadaniach związanych z identyfikacją obrazów pisma odręcznego, przewyższającą inne powszechnie stosowane metody pod względem dokładności klasyfikacji. Autorzy w artykule zaproponowali prosty algorytm rozpoznawania obrazów w przestrzeni dyfrakcyjnej dla celów kryminalistyki. Pozostaje pytanie, czy metoda ta może znaleźć zastosowanie w praktyce? W celu uzyskania odpowiedzi na problem badawczy i weryfikacji hipotezy badawczej zastosowane metody badawcze takie jak analiza literatury zarówno krajowej jak zagranicznej, analiza porównawcza, jak również modelowanie matematyczne.

5

Amplitude and Frequency Modulation in Speaker Recognition Systems

51%

Ciota Z.

International Journal of Microelectronics and Computer Science

|

2012

|

tom Vol. 3, nr 2

41-44

EN

The paper presents a review of the nowadays methods of voice vector extraction, applied in such speech processing, like person identification and emotion recognition. A special attention was held on mixed time-frequency analysis based on temporary frequency approach. The methods of calculation of time - frequency voice characterization were also described. The most important building blocks of identification and recognition of speakers have been presented. The characterization of feature vectors suitable for identification and verification in microcomputer systems was described. Components and appropriate method of speech identification based on the long-term spectra vectors were discussed.