CCL

Összesen 5 találat.
#/oldal:
Részletezés:
Rendezés:

1.

001-es BibID:BIBFORM065978
035-os BibID:(cikkazonosító)30091655
Első szerző:Azodinia, Mohammadreza (informatikus)
Cím:A novel method to increase the performance of recommender systems using a parallel CBIR approach / Mohammad Reza Azodinia, András Hajdu
Dátum:2016
ISSN:1947-5500
Megjegyzések:Recommender systems are among the most valuable components that can improve the user experience with a more general system considerably when embedded inside that system. The main objective of recommender systems is to reduce the complexity for users, sifting through very large datasets containing information about some items and selecting the most desired ones. In order to provide the users with such items, the recommender system should consider as much related information as possible in taking the decisions about the desirability of the items. One of the key features that has a major effect on people's point of view towards an item is the image which is assigned to that item. Despite the large number of studies carried out around the notion of the recommender systems, images have not gained a fair amount of attention which has derived us to conduct this study. In this paper we have proposed a novel method to effectively consider the images of the items in the recommender systems to improve the quality of the recommendations. The proposed method is implemented and tested on a significant dataset, and the result prove the effectiveness of our method.
Tárgyszavak:Műszaki tudományok Informatikai tudományok idegen nyelvű folyóiratközlemény külföldi lapban
Keywords-recommender system
Content Based Image Retrieval
Parallel CBIR
Megjelenés:International Journal of Computer Science and Information Security. - 14 : 10 (2016), p. 205-213. -
További szerzők:Hajdu András (1973-) (matematikus, informatikus)
Pályázati támogatás:NK101680
OTKA
TAMOP-4.2.2.C- 11/1/KONV2012-0001
TÁMOP
TAMOP-4.2.2.A- 11/1/KONV2012-0045
TÁMOP
TÁMOP 4.2.4. A/2-11-1- 2012-0001
TÁMOP
Internet cím:Intézményi repozitóriumban (DEA) tárolt változat
Borító:

2.

001-es BibID:BIBFORM065976
035-os BibID:(WOS)000392925600007 (Scopus)85005978087
Első szerző:Azodinia, Mohammadreza (informatikus)
Cím:A novel combinational relevance feedback based method for content-based image retrieval / Mohammadreza Azodinia, András Hajdu
Dátum:2016
ISSN:1785-8860
Megjegyzések:Due to the extensive use of images in various fields, using effective approaches to retrieve the most related images given a query image is of great importance. Content-based image retrieval is the approach commonly used to address this issue. The content-based image retrieval systems use many techniques to provide more accurate and comprehensive answers, among which is the relevance feedback. The relevance feedback is used by the system to help it retrieve more relevant images in response to a query. In this paper we have proposed a novel relevance feedback method that is able to improve the precision of the content-based retrieval systems. The proposed method is based on multi-query relevance feedback, and similarity function refinement.
Tárgyszavak:Műszaki tudományok Informatikai tudományok idegen nyelvű folyóiratközlemény hazai lapban
folyóiratcikk
CBIR image retrieval
CBVIR information retrieval
Image database
Recommender system
Megjelenés:Acta Polytechnica Hungarica. - 13 : 5 (2016), p. 121-134. -
További szerzők:Hajdu András (1973-) (matematikus, informatikus)
Pályázati támogatás:VKSZ_14-1-2015-0072
Egyéb
Internet cím:Intézményi repozitóriumban (DEA) tárolt változat
DOI
Szerző által megadott URL
Borító:

3.

001-es BibID:BIBFORM063707
Első szerző:Azodinia, Mohammadreza (informatikus)
Cím:A method for image retrieval using combination of color and frequency layers / Mohammad Reza Azodinia, András Hajdu
Dátum:2015
ISSN:0975-8887
Megjegyzések:In this paper a fast and effective noise-resistant method for image retrieval has been proposed. In this method, first, the image is decomposed into different frequency layers using complex wavelet transform so as to make it possible to extract the texture features of the image. Thereafter, in the HSV color space, each layer is quantized into 166 different colors and the color histogram is calculated for each layer. Furthermore, a number of statistical features are extracted from each sub-image using complex wavelet transform, which are used along with other features for image retrieval. In order to verify the effectiveness of the proposed method, it has been evaluated using a dataset containing 3000 images and compared to a competent method in this field. The results prove the superiority of the proposed method.
Tárgyszavak:Műszaki tudományok Informatikai tudományok idegen nyelvű folyóiratközlemény külföldi lapban
Color feature
complex wavelet transform
Content-based image retrieval
feature extraction
histogram
image processing
texture feature
Megjelenés:International Journal of Computer Applications 118 : 3 (2015), p. 10-13. -
További szerzők:Hajdu András (1973-) (matematikus, informatikus)
Pályázati támogatás:NK101680
OTKA
TAMOP-4.2.2.C-11/1/KONV2012-0001
TÁMOP
TAMOP-4.2.2.A-11/1/KONV-2012-0045
TÁMOP
TÁMOP 4.2.4. A/2-11-1-2012-0001
TÁMOP
Internet cím:Szerző által megadott URL
DOI
Intézményi repozitóriumban (DEA) tárolt változat
Borító:

4.

001-es BibID:BIBFORM063704
Első szerző:Azodinia, Mohammadreza (informatikus)
Cím:A recommender system that deals with items having an image as well as quantitative features / Mohammadreza Azodinia, Andras Hajdu
Dátum:2015
Megjegyzések:A big part of data around us is in image format and people use these images in many of their decisions. The popularity of an item, in many cases, depends highly on its visual quality. For instance, the shape of a car has a significant influence on the attitude of potential customers toward it. Recommender systems try to provide people with recommendations resulted from an automatic process which is aimed at giving the users a better experience working with system, and perhaps improve the system owner's sales. As images are quite important in users' decisions, in this paper we have proposed a method to take images into account when trying to give the user a recommendation, which despite its apparent advantages has not found a fair amount of attention so far.
ISBN:978-1-4799-7252-4
Tárgyszavak:Műszaki tudományok Informatikai tudományok könyvfejezet
recommender systems
image retrieval
similarity metric
collaborative filtering
content-based filtering
prediction
hybrid
Megjelenés:Proceedings of the 9th International Symposium on Intelligent Signal Processing (WISP), 2015 May 15-17, Siena. - p. 1-6. -
További szerzők:Hajdu András (1973-) (matematikus, informatikus)
Pályázati támogatás:NK101680
OTKA
TAMOP-4.2.2.C- 11/1/KONV2012-0001
TÁMOP
TAMOP-4.2.2.A-11/1/KONV-2012- 0045
TÁMOP
TÁMOP 4.2.4. A/2-11-1-2012-0001
TÁMOP
Internet cím:Szerző által megadott URL
DOI
Intézményi repozitóriumban (DEA) tárolt változat
Borító:

5.

001-es BibID:BIBFORM063702
Első szerző:Azodinia, Mohammadreza (informatikus)
Cím:Constant time median filtering of extra large images using Hadoop [elektronikus dokumentum] / Mohammadreza Azodinia, Vahid Farrokhi, Andras Hajdu
Dátum:2015
Megjegyzések:Letöltés ideje: 2016.09.19.
The spatial resolution of remote sensing and medical images such as MRI,CT and PET are constantly increasing and analyzing these images in real timeis a challenging task. But this limits the efficiency of many image processing algorithms. Among different efficient image processing algorithms, median filtering is a principal element in many image processing situations which manages to reduce the noise while preserving the edges. Median Filteringin Constant Time (MFCT) is a simple yet fastest median filtering algorithm which can handle N-dimensional data in fields like medical imaging and astronomy. With trend toward the median filtering of large images and proportionally large kernels, Hadoop MapReduce (a popular big data processing engine) can be applied and utilized. MapReduce provides the simplicity of defining the map and reduce functions while the framework takes care of parallelization and failover automatically. Hence, in this paper we discuss on possibility of the incorporation of MFCT algorithm with Hadoop MapReduce framework to improve the performance of processing of extra large images.
Hozzáférés: Internet
ISBN:978 615 5297 18 2
Tárgyszavak:Műszaki tudományok Informatikai tudományok könyvfejezet
median filtering
MFCT
MapReduce
Hadoop
parallelization
Megjelenés:Proceedings of the 9th International Conference on Applied Informatics January 29 - Februar 1, 2014. Eger, Hungary Volume I [elektronikus dokumentum] / ed. by Kovács Emőd, Kusper Gábor, Kunkli Roland, Tómács Tibor. - Vol. 1., p. 93-101. -
További szerzők:Farrokhi, Vahid (1966-) (informatikus) Hajdu András (1973-) (matematikus, informatikus)
Internet cím:Szerző által megadott URL
DOI
Intézményi repozitóriumban (DEA) tárolt változat
Borító:
Rekordok letöltése1 
Corvina könyvtári katalógus v8.2.27 © 2023 Monguz kft. Minden jog fenntartva.