Zobrazeno 1 - 10
of 15
pro vyhledávání: '"Bharathi Pilar"'
Publikováno v:
Computer Vision and Machine Intelligence ISBN: 9789811978661
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3b3d1dc8f22b228bee570b9a35431323
https://doi.org/10.1007/978-981-19-7867-8_37
https://doi.org/10.1007/978-981-19-7867-8_37
Publikováno v:
2022 IEEE 7th International Conference on Recent Advances and Innovations in Engineering (ICRAIE).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::45c61e2fc3f5e4f4f98179a02b3eda40
https://doi.org/10.1109/icraie56454.2022.10054336
https://doi.org/10.1109/icraie56454.2022.10054336
Autor:
Bharathi Pilar
Publikováno v:
Communications in Computer and Information Science ISBN: 9789811604249
This paper presents Spatial Pyramid image representation based technique with partial sum of second order Taylor Series Expansion (TSE) for offline signature verification. In this approach, the given signature image is partitioned into sub blocks rec
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::994887df505739a30741b6171b87a276
https://doi.org/10.1007/978-981-16-0425-6_5
https://doi.org/10.1007/978-981-16-0425-6_5
Publikováno v:
Communications in Computer and Information Science ISBN: 9789811391866
RTIP2R (3)
RTIP2R (3)
This paper presents a powerful feature representation method called Multi-scale Local Binary Patterns for offline signature verification. The multi-scale representation oriented local binary patterns can be obtained by changing the radius R value of
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a69338e7dda485f5ab7121bf7c365129
https://doi.org/10.1007/978-981-13-9187-3_13
https://doi.org/10.1007/978-981-13-9187-3_13
Publikováno v:
Data Analytics and Learning ISBN: 9789811325137
This paper presents a novel feature extraction technique which is based on partial sum of second-order Taylor Series Expansion (TSE) for offline signature verification. Partial sum of TSE is calculated with finite number of terms within a small neigh
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fa52978b75e18840f54759f978045c7a
https://doi.org/10.1007/978-981-13-2514-4_30
https://doi.org/10.1007/978-981-13-2514-4_30
Autor:
Bharathi Pilar, B. H. Shekar
Publikováno v:
Communications in Computer and Information Science ISBN: 9789811090585
In this work, we present eigenvalue based shape descriptor (EHough) which makes use of small eigenvalue and large eigenvalue along with Hough Transform to obtain the dominant features. The small eigenvalue and large eigenvalue are computed for each p
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::633a4d51e92c502c6b8650240c988b74
https://doi.org/10.1007/978-981-10-9059-2_27
https://doi.org/10.1007/978-981-10-9059-2_27
Autor:
B. H. Shekar, Bharathi Pilar
Publikováno v:
Procedia Computer Science. 58:714-722
In this paper, we propose a combined classifier model based on two dimensional discrete cosine transform (2D-DCT) and Height Functions (HF) for accurate shape representation and classification. The DCT is capable of capturing the region information a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::27d8a596b93125bc699f0e5a1d426bb7
https://doi.org/10.1016/j.procs.2015.08.092
https://doi.org/10.1016/j.procs.2015.08.092
Autor:
Bharathi Pilar, B. H. Shekar
Publikováno v:
Proceedings of the Third International Symposium on Computer Vision and the Internet.
In this work, we present eigenvalue based shape descriptor which makes use of small eigenvalue and large eigenvalue along with two dimensional Discrete Cosine Transformation (2D-DCT) for the purpose of feature extraction. The DCT based features are c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::32d9f075e51f6c34edd1b5c4fb9bb760
https://doi.org/10.1145/2983402.2983414
https://doi.org/10.1145/2983402.2983414
Autor:
Bharathi Pilar, B. H. Shekar
Publikováno v:
ICACCI
In this paper, we propose Radon Transform based shape descriptor. The Radon transform is region based and hence is robust to noise and it needs no normalization. These features are matched using Euclidean Distance. We have also proposed an integrated
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e99f631edc6abcf43408258eed6ac089
https://doi.org/10.1109/icacci.2016.7732341
https://doi.org/10.1109/icacci.2016.7732341
Autor:
Bharathi Pilar, B. H. Shekar
Publikováno v:
WCI
In this paper, we propose a combined classifier model based on two dimensional discrete cosine transform (2D-DCT) and Inner Distance Shape Context (IDSC) to classify shapes accurately. DCT is capable of capturing the region information and the inner-
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ad707a532f328b72a56a9e586631c4c9
https://doi.org/10.1145/2791405.2791488
https://doi.org/10.1145/2791405.2791488