 |
|
 |
Izvorni znanstveni članak
An improved saliency detection algorithm based on Itti’s model
Zhongshan Chen
; (1) School of Electronic Science & Engineering, Southeast University, NO. 2 Sipailou, 210096, Nanjing, China; (2) School of Information Engineering Yancheng Institute of Technology, NO. 211 Jianjun East Road, 224051, Yancheng, China
Yan Tu
; School of Electronic Science & Engineering, Southeast University, NO. 2 Sipailou, 210096, Nanjing, China
Lili Wang
; School of Electronic Science & Engineering, Southeast University, NO. 2 Sipailou, 210096, Nanjing, China
| Puni tekst: engleski, pdf (2 MB) | str. 1337-1344 | citiraj | |
|
APA 6th Edition Chen, Z., Tu, Y. i Wang, L. (2014). An improved saliency detection algorithm based on Itti’s model. Tehnički vjesnik, 21 (6), 1337-1344. Preuzeto s https://hrcak.srce.hr/131327 MLA 8th Edition Chen, Zhongshan, et al. "An improved saliency detection algorithm based on Itti’s model." Tehnički vjesnik, vol. 21, br. 6, 2014, str. 1337-1344. https://hrcak.srce.hr/131327. Citirano 08.03.2021. Chicago 17th Edition Chen, Zhongshan, Yan Tu i Lili Wang. "An improved saliency detection algorithm based on Itti’s model." Tehnički vjesnik 21, br. 6 (2014): 1337-1344. https://hrcak.srce.hr/131327 Harvard Chen, Z., Tu, Y., i Wang, L. (2014). 'An improved saliency detection algorithm based on Itti’s model', Tehnički vjesnik, 21(6), str. 1337-1344. Preuzeto s: https://hrcak.srce.hr/131327 (Datum pristupa: 08.03.2021.) Vancouver Chen Z, Tu Y, Wang L. An improved saliency detection algorithm based on Itti’s model. Tehnički vjesnik [Internet]. 2014 [pristupljeno 08.03.2021.];21(6):1337-1344. Dostupno na: https://hrcak.srce.hr/131327 IEEE Z. Chen, Y. Tu i L. Wang, "An improved saliency detection algorithm based on Itti’s model", Tehnički vjesnik, vol.21, br. 6, str. 1337-1344, 2014. [Online]. Dostupno na: https://hrcak.srce.hr/131327. [Citirano: 08.03.2021.] |
|||
| Puni tekst: hrvatski, pdf (2 MB) | str. 1337-1344 | citiraj | |
|
APA 6th Edition Chen, Z., Tu, Y. i Wang, L. (2014). Poboljšani algoritam otkrivanja istaknutih elemenata zasnovan na Itti modelu. Tehnički vjesnik, 21 (6), 1337-1344. Preuzeto s https://hrcak.srce.hr/131327 MLA 8th Edition Chen, Zhongshan, et al. "Poboljšani algoritam otkrivanja istaknutih elemenata zasnovan na Itti modelu." Tehnički vjesnik, vol. 21, br. 6, 2014, str. 1337-1344. https://hrcak.srce.hr/131327. Citirano 08.03.2021. Chicago 17th Edition Chen, Zhongshan, Yan Tu i Lili Wang. "Poboljšani algoritam otkrivanja istaknutih elemenata zasnovan na Itti modelu." Tehnički vjesnik 21, br. 6 (2014): 1337-1344. https://hrcak.srce.hr/131327 Harvard Chen, Z., Tu, Y., i Wang, L. (2014). 'Poboljšani algoritam otkrivanja istaknutih elemenata zasnovan na Itti modelu', Tehnički vjesnik, 21(6), str. 1337-1344. Preuzeto s: https://hrcak.srce.hr/131327 (Datum pristupa: 08.03.2021.) Vancouver Chen Z, Tu Y, Wang L. Poboljšani algoritam otkrivanja istaknutih elemenata zasnovan na Itti modelu. Tehnički vjesnik [Internet]. 2014 [pristupljeno 08.03.2021.];21(6):1337-1344. Dostupno na: https://hrcak.srce.hr/131327 IEEE Z. Chen, Y. Tu i L. Wang, "Poboljšani algoritam otkrivanja istaknutih elemenata zasnovan na Itti modelu", Tehnički vjesnik, vol.21, br. 6, str. 1337-1344, 2014. [Online]. Dostupno na: https://hrcak.srce.hr/131327. [Citirano: 08.03.2021.] |
|||
Sažetak
Visual attention mechanism (VAM) automatically ignores the superfluous information and pays attention to the most significant objects when people are watching the pictures. There are numerous bottom-up visual attention computational models to detect the salient area of an image. In this paper, an improved visual attention computational model based on Itti’s model is proposed, which is comprised of three components. Firstly, the lower-level primitive image features s are extracted from CIELa*b* color space instead of RGB color space; secondly, the feature images are decomposed into wavelet pyramids by wavelet-based multi-scale transform. Thirdly, a new strategy is used to combine all conspicuity maps into a final saliency map with different weights, which are proportional to the contribution of each conspicuity map. Compared with Itti’s models, subjective experiments prove that the approach proposed in this paper is more effective.
Ključne riječi
bottom-up model; image feature; saliency map; visual attention mechanism (VAM)
Hrčak ID: 131327
URI
https://hrcak.srce.hr/131327
Moj profil
Srce