|
|
|
| Research on Complex Image Contour Detection Model Based on Avian Visual Features |
| Wu Wei, Lou Kaiwen, Fan Yingle*, Fang Tao* |
| (Laboratory of Pattern Recognition and Image Processing, Hangzhou Dianzi University, Hangzhou 310018,China) |
|
|
|
|
Abstract This work aimed to address the limitations of traditional contour detection methods in extracting contour information from complex image objects on the basis of superior mechanisms of bird visual system in the image information processing. Firstly, by utilizing the preferred orientation mechanism of birds, the optimal direction selection for the receptive field was determined to enhance contour responses and reduce noise interference. Secondly, a color pre-segmentation model is constructed based on the specific wavelength filtering mechanism of bird oil droplets, which enhanced the color difference between the target and the background. Additionally, a color difference calculation model based on the spectral response characteristics of bird photoreceptors was proposed to avoid fragmentation of color channels in the image. Finally, inspired by the excitatory input mechanism of the avian optic tectum (TeO) for targets and the inhibitory projection mechanism of avian thalamic nuclei for backgrounds, the fine extraction of complex image contour and the suppression of image texture were achieved. Comparative experiments were conducted on 1449 images from the NYUD dataset and 500 images from the BSDS500 dataset, with ODS, OIS, and AP values of 0.68, 0.69, and 0.68, respectively, demonstrating superior performance compared to mainstream comparison methods. In conclusion, this study applied the excellent visual information processing mechanisms of birds to contour detection tasks, improving existing computational models and providing new ideas and methods for visual tasks. These findings are of significance in promoting the development of bioinspired visual models.
|
|
Received: 26 January 2024
|
|
|
|
|
|
[1] Grigorescu C, Petkov N, Westenberg MA. Contour detection based on nonclassical receptive field inhibition [J]. IEEE Transactions on Image Processing, 2003, 12(7): 729-739.
[2] Fang Tao, Fan Yingle, Wu Wei. Salient contour detection on the basis of the mechanism of bilateral asymmetric receptive fields [J]. Signal, Image and Video Processing, 2020, 14: 1461-1469.
[3] Yang Kaifu, Gao Shaobin, Guo Cefeng, et al. Boundary detection using double-opponency and spatial sparseness constraint [J]. IEEE Transactions on Image Processing, 2015, 24(8): 2565-2578.
[4] Li Fuzhang, Lin Chuan, Zhang Qing, et al. A biologically inspired contour detection model based on multiple visual channels and multi-hierarchical visual information [J]. IEEE Access, 2020, 8: 15410-15422.
[5] Zhong Haixin, Wang Rubin. A visual-degradation-inspired model with HSV color-encoding for contour detection [J]. Journal of Neuroscience Methods, 2022, 369: 109423.
[6] Herrnstein RJ, Loveland DH. Complex visual concept in the pigeon [J]. Science, 1964, 146(3643): 549-551.
[7] Zhang Beiwei, Cao Jiangtao, Liu Honghai. Avian eye-inspired visual attention approach to UAV target detection [J]. Optik, 2017, 130: 1205-1213.
[8] Wang Xiaohua, Duan Haibin. Hierarchical visual attention model for saliency detection inspired by avian visual pathways [J]. IEEE/CAA Journal of Automatica Sinica, 2019, 6(2): 540-552.
[9] Hu Pingge, Wang Xingtong, Zhang Xiaoteng, et al. OTNet: a small object detection algorithm for video inspired by avian visual system [J]. Mathematics, 2022, 10(21): 4125.
[10] Maturana HR, Varela FJ. Color-opponent responses in the avian lateral geniculate: a study in the quail (Coturnix coturnix japonica) [J]. Brain Research, 1982, 247(2): 227-241.
[11] Wang Jiangtao, Qian Longlong, Wang Songwei, et al. Directional preference in avian midbrain saliency computing nucleus reflects a well-designed receptive field structure [J]. Animals (Basel), 2022, 12(9): 1143.
[12] Toomey MB, Corbo JC. Evolution, development and function of vertebrate cone oil droplets [J]. Frontiers in Neural Circuits, 2017, 11: 97.
[13] Wilby D, Toomey MB, Olsson P, et al. Optics of cone photoreceptors in the chicken (Gallus gallus domesticus) [J]. Journal of the Royal Society Interface, 2015, 12(111): 20150591.
[14] Wilby D, Roberts NW. Optical influence of oil droplets on cone photoreceptor sensitivity [J]. Journal of Experimental Biology, 2017, 220(Pt 11): 1997-2004.
[15] Kelber A. Bird colour vision - from cones to perception [J]. Current Opinion in Behavioral Sciences, 2019, 30: 34-40.
[16] Stavenga DG, Wilts BD. Oil droplets of bird eyes: microlenses acting as spectral filters [J]. Philosophical Transactions of the Royal Society B: Biological Sciences, 2014, 369(1636): 20130041.
[17] Young SR, Martin GR. Optics of retinal oil droplets: a model of light collection and polarization detection in the avian retina [J]. Vision Research, 1984, 24(2): 129-137.
[18] Kemp DJ, Herberstein ME, Fleishman LJ, et al. An integrative framework for the appraisal of coloration in nature [J]. American Naturalist, 2015, 185(6): 705-724.
[19] Cuthill IC, Allen WL, Arbuckle K, et al. The biology of color [J]. Science, 2017, 357(6350): eaan0221.
[20] Chittka L. The colour hexagon: a chromaticity diagram based on photoreceptor excitations as a generalized representation of colour opponency [J]. Journal of Comparative Physiology A, 1992, 170(5): 533-543.
[21] Kelber A, Vorobyev M, Osorio D. Animal colour vision--behavioural tests and physiological concepts [J]. Biological Reviews of the Cambridge Philosophical Society, 2003, 78(1): 81-118.
[22] Vorobyev M, Osorio D. Receptor noise as a determinant of colour thresholds [J]. Proceedings of the Royal Society B: Biological Sciences, 1998, 265(1394): 351-358.
[23] Pike TW. Generalised chromaticity diagrams for animals with n-chromatic colour vision [J]. Journal of Insect Behavior, 2012, 25(3): 277-286.
[24] Pike TW. Preserving perceptual distances in chromaticity diagrams [J]. Behavioral Ecology, 2012, 23(4): 723-728.
[25] Clark R, Santer R, Brebner JS. A generalized equation for the calculation of receptor noise limited colour distances in n-chromatic visual systems [J]. Royal Society Open Science, 2017, 4(9): 170712.
[26] Olsson P, Wilby D, Kelber A. Spatial summation improves bird color vision in low light intensities [J]. Vision Research, 2017, 130: 1-8.
[27] Lazareva O. Bilateral lesions of nucleus subpretectalis/interstitio-pretecto-subpretectalis (SP/IPS) selectively impair figure-ground discrimination in pigeons[J]. Visual Neuroscience. 2014, 31(1): 105-110.
[28] Xu Yanan, Fan Yingle. Contour detection based on the interactive response and fusion model of bilateral attention pathways[J]. Signal, Image and Video Processing, 2022, 16: 1-9.
[29] 陈树楠, 范影乐, 房涛, 等. 基于主视通路结构分级响应模型的轮廓检测方法[J]. 自动化学报, 2022, 48(3):820-833.
[30] 张明琦, 范影乐, 武薇. 基于初级视通路视觉感知机制的轮廓检测方法[J]. 自动化学报, 2020, 46(2):264-273. |
| [1] |
Hu Junhao, Fan Yingle, Li Kangqun, Wu Wei. A Contour Detection Method Based on Color Opponent and Dynamic Coding of Neurons[J]. Chinese Journal of Biomedical Engineering, 2017, 36(5): 520-528. |
| [2] |
Li Kangqun, Fan Yingle, Gan Haitao, Wu Wei. A Contour Detection Method Based on Correlation of Orientation for Multiple Receptive Fields in Visual Pathway[J]. Chinese Journal of Biomedical Engineering, 2017, 36(1): 1-11. |
|
|
|
|
