👽 🚁 👨🏾‍🏫 HoughNet：搜索与经典算法融合的消失点 😙 🎪 ✊🏿

尽管在对象识别领域教授了数十甚至数百种经过验证的人工神经网络（ANN）架构，并通过功能强大的视频卡使地球变暖，并为计算机视觉的所有任务创造了“灵丹妙药”，但我们坚定地走在智能引擎的研究道路上，提供了有效的新型ANN架构解决特定问题。今天，我们将讨论HafNet-一种在图像上搜索消失点的新方法。

霍夫变换及其快速实施

. , , , , . ( ). () : , , , .. , , , , , .

(x_i,y_i). , y_i=x_ia+b a b. b=-x_ia+y_i ab, , (x_i,y_i) . : , , , . : , . ( – , ).

, , , – .

, . .

, , : – O(n³), n – .

() – , , () . O(n² log(n)), . , , , [5]. , : : « » ( H₁), « » ( H₂), « » ( H₃) « » ( H₄). , H₁₂ H₃₄ , .

( , ). , , . .

. , , - , : ( , , ), – . , . . , - . , H₁₂ , . , , H₃₄ , . , , H₁₂ , , , . ( , H₁₂ ).

( ). , ( – ).

, , : ? , … , !

HoughNet

, , - (, – , – ). «» ( , ). «» . «» , , ?

, ( HoughNet), , - . , , – , , . , ( [1]).


1	conv	12 filters 5x5, stride 1x1, no padding	relu
2	conv	12 filters 5x5, stride 2x2, no padding	relu
3	conv	12 filters 5x5, stride 1x1, no padding	relu
4	FHT	H12 for vertical, H34 for horizontal	-
5	conv	12 filters 3x9, stride 1x1, no padding	relu
6	conv	12 filters 3x5, stride 1x1, no padding	relu
7	conv	12 filters 3x9, stride 1x1, no padding	relu
8	conv	12 filters 3x5, stride 1x1, no padding	relu
9	FHT	H34 for both branchesg	-
10	conv	16 filters 5x5, stride 3x3, no padding	relu
11	conv	16 filters 5x5, stride 3x3, no padding	relu
12	conv	1 filter 5x5, stride 3x3, no padding	1 – rbf

: «» , «» . .

. MIDV-500 [6]. , . 50 . ( , 30 ) , – .

, , ICDAR 2011 dewarping contest dataset ( 100 - , ) .

«» ( ), state-of-the-art [7] [8].

		[7]	[8]	HoughNet
	31.3%	49.6%	50.1%	59.7%

[1] Sheshkus A. et al. HoughNet: neural network architecture for vanishing points detection // 2019 International Conference on Document Analysis and Recognition (ICDAR). – 2020. doi: 10.1109/ICDAR.2019.00140.
[2] . ., . ., . . // . – 2014. – . 64. – №. 3. – . 25-34.
[3] .. : . … . . .-. . – ., 2019. – 24 .
[4] [ ]: . . – : https://ru.wikipedia.org/wiki/_/ ( : 13.03.2020).
[5] Nikolaev D. P., Karpenko S. M., Nikolaev I. P., Nikolayev P. P. Hough Transform: Underestimated Tool in the Computer Vision Field // 22st European Conference on Modelling and Simulation, ECMS 2008. – Nicosia, Cyprys, 2008. – P. 238–243.
[6] Arlazarov V. V. et al. MIDV-500: a dataset for identity document analysis and recognition on mobile devices in video stream // . – 2019. – . 43. – №. 5.
[7] Y. Takezawa, M. Hasegawa, and S. Tabbone, “Cameracaptured document image perspective distortion correction using vanishing point detection based on radon transform,” in Pattern Recognition (ICPR), 2016 23rd International Conference on. IEEE, 2016, pp. 3968–3974.
[8] Y. Takezawa, M. Hasegawa, and S. Tabbone, “Robust perspective rectification of camera-captured document images,” in Document Analysis and Recognition (ICDAR), 2017 14th IAPR International Conference on, vol. 6. IEEE, 2017, pp. 27–32.

HoughNet：搜索与经典算法融合的消失点

霍夫变换及其快速实施

HoughNet

More articles: