臺灣博碩士論文加值系統

近年來由於深度學習其優秀的計算性能在影像視覺成為主要研究議題。我們經由一次產學合作做為契機接觸到前景切割，然而在我們原先開發的傳統演算法上有太多使用限制，因此轉而投入深度學習演算法開發。在使用現有的顯著性物件偵測演算法，切割我們自行提出具有不一樣挑戰的顯著性物件偵測資料集時，由於影像風格過於單一，同時影像數量並不充裕的情形下，導致網路在訓練時難以捕捉到良好的特徵圖，因此我們使用生成對抗網路在已有的標注資料情形下，藉此擴充更多不同風格的仿真影像；與此同時我們探討在不同狀況的訓練資料集，藉由生成對抗網路所生成的擴充影像是否對顯著物件偵測會有所影響，經由實驗後可以得到顯著性提升整體偵測。此外我們為了更進一步提升偵測效能，我們提出一個新的網路架構，結合現今兩個架構的特點，分別是使用U^2-Net中RSU架構最為特徵提取部分可降低低階特徵影像雜訊影像，與SCRN中CRU架構將特徵圖融合時是如何減少低階特徵圖雜訊判讀結果，並在常見的顯著物件偵測測試資料集上與其他近年來具有代表性的顯著物件偵測網路架構做值化分析與量化分析，在評測上得到不錯的結果。

In recent years, due to the excellent computing performance of deep learning, image vision has become a major research topic. We used an industry-university cooperation as an opportunity to get in touch with the prospect cutting. However, there are too many limitations on the traditional algorithms which was we originally developed, so we turned to deep learning algorithm development. When using the existing salient object detection algorithm to cut the salient object detection dataset that we proposed by ourselves with different challenges, it’s difficult for network to grab the good feature maps during training, the image style is too single and the number of images is insufficient. We use generative adversarial networks to expand more simulation images of different styles in the case of existing labeled data; at the same time, we discuss training data sets in different situations, Whether the extended image generated by generating the confrontation network will affect the detection of significant objects can be significantly improved after experiments. In addition, to improve the detection performance, we propose a new network architecture that combines the characteristics of each organization. The feature extraction part of the RSU architecture in U^2-Net could reduce the noise image of the low-level network feature image. The CRU architecture in SCRN combines the features How to connect low-level feature map’s noise reading results during map fusion, and observe significant objects on the data set and infer other significant objects on the dataset. The qualitative analysis and quantitative analysis of the target network structure, and obtained good results in the evaluation.

目錄
摘要 i
英文摘要 ii
誌謝 iii
目錄 iv
表目錄 vi
圖目錄 vii
第一章 簡介 1
1.1 研究背景 3
1.2 研究目的 3
1.3 方法概要 4
1.4 論文概要 4
第二章 文獻探討 6
2.1 影像分割 6
2.2 顯著性物件偵測 8
2.3 數據增強 11
2.3.1幾何轉換 11
2.3.2 生成對抗網路 11
第三章 深層堆疊交叉優化單元網路與影像擴充 13
3.1主架構Stacked Cross Refinement Network(SCRN) 13
3.1.1 SCRN網路架構 13
3.1.2 Loss Function 16
3.1.3 改良架構 16
3.2 CycleGAN影像擴充應用於顯著性物件偵測 19
3.2.1 網路架構 20
3.2.2 CycleGAN Loss Function 21
3.2.3 擴充影像驗證 22
第四章 顯著性物件偵測於消費性電子之應用-美甲影像切割 24
4.1 指甲影像資料集 25
4.2 以發表之傳統演算法 26
第五章 實驗 32
5.1實驗環境 32
5.2影像擴充實驗 34
5.2.1 ICNI用於CycleGAN訓練擴充影像 35
5.2.2 ONIE用於CycleGAN訓練擴充影像 37
5.2.3 幾何轉換影像擴充 41
5.3架構改良實驗 42
5.4 SOD實驗比較 45
5.4.1常見SOD Dataset 45
5.4.2 實驗比較 46
5.4.3 特例比較 52
第六章 結論 54
參考文獻 55


表目錄 頁次
表 1 傳統演算法各項評分平均數據 31
表 2 ICNI各項CASE正確率比較 36
表 3 ONIE指甲顏色紋路訓練影像分類 37
表 4 ONIE皮膚膚色訓練影像分類 38
表 5 ONIE指甲顏色紋路訓練影像訓練結果 39
表 6 ANCR膚色顏色紋路訓練影像訓練結果 40
表 7 加入幾何轉換影像擴充方法後各項數據評分 41
表 8 ONI資料集在DSCRUN-L不同層數下數據結果 43
表 9 傳統演算法與深度學習在ONI資料集平均數據比較 44
表 10 架構比較 47

圖目錄 頁次
圖 1 SOD圖片範例，左圖為原圖，右圖為偵測結果 2
圖 2 近年於三大電腦視覺會議和其他會議的SOD研究論文數量 2
圖 3 DSCRUN-L簡易流程圖 4
圖 4 SOD簡介歷史，已代表性的演算法為主 8
圖 5 SOD主要網路架構圖 9
圖 6 PIX2PIX與CYCLEGAN的對比 12
圖 7 SCRN網路架構 14
圖 8 現有卷機塊與RSU架構圖 17
圖 9 RESNET區塊與RSU差異圖 18
圖 10 DSCRUN-DEEP架構圖 18
圖 11 CYCLEGAN實驗圖 19
圖 12 CYCLEGAN網路示意圖 21
圖 13 驗證CYCLEGAN擴充影像流程圖 23
圖 14 指甲彩繪過程 24
圖 15 上排為原圖，下排為其他傳統演算法其偵測結果遮罩圖 26
圖 16 系統流程圖 27
圖 17 基座影像與RECT範圍。 28
圖 18 (A) FIRST GRABCUT處理結果，(B)PR_BGD輸出結果；(C)PR_FGD輸出結果。 29
圖 19 MORPHOLOGY圖片 30
圖 20 CONTOUR圖解(第一階段OUTPUT) 30
圖 21 USER INTERFACE圖解 31
圖 22 網路搜集影像示意圖 32
圖 23 CYCLEGAN影像擴充實驗流程圖 34
圖 24 藉由ICNI資料集生成出的FAKE影像 35
圖 25 加入ICNI 資料集生成影像經由SCRN訓練 36
圖 26 INCI數據分析圖 37
圖 27 有無去背的CYCLEGAN預訓練示意圖 38
圖 28 ONIE生成影像NWG與NGB以及NGA經由CYCLEGAN訓練後所得到的生成影像 39
圖 29 ONIE指甲數據分析圖 39
圖 30 ONIE皮膚數據分析圖 40
圖 31 自行拍攝(上排)與廠商提拱影像(下排) 切割結果 41
圖 32 加入幾何轉換數據分析圖 42
圖 33 RSU-L示意圖 43
圖 34 DSCRUN-L在ONI分析圖 44
圖 35 ANCR(綠圈)與DSCRUN-DEEP(++)(紅圈)兩者切割結果比較 45
圖 36 驗證集示意圖 46
圖 37 STATE-OF-THE-ART分析圖 48
圖 38 不同DSCRUN-L架構下的切割結果 49
圖 39 與其他架構比較圖 52
圖 40 特例影像範例 52
圖 41 訓練資料集佐證影像 53

[1] J. Canny, "A computational approach to edge detection," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PAMI-8, no. 6, pp. 679-698, Nov. 1986
[2] L. Vincent and P. Soille, "Watersheds in digital spaces: An efficient algorithm based on immersion simulations," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 13, no. 6, pp. 583-598, June 1991
[3] S. Beucher and F. Meyer, "The morphological approach to segmentation: The watershed transformation,” in Proc.Mathematical Morphology Image Processing, pp. 433-481, 1993.
[4] M. Couprie and G. Bertrand. "Topological grayscale watershed transform," in Proc. of SPIE Vision Geometry, pp. 136-146, 1997.
[5] J. B. MacQueen, "Some methods for classification and analysis of multivariate observations," in Proc. Fifth Berkeley Symposium on Math. Stat and Prob., vol. 1, pp. 281-296, 1967.
[6] P. Felzenszwalb and D. Huttenlocher, "Efficient graph-basedimage segmentation," in International Journal of Computer Vision (IJCV), vol. 59, no. 2, pp. 167-181, Sep. 2004.
[7] J. Shi and J. Malik, "Normalized cuts and image segmentation," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 22, no. 8, pp. 888-905, Aug. 2000
[8] A. Levinshtein, A. Stere, K. N. Kutulakos, D. J. Fleet, S. J. Dickinson, and K. Siddiqi, "TurboPixels: Fast superpixels using geometric flows," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 31, no. 12, pp. 2290-2297, Dec. 2009.
[9] A. Vedaldi and S. Soatto, "Quick shift and kernel methods for mode seeking," in Proc. European Conference on Computer Vision (ECCV), 2008.
[10] O. Veksler, Y. Boykov, and P. Mehrani, "Superpixels and supervoxels in an energy optimization framework," in Proc. European Conference on Computer Vision (ECCV), 2010.
[11] R. Achanta, A. Shaji, K. Smith, A. Lucchi, P. Fua, and S. Süsstrunk, "SLIC superpixels compared to state-of-the-art superpixel methods," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 34, no. 11, pp. 2274-2282, Nov. 2012
[12] Y. Boykov, O. Veksler, and R. Zabih, "Fast approximate energy minimization via graph cuts," in Proc. Seventh IEEE International Conference on Computer Vision, 1999.
[13] C. Rother, V. Kolmogorov, and A. Blake, "GrabCut: Interactive foreground extraction using iterated graph cuts,” in Proc. ACM SIGGRAPH, pp. 309-314, 2004.
[14] Y. Lecun, L. Bottou, Y. Bengio, and P. Haffner, "Gradient-based learning applied to document recognition," Proceedings of the IEEE, vol. 86, no. 11, pp. 2278-2324, Nov. 1998
[15] C. Cortes and V. Vapnik, "Support vector networks,” Machine Learning, vol. 20, pp. 1-25, 1995.
[16] A. Krizhevsky, I. Sutskever, and G. E. Hinton, "ImageNet classification with deep convolutional neural networks," in Proc. Neural Information Processing Systems(NIPS), pp. 1106-1114, 2012.
[17] H. Noh, S. Hong, and B. Han, "Learning deconvolution network for semantic segmentation," in Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp. 1520-1528, 2015.
[18] V. Badrinarayanan, A. Kendall, and R. Cipolla, "SegNet: A deep convolutional encoder-decoder architecture for image segmentation,” arXiv:1511.00561, 2015.
[19] C.-Y. Lee, S. Xie, P. Gallagher, Z. Zhang, and Z. Tu. "Deeply supervised nets,” arXiv:1409.5185, 2014.
[20] J. Long, E. Shelhamer, and T. Darrell, "Fully convolutional networks for semantic segmentation,” in Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431-3440, 2015.
[21] W. Liu, A. Rabinovich, and A. C. Berg, "Parsenet: Looking wider to see better" , arXiv:1506.04579, 2015.
[22] L.-C. Chen, G. Papandreou, I. Kokkinos, K. Murphy, and A. L. Yuille, "DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 40, no. 4, pp. 834-848, 1 Apr. 2018.
[23] S. Xie and Z. Tu. "Holistically-nested edge detection,” in Proc. IEEE International Conference on Computer Vision(ICCV), pp. 1395-1403, 2015.
[24] P. Buyssens, A. Elmoataz, and O. Lezoray, "Multiscale convolutional neural networks for vision–based classification of cells,” in Proc. Asian Conference on Computer Vision(ACCV), pp. 342-352, 2013
[25] N. Neverova, C. Wolf, G. W. Taylor, and F. Nebout, "Multiscale deep learning for gesture detection and localization,” in Proc. European Conference on Computer Vision (ECCV), 2014.
[26] Y. Ganin and V. Lempitsky, "N4-fields: Neural network nearest neighbor fields for image transforms,” arXiv:1406.6558, 2014.
[27] B. Hariharan, P. Arbelaez, R. Girshick, and J. Malik. "Hypercolumns for object segmentation and fine-grained localization,” in Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp. 447-456, 2015.
[28] J. Long, E. Shelhamer, and T. Darrell, "Fully convolutional networks for semantic segmentation," in Proc. IEEE Conference on Computer Vision and Pattern Recognition , 2015.
[29] I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio, "Generative adversarial nets,” in Proc. Neural Information Processing Systems(NIPS), pp. 2672-2680, 2014.
[30] J.-Y. Zhu et al., "Toward multimodal image-to-image translation,” in Proc. Neural Information Processing Systems(NIPS), pp. 465-476, 2017.
[31] J. Zhu, T. Park, P. Isola, and A. A. Efros, "Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks," in Proc. IEEE International Conference on Computer Vision (ICCV), 2017.
[32] C. Ledig et al., "Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network," in Proc. IEEE Conference on Computer Vision and Pattern Recognition , 2017.
[33] S. Kolkur, D. Kalbande, P. Shimpi, C. Bapat, and J. Jatakia, "Human skin detection using RGB HSV and YCbCr color models," arXiv:1708.02694, 2017 .
[34] V. Vezhnevets, V. Sazonov, and A. Andreeva, "A survey on pixel-based skin color detection techniques,” in Proc. GRAPHICON03, pp. 85-92, 2003.
[35] M. Poorani, T. Prathiba, and G. Ravindran, "Integrated feature extraction for image retrieval,” International Journal of Computer Science and Mobile Computing vol.2 no. 2, 28-35, Feb. 2013.
[36] M. J. Swain and D. H. Ballard, "Indexing via color histograms," in Proc. Proceedings Third International Conference on Computer Vision, 1990
[37] M. Swain and D. Ballard, "Color indexing,” International Journal of Computer Vision(IJCV), vol. 7, no. 1, pp. 11-32, 1991.
[38] S. Suzuki and K. Abe " Topological structural analysis of digital binary images by border following,” in Proc. Computer Vision, Graphics, and Image Processing , vol. 30, no. 1, pp. 32-46, 1985.
[39] C. Hung, Y. Wang, and P. Shih, "Design and implement a smart nail machine with image segmentation techniques," in Proc. IEEE 8th Global Conference on Consumer Electronics (GCCE), pp. 147-148, 2019.
[40] J. Zhu, J. Wu, Y. Xu, E. Chang, and Z. Tu, "Unsupervised object class discovery via saliency-guided multiple class learning," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 37, no. 4, pp. 862-875, Apr. 2015.
[41] F. Zhang, B. Du, and L. Zhang, "Saliency-guided unsupervised feature learning for scene classification," IEEE Transactions on Geoscience and Remote Sensing, vol. 53, no. 4, pp. 2175-2184, Apr. 2015.
[42] K. Xu et al., "Show, attend and tell: Neural image caption generation with visual attention,” in Proc. International Conference on Machine Learning (ICML), pp. 2048-2057, 2015.
[43] H. Fang et al., "From captions to visual concepts and back," in Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp. 1473-1482, 2015.
[44] A. Das, H. Agrawal, L. Zitnick, D. Parikh, and D. Batra, "Human attention in visual question answering: Do humans and deep networks look at the same regions,” Computer Vision and Image Understanding, vol. 163, pp. 90-100, 2017.
[45] Z. Ren, S. Gao, L. Chia, and I. W. Tsang, "Region-based saliency detection and Its application in object recognition," IEEE Transactions on Circuits and Systems for Video Technology, vol. 24, no. 5, pp. 769-779, May 2014.
[46] D. Zhang, D. Meng, L. Zhao, and J. Han, "Bridging saliency detection to weakly supervised object detection based on self-paced curriculum learning,” in Proc. International Joint Conferences on Artificial Intelligence, 2016.
[47] W. Wang, J. Shen, R. Yang, and F. Porikli, "Saliency-aware video object segmentation," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 40, no. 1, pp. 20-33, 1 Jan. 2018.
[48] H. Song, W. Wang, S. Zhao, J. Shen, and K.-M. Lam, "Pyramid dilated deeper convlstm for video salient object detection,” in Proc. European Conference on Computer Vision (ECCV), pp. 715-731, 201.
[49] Y. Wei, J. Feng, X. Liang, M. Cheng, Y. Zhao, and S. Yan, "Object region mining with adversarial erasing: A simple classification to semantic segmentation approach," in Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp. 6488-6496, 2017.
[50] Y. Wei et al., "STC: A simple to complex framework for weakly-supervised semantic segmentation," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 39, no. 11, pp. 2314-2320, 1 Nov. 2017.
[51] X. Wang, S. You, X. Li, and H. Ma, "Weakly-supervised semantic segmentation by iteratively mining common object features," in Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1354-1362, 2018.
[52] R. Zhao, W. Ouyang, and X. Wang, "Unsupervised salience learning for person re-identification," in Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp. 3586-3593, 2013.
[53] S. Bi, G. Li, and Y. Yu, "Person re-identification using multiple experts with random subspaces,” Journal of Image and Graphics, vol. 2, no. 2, 2014.
[54] Y.-F. Ma, L. Lu, H.-J. Zhang, and M. Li, "A user attention model for video summarization,” in Proc. ACM International Conference on Multimedia, pp. 533-542, 2002.
[55] D. Simakov, Y. Caspi, E. Shechtman, and M. Irani, "Summarizing visual data using bidirectional similarity," in Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp. 1-8, 2008.
[56] A. Borji, M.-M. Cheng, H. Jiang, and J. Li, "Salient object detection: A survey,” arXiv:1411.5878, 2014.
[57] A. Borji, M. Cheng, H. Jiang, and J. Li, "Salient object detection: A benchmark," IEEE Transactions on Image Processing, vol. 24, no. 12, pp. 5706-5722, Dec. 2015.
[58] Guanbin Li and Y. Yu, "Visual saliency based on multiscale deep features," in Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp. 5455-5463, 2015.
[59] R. Zhao, W. Ouyang, H. Li, and X. Wang, "Saliency detection by multi-context deep learning," in Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp. 1265-1274, 2015.
[60] W. Wang, Q. Lai, H. Fu, J. Shen, H. Ling, and R. Yang, "Salient object detection in the deep learning era: An in-depth survey,” arXiv: 1904.09146, 2021.
[61] N. Liu and J. Han, "DHSNet: Deep hierarchical saliency network for salient object detection," in Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp. 678-686, 2016.
[62] J. Zhang, S. Sclaroff, Z. Lin, X. Shen, B. Price, and R. Mech, "Unconstrained salient object detection via proposal subset optimization," in Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp. 5733-5742, 2016.
[63] Q. Hou, M. Cheng, X. Hu, A. Borji, Z. Tu, and P. H. S. Torr, "Deeply supervised salient object detection with short connections," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 41, no. 4, pp. 815-828, Apr. 2019.
[64] Z. Luo, A. Mishra, A. Achkar, J. Eichel, S. Li, and P. Jodoin, "Non-local deep features for salient object detection," in Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp. 6593-6601, 2017.
[65] X. Chen, A. Zheng, J. Li, and F. Lu, "Look, perceive and segment: Finding the salient objects in images via two-stream fixation-semantic CNNs," in Proc. IEEE International Conference on Computer Vision (ICCV), pp. 1050-1058, 2017.
[66] N. Liu, J. Han and M. Yang, "PiCANet: Learning pixel-wise contextual attention for saliency detection," in Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3089-3098, 2018.
[67] T. Wang et al., "Detect globally, refine locally: A novel approach to saliency detection," in Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3127-3135, 2018.
[68] X. Zhang, T. Wang, J. Qi, H. Lu, and G. Wang, "Progressive Attention Guided Recurrent Network for Salient Object Detection," in Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 714-722, 2018.
[69] J. Liu, Q. Hou, M. Cheng, J. Feng, and J. Jiang, "A simple pooling-based design for real-time salient object detection," in Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3912-3921, 2019.
[70] Z. Wu, L. Su and Q. Huang, "Stacked cross refinement network for edge-aware salient object detection," in Proc. IEEE/CVF International Conference on Computer Vision (ICCV), pp. 7263-7272, 2019.
[71] J. Zhao, J. Liu, D. Fan, Y. Cao, J. Yang, and M. Cheng, "EGNet: Edge guidance network for salient object detection," in Proc. IEEE/CVF International Conference on Computer Vision (ICCV), pp. 8778-8787, 2019.
[72] J. Su, J. Li, Y. Zhang, C. Xia, and Y. Tian, " Selectivity or invariance: Boundary-aware salient object detection,” in Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019.
[73] Y. Liu, Q. Zhang, D. Zhang, and J. Han, "Employing deep part-object relationships for salient object detection," in Proc. IEEE/CVF International Conference on Computer Vision (ICCV), pp. 1232-1241, 2019.
[74] M. Cheng, G. Zhang, N. J. Mitra, X. Huang, and S. Hu, "Global contrast based salient region detection," in Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp. 409-416, 2011.
[75] F. Perazzi, P. Krähenbühl, Y. Pritch, and A. Hornung, "Saliency filters: Contrast based filtering for salient region detection," in Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp. 733-740, 2012.
[76] H. Jiang, J. Wang, Z. Yuan, Y. Wu, N. Zheng, and S. Li, "Salient object detection: A discriminative regional feature integration approach," in Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp. 2083-2090, 2013.
[77] Q. Yan, L. Xu, J. Shi, and J. Jia, "Hierarchical saliency detection," in Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp. 1155-1162, 2013.
[78] W. Zhu, S. Liang, Y. Wei, and J. Sun, "Saliency optimization from robust background detection," in Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp. 2814-2821, 2014.
[79] J. Wei, S. Wang , Z. Wu, C. Su , Q. Huang, and Q. Tian, "Label decoupling framework for salient object detection,” in Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 13022-13031, 2020.
[80] O. Ronneberger, P. Fischer, and T. Brox, "Unet: Convolutional networks for biomedical image segmentation,” in Proc. International Conference on Medical Image Computing and Computer-assisted Intervention, pp 234-241, 2015.
[81] L. Itti, C. Koch, and E. Niebur, "A model of saliency-based visual attention for rapid scene analysis," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 20, no. 11, pp. 1254-1259, Nov. 1998.
[82] T. Liu, J. Sun, N. Zheng, X. Tang, and H. Shum, "Learning to detect a salient object," in Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp. 1-8, 2007.
[83] Z. Yu, C. Feng, M. Liu, and S. Ramalingam, "CASENet: Deep category-aware semantic edge detection," in Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp. 1761-1770, 2017.
[84] Q, Xuebin, Z. Zhang, C Huang, M Dehghan, O. R. Zaïane, and M Jägersand. “U2-Net: Going deeper with nested u-structure for salient object detection,” Pattern Recognition, vol.106, no. 11, pp. 107404, 2020.
[85] D. Martin, C. Fowlkes, D. Tal, and J. Malik, "A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics,” in Proc. Eighth IEEE International Conference on Computer Vision., vol. 2, pp. 416-423, 2001.
[86] R. Achanta, S. Hemami, F. Estrada, and S. Susstrunk, "Frequency-tuned salient region detection," in Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp. 1597-1604, 2009.
[87] J. Liu, Q. Hou, M. Cheng, J. Feng, and J. Jiang, "A simple pooling-based design for real-time salient object detection," in Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3912-3921 2019.
[88] R. Margolin, L. Zelnik-Manor, and A. Tal, "How to evaluate foreground maps," in Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp. 248-255, 2014.
[89] V. Movahedi and J. H. Elder, "Design and perceptual validation of performance measures for salient object segmentation," in Proc. IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops, pp. 49-56, 2010.
[90] L. Wang et al., "Learning to detect salient objects with image-level supervision," in Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp. 3796-3805, 2017.
[91] Q. Yan, L. Xu, J. Shi, and J. Jia, "Hierarchical saliency detection," in Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp. 1155-1162 , 2013.
[92] C. Yang, L. Zhang, H. Lu, X. Ruan, and M. Yang, "Saliency detection via graph-Based Manifold Ranking," in Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp. 3166-3173, 2013.
[93] Y. Li, X. Hou, C. Koch, J. M. Rehg, and A. L. Yuille, "The secrets of salient object segmentation," IEEE Conference on Computer Vision and Pattern Recognition, pp. 280-287, 2014.
[94] G. Li and Y. Yu, "Visual saliency detection based on multiscale deep CNN features," IEEE Transactions on Image Processing, vol. 25, no. 11, pp. 5012-5024, Nov. 2016.
[95] C.-H. Hung, Y.-K. Wang, P.-Y. Shih, and H.-Y. Huang, "Design and implementation of an intelligent nail machine with computer vision techniques," in Proc. IEEE International Conference on Consumer Electronics (ICCE), pp. 1-2, 2020.
[96] K. He, G. Gkioxari, P. Dollár, and R. Girshick, "Mask R-CNN," in Proc. IEEE International Conference on Computer Vision (ICCV), pp. 2980-2988, 2017.
[97] T.-Y. Lin et al., "Microsoft coco: Common objects in context,” in Proc. European Conference on Computer Vision (ECCV), 2014.