リケラボ論文検索は、全国の大学リポジトリにある学位論文・教授論文を一括検索できる論文検索サービスです。

リケラボ 全国の大学リポジトリにある学位論文・教授論文を一括検索するならリケラボ論文検索大学・研究所にある論文を検索できる

リケラボ 全国の大学リポジトリにある学位論文・教授論文を一括検索するならリケラボ論文検索大学・研究所にある論文を検索できる

大学・研究所にある論文を検索できる 「Research on application of a Faster R-CNN based on upper and lower layers in face detection」の論文概要。リケラボ論文検索は、全国の大学リポジトリにある学位論文・教授論文を一括検索できる論文検索サービスです。
リケラボ

コピーが完了しました

URLをコピーしました

論文の公開元へ論文の公開元へ
書き出し

Research on application of a Faster R-CNN based on upper and lower layers in face detection

姜 琳 富山大学

2022.09.28

概要

At present, face detection technology has been widely used in many fields such as security, campus and finance. As society progresses and technology further matures, face detection technology will inevitably be applied to more fields . However, the human face is a very common yet complex pattern that contains a large amount of information . It is a challenge to distinguish faces from other objects in complex background images, and face detection becomes more difficult due to variations in the proportions, pose, facial expressions, lighting, image quality, age, occlusion and other factors of faces. Therefore, in order to accomplish robustness of the detection method, the designed detection algorithm must consider the possible interference caused by various complex backgrounds of faces .

　Faster R-CNN is a fast region convolutional network based method. It can effectively improve detection efficiency and accuracy by using deep convolutional networks to efficiently extract and classify the object to be detected. Compared to traditional face detection techniques, Faster R-CNN uses Region of Interest Pooling (ROI Pooling) techniques to allow the network to share computational results, thus speeding up the model . Traditional CNN structures can maintain a degree of translation and rotation invariance to specific locations in the input image. This spatial invariance exists only for local regions of the input image, and overall spatial rotational invariance for superimposed local regions cannot be achieved for the entire image. This is because the pooling layer in the CNN structure has many limitations, such as the fact that much useful information is lost when extracting features and the input data is only a local operation . The feature maps in the middle of the CNN framework produce large distortions, making it difficult for CNNs to implement spatial transformations such as image rotation and scaling. the feature maps produced during feature extraction in CNNs are not an overall transformation of the input data, which is more restrictive. Also, when the training face dataset has a large amount of data, it generates a large number of candidate regions that occupy disk space. And when the candidate regions are transferred to the CNN, they are normalised in advance, causing a loss of information . Each candidate region is placed in the network, resulting in the same feature being extracted repeatedly and wasting resources .

　The network in this paper is an improvement of the traditional Faster R-CNN, proposing a multi-scale fast RCN method based on the upper and lower layers that can robustly detect small targets at different scales, poses and environments . Experimental results show that the multiscale fast RCNN based on both upper and lower layers has better detection performance than fast RCNN while maintaining the same testing cost. Compared with the current state-of-the-art face detection methods, the improved method in this paper can accurately detect faces with different poses in various environments.

　The contributions and originality of this paper are summarised as follows.
　(1) A new spatial radiometric transform is proposed for the first time to improve the detection capability of the original Faster-RCNN. The spatial affine transform identifies face parts by detecting meaningful regions in the image, thus improving the detection of small face parts by the original network. The experimental results also verify that the face detection effectiveness of UPL-RCNN is improved compared with other networks.
　(2) A method combining the upper and lower layers is proposed. The upper layer adopts the bionic transformation strategy and the lower layer adopts the feature region strategy. It enables the original network to robustly detect small targets at different scales, in different poses and under different environments.
　(3) The bionic spatial transform uses feature fusion to enhance the continuity of the action, which can better improve face recognition.

論文の公開元へ

この論文で使われている画像

関連論文

関連論文をもっと見る

参考文献

[1] Szeliski R. Computer Vision: Algorithms and Applications[M]. New York: Springer, 2010.

[2] M. Cristani, V. Murino, A. Vinciarelli. Socially intelligent surveillance and monitoring: Analysing social dimensions of physical space[C]//San Francisco: IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2010:51-58.

[3] A. C. Alexandros. A Vision System for Intelligent Monitoring of Activities of Daily Living at Home[J]. Lecture Notes in Computer Science, 2013(8277):96-99.

[4] T. R. Bretschneider, K. Odej. Content-Based Image Retrieval[J]. Encyclopedia of Data Ware-housing Mining, 2010, 43(4):96-102.

[5] M. G. R. S., J. R. S. Computer Vision Based Human Computer Interaction[J]. Journal of Artificial Intelligence, 2011, 4(4):245-256.

[6] Z. Zhengyou. Microsoft Kinect Sensor and Its Effect[J]. IEEE Transactions on Multimedia, 2012,19(2):4-10.

[7] J. Levinson, J. Askeland, J. Dolson, et al. Traffic light mapping, localization, and state detection for autonomous vehicles[C]//Shanghai: IEEE International Conference on Robotics and Automa-tion, 2011:5784-5791.

[8] J. Kichun, S. Myoungho. Generation of a Precise Roadway Map for Autonomous Cars[J]. IEEE Transactions on Intelligent Transportation Systems, 2014, 15(3):925-937.

[9] Y. Alper, J. Omar, S. Mubarak. Object tracking: A survey[J]. Acm Computing Surveys, 2006, 38(1):81-93.

[10] Huang T S. Image Sequence Processing and Dynamic Scene Analysis[M]. Berlin: Springer, 2012.

[11] The PASCAL Visual Object Classes Challenge 2007. Available online at http://host.robots.ox.ac.uk:8080/pascal/VOC/voc2007/index.html.

[12] E. Mark, G. L. Van, C. K. I. Williams, et al. StreetScenes: Towards Scene Understanding in Still Images[D]. Cambridge,Massachusetts,USA: Massachusetts Institute of Technology,Department of Electrical Engineering and Computer Science, 2006.

[13] D. Navneet, T. Bill. Histograms of oriented gradients for human detection[C]//San Diego: IEEE Conference on Computer Vision and Pattern Recognition, 2005:8863-893.

[14] L. Fei-Fei, P. Perona. A Bayesian hierarchical model for learning natural scene cate-gories[C]//San Diego: IEEE Conference on Computer Vision and Pattern Recognition, 2005:524-531.

[15] P. Srinivasan, Q. Zhu, J. Shi. Many-to-one contour matching for describing and discriminating object shape[C]//San Francisco: IEEE Conference on Computer Vision and Pattern Recognition, 2010:1673-1680.

[16] O. Timo, M. Pietikainen, T. Maenpaa. Multiresolution Gray-Scale and Rotation Invariant Tex-ture Classification with Local Binary Patterns[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(7):971-987.

[17] T. Ahonen, S. Member, A. Hadid, et al. Face description with local binary patterns: Application to face recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28(12):2037-2041.

[18] Z. Guoying, P. Matti. Dynamic texture recognition using local binary patterns with an application to facial expressions.[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(6):915-928.

[19] X. Wang, T. X. Han, S. Yan. An HOG-LBP human detector with partial occlusion han-dling[C]//Kyoto: IEEE International Conference on Computer Vision, 2009:32-39.

[20] S. Hinterstoisser, V. Lepetit, S. Ilic, et al. Dominant orientation templates for real-time detec-tion of texture-less objects[C]//San Francisco: IEEE Conference on Computer Vision and Pattern Recognition, 2010:2257-2264.

[21] E. Shechtman, M. Irani. Matching Local Self-Similarities across Images and Videos[C]//Minneapolis: IEEE Conference on Computer Vision and Pattern Recognition, 2007:1-8.

[22] D. T. Nguyen. A Novel Chamfer Template Matching Method Using Variational Mean Field[C]//Columbus: IEEE Conference on Computer Vision and Pattern Recognition, 2014:2425-2432.

[23] D. T. Nguyen, M.-K. Tran, S.-K. Yeung. An MRF-Poselets Model for Detecting Highly Artic-ulated Humans[C]//Santiago: IEEE International Conference on Computer Vision, 2015:1967-1975.

[24] S. Korman, D. Reichman, G. Tsur. FasT-Match: Fast Affine Template Matching[C]//Portland: IEEE Conference on Computer Vision and Pattern Recognition, 2013:2331-2338.

[25] T. F. Cootes, C. J. Taylor, D. H. Cooper, et al. Active Shape Models-Their Training and Appli-cation[J]. Computer Vision Image Understanding, 1995, 61(1):38-59.

[26] M. Iain, B. Simon. Active Appearance Models Revisited[J]. International Journal of Computer Vision, 2004, 60(2):135-164.

[27] F. Kahraman, M. Gokmen, S. Darkner, et al. An Active Illumination and Appearance (AIA) Model for Face Alignment[C]//Minneapolis: IEEE Conference on Computer Vision and Pattern Recognition, 2007:336-343.

[28] G. J. Edwards, C. J. Taylor, T. F. Cootes. Interpreting face images using active appearance models[C]//Nara: IEEE Conference on Automatic Face and Gesture Recognition, 1998:300-305.

[29] B. Mohammed, S. Mahmoudi, F. Lecron. A Framework of Vertebra Segmentation Using the Active Shape Model-Based Approach[J]. International Journal of Biomed Imaging, 2011, 2011:621905-621905.

[30] P. J. Besl, N. D. McKay. A method for registration of 3-D shapes[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 14(2):239-256.

[31] C. Haili, R. Anand. A new algorithm for non-rigid point matching[C]//South Carolina: IEEE Conference on Computer Vision and Pattern Recognition, 2000:44-51.

[32] C. Haili, R. Anand. A new point matching algorithm for non-rigid registration[J]. Computer Vision Image Understanding, 2003, 89(3):114-141.

[33] Y. Zheng, D. Doermann. Robust point matching for nonrigid shapes by preserving local neigh-borhood structures[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28(4):643-649.

[34] L. Jong-Ha, W. Chang-Hee. Topology Preserving Relaxation Labeling for Nonrigid Point Matching[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(2):427-432.

[35] X. Wang, X. Bai, T. Ma, et al. Fan Shape Model for object detection[C]//Providence: IEEE Conference on Computer Vision and Pattern Recognition, 2012:151-158.

[36] X. Bai, Y. Xingwei, L. J. Latecki, et al. Learning Context-Sensitive Shape Similarity by Graph Transduction[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 32(5):861-874.

[37] T. Ma, L. J. Latecki. From partial shape matching through local deformation to robust global shape similarity for object detection[C]//Providence: IEEE Conference on Computer Vision and Pattern Recognition, 2011:1441-1448.

[38] X. Wang, B. Feng, X. Bai, et al. Bag of contour fragments for robust shape classification[J]. Pattern Recognition, 2014, 47(6):2116-2125.

[39] V. Ferrari, T. Tuytelaars, L. V. Gool. Object Detection by Contour Segment Networks[C]//South Carolina: European Conference on Computer Vision, 2006:14-28.

[40] V. Ferrari, F. Jurie, C. Schmid. Accurate Object Detection with Deformable Shape Models Learnt from Images[C]//Minneapolis: IEEE Conference on Computer Vision and Pattern Recognition, 2007:1-8.

[41] V. Ferrari, L. Fevrier, F. Jurie, et al. Groups of Adjacent Contour Segments for Object Detec-tion[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008, 30(1):36-51.

[42] V. Ferrari, F. Jurie, C. Schmid. From Images to Shape Models for Object Detection[J]. Interna-tional Journal of Computer Vision, 2010, 87(3):284-303.

[43] D. R. Martin, C. C. Fowlkes, J. Malik. Learning to detect natural image boundaries using lo-cal brightness, color, and texture cues[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 26(5):530-549.

[44] Y. Su, Y. Liu, B. Cuan, et al. Contour Guided Hierarchical Model for Shape Match-ing[C]//Santiago: IEEE International Conference on Computer Vision, 2015:1609-1617.

[45] M. A. Fischler, R. A. Elschlager. The representation and matching of pictorial structures[J].IEEE Transactions on Computer, 1973, 22(1):67-92.

[46] P. Felzenszwalb, D. P. Huttenlocher. Pictorial Structures for Object Recognition[J]. International Journal of Computer Vision, 2005, 61(1):55-79.

[47] M. Andriluka, S. Roth, B. Schiele. Pictorial structures revisited: People detection and articulat-ed pose estimation[C]//Miami: IEEE Conference on Computer Vision and Pattern Recognition, 2009:1014-1021.

[48] B. Martin, J. Kappes, S. Schmidt. A Study of Parts-Based Object Class Detection Using Com-plete Graphs[J]. International Journal of Computer Vision, 2010, 87(1-2):93-117.

[49] E. Marcin, F. Vittorio. Better Appearance Models for Pictorial Structures[C]//London: British Machine Vision Conference, 2009:35-48.

[50] M. Dantone, J. Gall, C. Leistner, et al. Body Parts Dependent Joint Regressors for Human Pose Estimation in Still Images[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2014, 33(11):2131-2143.

[51] X. Zhu, D. Ramanan. Face detection, pose estimation, and landmark localization in the wild[C]//Providence: IEEE Conference on Computer Vision and Pattern Recognition, 2012:2879-2886.

[52] M. Andriluka, S. Roth, B. Schiele. Discriminative Appearance Models for Pictorial Struc-tures[J]. International Journal of Computer Vision, 2012, 99(3):259-280.

[53] P. Felzenszwalb, R. B. Girshick, D. McAllester, et al. Object Detection with Discriminatively Trained Part-Based Models[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(9):1627-1645.

[54] P. Felzenszwalb, D. McAllester, D. Ramanan. A discriminatively trained, multiscale, deformable part model[C]//Anchorage: IEEE Conference on Computer Vision and Pattern Recognition, 2008:1-8.

[55] P. Felzenszwalb, R. B. Girshick, D. McAllester. Cascade Object Detection with Deformable Part Models[C]//San Francisco: IEEE Conference on Computer Vision and Pattern Recognition, 2010:2241-2248.

[56] L. Zhu, Y. Chen, A. Yuille, et al. Latent hierarchical structural learning for object de-tection[C]//San Francisco: IEEE Conference on Computer Vision and Pattern Recognition, 2010:1060-1069.

[57] M. Pedersoli, A. Vedaldi, J. Gonzalez. A coarse-to-fine approach for fast deformable ob-ject detection[C]//Providence: IEEE Conference on Computer Vision and Pattern Recognition, 2011:1353-1360.

[58] P. Ott, M. Everingham. Shared parts for deformable part-based models[C]//Providence: IEEE Conference on Computer Vision and Pattern Recognition, 2011:1513-1520.

[59] I. Kokkinos. Shufflets: Shared Mid-level Parts for Fast Object Detection[C]//Sydney: IEEE International Conference on Computer Vision, 2013:1393-1400.

[60] H. O. Song, R. B. Girshick, S. Zickler, et al. Generalized Sparselet Models for Real-Time Mul-ticlass Object Recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(5):1001-1012.

[61] L. Bastian, A. Leonardis, S. Bernt. Combined Object Categorization and Segmentation With An Implicit Shape Model[C]//Prague: European Conference on Computer Vision Workshop, 2004:17-32.

[62] L. Bastian, A. Leonardis, S. Bernt. Robust Object Detection with Interleaved Categorization and Segmentation[J]. International Journal of Computer Vision, 2008, 77(1-3):259-289.

[63] D. H. Ballard. Generalizing the Hough transform to detect arbitrary shapes[J]. Pattern Recogni-tion, 1987, 13(81):111-122.

[64] B. Herbert, E. Andreas, T. Tinne, et al. Speeded-Up Robust Features (SURF)[J]. Computer Vision Image Understanding, 2008, 110(3):346-359.

[65] D. Lowe. Distinctive image features from scale invariant keypoints[J]. International Journal of Computer Vision, 2004, 60(2):91-110.

[66] C. Harris, M. Stephens. A combined corner and edge detector[C]//Queensland: Alvey Vision Conference, 1988:147-151.

[67] J. MacQueen. Some methods for classification and analysis of multi-variate observation[C]//San Francisco: The 5th Berkeley Symposium on Mathematical Statistics and Probability, 1967:281-297.

[68] J. L.-S. Roberto, O.-R. Daniel, G.-J. Pedro, et al. Fast reciprocal nearest neighbors clustering[J]. Signal Processing, 2012, 92(1):270-275.

[69] Y. Cheng. Mean shift, mode seeking, and clustering[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1995, 17(8):790-799.

[70] C. Dorin, M. Peter. Mean shift: A robust approach toward feature space analysis[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(5):603-619.

[71] Y. Pradeep, O. Bjorn. Beyond the Sum of Parts: Voting with Groups of Dependent Entities[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(2):1134-1147.

[72] Y. Pradeep, A. Monroy, O. Bjorn. Voting by grouping dependent parts[C]//Crete: European Conference on Computer Vision, 2010:197-210.

[73] B. Martinez, M. F. Valstar, X. Binefa, et al. Local Evidence Aggregation for Regression-Based Facial Point Detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(5):1149-1163.

[74] X. Pei, Y. Mao, L. Xue, et al. Object detection using voting spaces trained by few samples[J]. Optical Engineering, 2013, 52(9):72-81.

[75] L. Tao, Y. Mao, D. Jian. Discriminative Hough context model for object detection[J]. Visual Computer, 2014, 30(1):59-69.

[76] Z. Yimeng, C. Tsuhan. Implicit Shape Kernel for Discriminative Learning of the Hough Trans- form Detector[C]//Aberystwyth: British Machine Vision Conference, 2010:87-101.

[77] S. Maji, J. Malik. Object detection using a max-margin Hough transform[C]//Miami: IEEE Conference on Computer Vision and Pattern Recognition, 2009:1038-1045.

[78] Criminisi A, Shotton J. Decision Forests for Computer Vision and Medical Image Analysis[M]. London: Springer, 2013:73-89.

[79] B. Leo. Random Forests[J]. Machine Learning, 2001, 45(1):5-32.

[80] J. Gall, V. Lempitsky. Class-specific Hough forests for object detection[C]//Miami: IEEE Con- ference on Computer Vision and Pattern Recognition, 2009:1022-1029.

[81] G. Juergen, Y. Angela, R. Negin, et al. Hough forests for object detection, tracking, and ac-tion recognition.[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(11):2188-2202.

[82] P. Nadia, T. Sinisa. Hough Forest Random Field for Object Recognition and Segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(5):1066-1079.

[83] C. Lindner, S. Thiagarajah, J. M. Wilkinson, et al. Fully automatic segmentation of the proximal femur using random forest regression voting.[J]. IEEE Transactions on Medical Imaging, 2013, 32(8):1462-1472.

[84] M. Dantone, J. Gall, G. Fanelli, et al. Real-time Facial Feature Detection using Conditional Re-gression Forests[C]//Providence: IEEE Conference on Computer Vision and Pattern Recognition, 2012:2578-2585.

[85] O. Barinova, V. Lempitsky, P. Kholi. On Detection of Multiple Object Instances Using Hough Transforms[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(9):1773-1784.

[86] A. Yao, J. Gall, V. G. L. A Hough transform-based voting framework for action recog-nition[C]//San Francisco: IEEE Conference on Computer Vision and Pattern Recognition,2010:2061-2068.

[87] G. Yu, N. A. Goussies, J. Yuan, et al. Fast Action Detection via Discriminative Random Forest Voting and Top-K Subvolume Search[J]. IEEE Transactions on Multimedia, 2011, 13(3):507-517.

[88] M. Sun, P. Kohli, J. Shotton. Conditional regression forests for human pose estima-tion[C]//Providence: IEEE Conference on Computer Vision and Pattern Recognition, 2012:3394-3401.

[89] M. Godec, P. M. Roth, H. Bischof. Hough-based tracking of non-rigid objects[C]//Barcelona:IEEE International Conference on Computer Vision, 2011:81-88.

[90] I. Nathan, R. Avnimelech. Boosted Mixture of Experts: An Ensemble Learning Scheme[J].Neural Computation, 1999, 11(2):483-497.

[91] R. Meir, G. Ratsch. An Introduction to Boosting and Leveraging[J]. Advanced Lectures on Machine Learning, 2002, 2600(7):118-183.

[92] F. A. J., F. M. A. T. Boosting Algorithms: A Review of Methods, Theory, and Applications[J]. Ensemble Machine Learning, 2012, 23(5):35-85.

[93] P. Viola, M. Jones. Robust Real-time Object Detection[J]. International Journal of Computer Vision, 2004, 57(2):137-154.

[94] R. Lienhart, J. Maydt. An extended set of Haar-like features for rapid object detection[C]//New York: International Conference on Image Processing, 2002:111-117.

[95] C. Huang, H. Ai, Y. Li, et al. Learning sparse features in granular space for multi-view face de-tection[C]//Southampton: International Conference on Automatic Face and Gesture Recognition,2006:401-408.

[96] Z. Hongming, G. Wen, C. Xilin, et al. Object detection using spatial histogram features[J]. Image Vision Computing, 2006, 24(4):327-341.

[97] T. Mita, T. Kaneko, O. Hori. Joint Haar-like features for face detection[C]//Beijing: IEEE International Conference on Computer Vision, 2005:1619-1626.

[98] S. C. Brubaker, W. Jianxin, S. Jie, et al. On the Design of Cascades of Boosted Ensembles for Face Detection[J]. International Journal of Computer Vision, 2008, 77(13):65-86.

[99] J. H. Friedman. Greedy Function Approximation: A Gradient Boosting Machine[J]. The Annals of Statistics, 2001, 29(5):1189-1232.

[100] R. Xiao, L. Zhu, H.-J. Zhang. Boosting chain learning for object detection[C]//Nice: IEEE International Conference on Computer Vision, 2003:709-715.

[101] B. Wu, H. Ai, C. Huang, et al. Fast rotation invariant multi-view face detection based on real Adaboost[C]//Prague: IEEE International Conference on Automatic Face and Gesture Recogni-tion, 2004:86-92.

[102] B. Wu, R. Nevatia. Cluster Boosted Tree Classifier for Multi-View, Multi-Pose Object Detec-tion.[C]//Rio de Janeiro: IEEE International Conference on Computer Vision, 2007:1-8.

[103] R. Benenson, M. Mathias, R. Timofte, et al. Pedestrian detection at 100 frames per sec-ond[C]//Providence: IEEE Conference on Computer Vision and Pattern Recognition, 2012:2903-2910.

[104] R. Benenson, M. Mathias, T. Tuytelaars, et al. Seeking the Strongest Rigid Detec-tor[C]//Portland: IEEE Conference on Computer Vision and Pattern Recognition, 2013:3666-3673.

[105] M. A. Friedl, C. E. Brodley. Decision tree classification of land cover from remotely senseddata[J]. Remote Sensing of Environment, 1997, 61(3):399-409.

[106] Rodrigo V, Javier R D S. TCAS: A Multiclass Object Detector for Robot and Computer Vision Applications[M]. Berlin: Springer, 2012:632-641.

[107] Ruiz-Del-Solar V J. Multiclass Adaboost and Coupled Classifiers for Object Detection[M]. Berlin: Springer, 2008:560-567.

[108] S. Ruslan, H. Geoffrey. Deep Boltzmann Machines[C]//Vancouver: Advances In Neural Infor-mation Processing Systems, 2009:1967-2006.

[109] B. Scholkopf, J. Platt, T. Hofmann. Greedy Layer-Wise Training of Deep Network-s[C]//Vancouver: Advances In Neural Information Processing Systems, 2007:17-25.

[110] H. G. E., Z. R. S. Autoencoders, Minimum Description Length and Helmholtz Free Ener-gy[C]//Vancouver: Advances In Neural Information Processing Systems, 1994:3-10.

[111] H. O. Song, R. B. Girshick, S. Zickler, et al. Backpropagation Applied to Handwritten Zip Code Recognition[J]. Neural Computation, 1989(1):541-551.

[112] H. O. Song, R. B. Girshick, S. Zickler, et al. Reducing the Dimensionality of Data with Neural Networks[J]. Science, 2006, 313(5786):504-507.

[113] S. C. Turaga, J. F. Murray, V. Jain, et al. Convolutional Networks Can Learn to Generate Affinity Graphs for Image Segmentation[J]. Neural Computation, 2010(2):511-538.

[114] Y. Bengio, A. Courville, P. Vincent. Representation Learning: A Review and New Perspec-tives[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(8):1798-1828.

[115] D. H. Hubel, T. N. Wiesel. Receptive fields of single neurones in the cat’s striate cortex[J].Journal of Physiology, 1959, 148(3):574-591.

[116] A. Krizhevsky, I. Sutskever, H. G. E. Imagenet classification with deep convolutional neural networks[C]//Nevada: Advances In Neural Information Processing Systems, 2012:1097-1105.

[117] G. Christophe, D. Manolis. Convolutional Face Finder: A Neural Architecture for Fast and Robust Face Detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(11):1408-1423.

[118] P. Sermanet, K. Kavukcuoglu, S. Chintala, et al. Pedestrian detection with unsupervised multi-stage feature learning[C]//Portland: IEEE Conference on Computer Vision and Pattern Recogni-tion, 2013:3626-3633.

[119] O. Wanli, X. Wang. Joint Deep Learning for Pedestrian Detection[C]//Portland: IEEE Confer-ence on Computer Vision and Pattern Recognition, 2013:3626-3633.

[120] R. B. Girshick, J. Donahue, T. Darrell, et al. Rich feature hierarchies for accurate object de-tection and semantic segmentation[C]//Columbus: IEEE Conference on Computer Vision and Pattern Recognition, 2014:580-587.

[121] Y. Zhang, K. Sohn, R. Villegas, et al. Improving object detection with deep convolutional networks via bayesian optimization and structured prediction[C]//Boston: IEEE Conference on Computer Vision and Pattern Recognition, 2015.

[122] C. Szegedy, A. Toshev, D. Erhan. Deep neural networks for object detection[C]//Nevada: Ad-vances In Neural Information Processing Systems, 2013:676-685.

[123] E. Dumitru, C. Szegedy, A. Toshev, et al. Scalable Object Detection Using Deep Neu-ral Networks[C]//Columbus: IEEE Conference on Computer Vision and Pattern Recognition, 2014:2155-2162.

[124] R. B. Girshick, F. Iandola, T. Darrell, et al. Deformable part models are convolutional neural networks[C]//Boston: IEEE Conference on Computer Vision and Pattern Recognition, 2015.

[125] W. Ouyang, X. Wang, X. Zeng, et al. Deepid-net: Deformable deep convolutional neural networks for object detection[C]//Boston: IEEE Conference on Computer Vision and Pattern Recognition, 2015.

[126] L. Wan, D. Eigen, R. Fergus. End-to-end integration of a convolutional network, deformable parts model and non-maximum suppression[C]//Boston: IEEE Conference on Computer Vision and Pattern Recognition, 2015.

[127] Wang Gongpeng, Duan Meng, Niu Changyong. Stochastic gradient descent algorithm based on convolutional neural networks[J]. Computer Engineering and Design, 2018, 39(02): 441-462.

[128] Cui Shanbo. Small target detection based on deep learning[D]. Xi'an University of Electronic Science and Technology, 2019.

[129] Simonyan K, Zisserman A. Very Deep Convolutional Networks for Large-Scale Image Recognition[J]. arXiv preprint arXiv:1409.1556, 2014.

[130] M.-H. Yang, D. Kriegman, and N. Ahuja, “Detecting faces in images: a survey,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 24, no. 1, pp.34-58,2002.

[131] Shangce Gao, Shuangbao Song, Jiujun Cheng, Yuki Todo, and MengChu Zhou, “Incorporation of Solvent Effect into Multi-objective Evolutionary Algorithm for Improved Protein Structure Prediction,” IEEE/ACM Transactions on Computational Biology and Bioinformatics, vol. 15, no.4, pp.1365-1378, July-Aug. 2018.

[132] D. Chen, S. Ren, Y. Wei, X. Cao, and J. Sun, “Joint cascade face detection and alignment,” European Conference on Computer Vision, 2014.

[133] H. Li, Z. Lin, X. Shen, J. Brandt, and G. Hua, “A convolutional neural network cascade for face detection,” Computer Vision & Pattern Recognition, 2015.

[134] M. Mathias, R. Benenson, M. Pedersoli, and L. Van Gool, “Face detection without bells and whistles,” Springer International Publishing,2014.

[135] B. Yang, J. Yan, Z. Lei, and S. Z. Li, “Aggregate channel features for multi-view face detection,” IEEE International Joint Conference on Biometrics, 2014.

[136] S. Yang, P. Luo, C. C. Loy, and X. Tang, “From facial parts responses to face detection: A deep learning approach,” IEEE International Conference on Computer Vision, 2016.

[137] Yang Yu, Shangce Gao, Yirui Wang, and Yuki Todo, “Global Optimum-based Search Differential Evolution,” IEEE/CAA Journal of Automatica Sinica, vol.6, no.2, pp.379-394, March 2019.

[138] X. Zhu and D. Ramanan, “Face detection, pose estimation, and landmark localization in the wild,” Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on, 2012.

[139] J. Yan, X. Zhang, Z. Lei, and S. Z. Li, “Face detection by structural models,” Image and Vision Computing, 2014.

[140] B. F. Klare, B. Klein, E. Taborsky, A. Blanton, J. Cheney, K. Allen, P. Grother, A. Mah, M. Burge, and A. K. Jain, “Pushing the frontiers of unconstrained face detection and recognition: IARPA janus benchmark A,” IEEE Computer Vision and Pattern Recognition (CVPR), 2015.

[141] Jian Sun, Shangce Gao, Hongwei Dai, Jiujun Cheng, MengChu Zhou, and Jiahai Wang, “Bi-objective Elite Differential Evolution Algorithm for Multivalued Logic Networks,” IEEE Transactions on Cybernetics, vol.50, no.1, pp. 233-246, January 2020..

[142] J. Li and Y. Zhang, “Learning surf cascade for fast and accurate object detection,” Computer Vision and Pattern Recognition, pp. 3468-3475,2013.

[143] X. Zhu and D. Ramanan, “Face detection, pose estimation, and landmark localization in the wild,” Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on. IEEE, pp. 2879-2886. 2012.

[144] P. Felzenszwalb, R. Girshick, D. McAllester, and D. Ramanan, “Object detection with discriminatively trained part-based models,” IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 32, no. 9, pp. 1627-1645, 2010.

[145] X. Yu, J. Huang, S. Zhang, W. Yan, and D. Metaxas, “Pose-free facial landmark fitting via optimized part mixtures and cascaded deformable shape model,” IEEE International Conference on Computer Vision, 2014.

[146] G. Ghiasi and C. C. Fowlkes, “Occlusion coherence: Detecting and localizing occluded faces,” Computer Science, 2015.

[147] D. Chen, S. Ren, Y. Wei, X. Cao, and J. Sun, “Joint cascade face detection and alignment,” European Conference on Computer Vision ,2014.

[148] M. Mathias, R. Benenson, M. Pedersoli, and L. Van Gool, “Face detection without bells and whistles,” Springer International Publishing, 2014.

[149] H. Li, Z. Lin, X. Shen, J. Brandt, and G. Hua, “A convolutional neural network cascade for face detection,” Computer Vision & Pattern Recognition, 2015.

[150] S. Yang, P. Luo, C.-C. Loy, and X. Tang, “From facial parts responses to face detection: A deep learning approach,” IEEE International Conference on Computer Vision, 2016.

[151] Shangce Gao, Yang Yu, Yirui Wang, Jiahai Wang, Jiujun Cheng, and MengChu Zhou, “Chaotic Local Search-based Differential Evolution Algorithms for Optimization,” IEEE Transactions on Systems, Man and Cybernetics: Systems, vol. PP, no. 99, pp. 1-14, 2019.

[152] S. Bell, C. L. Zitnick, K. Bala, and R. Girshick, “Inside-outside net: Detecting objects in context with skip pooling and recurrent neural networks,” 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016.

[153] S. Zagoruyko, A. Lerer, T.-Y. Lin, P. O. Pinheiro, S. Gross, S. Chintala, and P. Doll´ar, “A multipath network for object detection,”2016.

[154] Y. Xiong, K. Zhu, D. Lin, and X. Tang, “Recognize complex events from static images by fusing deep channels,” Computer Vision & Pattern Recognition, 2015.

[155] Yirui Wang, Shangce Gao, MengChu Zhou, and Yang Yu, “A Multi-layered Gravitational Search Algorithm for Function Optimization and Real-world Problems,” IEEE/CAA Journal of Automatica Sinica, vol. 8, no. 1, pp. 1-16, January 2021.

[156] B.Yang, J.Yan, Z.Lei, and S.Z.Li, “Fine-grainedevaluation on face detection in the wild,” 2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG),2015.

[157] Shangce Gao, Mengchu Zhou, Yirui Wang, Jiujun Cheng, Hanaki Yachi, and Jiahai Wang, “Dendritic neuron model with effective learning algorithms for classification, approximation, and prediction,” IEEE Transactions on Neural Networks and Learning Systems, vol. 30, no. 2, pp. 601-614, 2019.

[158] K. Song and Y. Yan, “A noise robust method based on completed local binary patterns for hot-rolled steel strip surface defects,” Applied Surface Science, vol. 285, no. 21, pp. 858-864, 2013.

[159] Y. Dong, D. Tao, X. Li, J. Ma, and J. Pu, “Texture classification and retrieval using shearlets and linear regression,” IEEE Trans Cybern, vol. 45, no. 3, pp. 358-369, 2015.

[160] M. Xiao, M. Jiang, G. Li, L. Xie, and L. Yi, “An evolutionary classifier for steel surface defects with small sample set,” EURASIP Journal on Image and Video Processing, vol. 2017, no. 1, pp.48, 2017.

[161] Lin Jiang ,Jia Chen ,Hiroyoshi Todo , Zheng Tang , Sicheng Liu ,Yang Li,Application of a fast RCNN based on upper and lower layers in face recognition,Computational Intelligence and Neuroscience,Volume 2021, Article ID 9945934.

[162] Tao Cong,Lin Jiang,Qihang Sun,Yang Li,Application of Rough Ant Colony Algorithm in Adolescent Psychology,Computational Intelligence and Neuroscience,Volume 2021,Article ID 6636150.

[163] Sicheng Liu,Sichen Tao,Haichuan Yang,Lin Jiang,Yuki Todo,Shangce Gao, Using Grey Wolf Hunting Mechanism to Improve Spherical Search,IEEE 13th International Symposium on Computational Intelligence and Design (ISCID), Hangzhou, China, 2020.12, DOI:10.1109/ISCID51228.2020.00022

[164] Yan. LeCun, L. Bottou, Y. Bengio and P. Haffner,Gradient-Based Learning Applied to Document Recognition, Proceedings of the IEEE, 86(11):2278-2324, November 1998.

参考文献をもっと見る

全国の大学の
卒論・修論・学位論文
を
一発検索！

この論文の関連論文を見る