Deep Learning Alpha Numeric and Multi Object Recognization in Captured Motion
Keywords:
Dataset, Contour Analysis, DetectionAbstract
Object detection based on deep learning is an important application due to its strong capability of feature learning and feature reprensentation compared with traditional detection methods. An introduction of Classical methods in object detection is explained first and a detailed approach of relation and difference between classical methods and deep learning is also shown. The paper focusses on the frame work design and working principle of models. It analyzes the model performance in real time using concept of Contour analysis which can be worked in normal camera. Text and face recognition are done. Once known face abd unknown faces are detected using recognizer name of the known persons will be displayed and an email (sms) would be sent to the higher authority.
References
- Hinterstoisser S, Lepetit V, Ilic S, et al. Dominant orientation templatesfor real-time detection of texture-less objectsC]//Computer Vision andPattern Recognition (CVPR), 2010 IEEE Conference on. IEEE, 2010:2257-2264.
- Hinterstoisser S, Cagniart C, Ilic S, et al. Gradient response maps for real-time detection of textureless objectsJ]. Pattern Analysis and MachineIntelligence, IEEE Transactions on, 2012, 34(5): 876-888.
- Rios-Cabrera R, Tuytelaars T. Discriminatively Trained Templates for3D Object Detection: A Real Time Scalable ApproachC]//ComputerVision (ICCV), 2013 IEEE International Conference on. IEEE, 2013:2048-2055.
- Rios-Cabrera R, Tuytelaars T. Boosting masked dominant orientationtemplates for efficient object detectionJ]. Computer Vision and ImageUnderstanding, 2014, 120: 103-116.
- Hsiao E, Hebert M. Gradient Networks: Explicit Shape Matching WithoutExtracing images
- Y. Yang and D. Ramanan. Articulated human detection withflexible mixtures of parts. IEEE Trans. PAMI, 35(12):2878–2890, 2013. 2
- B. Yao and L. Fei-Fei. Modeling mutual context of objectand human pose in human-object interaction activities. InCVPR, 2010.
- M. D. Zeiler and R. Fergus. Visualizing and under-standing convolutional neural networks. arXiv preprint arXiv:1311.2901, 2013. 2, 3, 4, 6, 7
- X. Zeng, W. Ouyang, M. Wang, and X. Wang. Deep learn-ing of scene-specific classifier for pedestrian detection. InECCV, pages 472–487. 2014. 2
- X. Zeng, W. Ouyang, and X. Wang. Multi-stage contextualdeep learning for pedestrian detection. In ICCV, 2013. 2
- N. Zhang, J. Donahue, R. Girshick, and T. Darrell. Part-based r-cnns for fine-grained category detection. In ECCV,pages 834–849. 2014. 1, 4
- R. Zhao, W. Ouyang, H. Li, and X. Wang. Saliency detectionby multi-context deep learning. In CVPR, 2015. 2
- L. Zhu, Y. Chen, A. Yuille, and W. Freeman. Latent hierarchical structural learning for object detection. In CVPR,2010.
- C. L. Zitnick and P. Doll ́ar. Edge boxes: Locating objectproposals from edges. In ECCV, 2014. 8
- W. Y. Zou, X. Wang, M. Sun, and Y. Lin. Generic objectdetection with dense neural
Downloads
Published
Issue
Section
License
Copyright (c) IJSRCSEIT
This work is licensed under a Creative Commons Attribution 4.0 International License.