Advancements in Image Classification and Object Detection: Leveraging Deep Learning for Enhanced Performance
Keywords:
CNN, RNN, SVM, Object detection.Abstract
This paper summarizes the research focusing on image classification and object detection. For object detection, we addressed the challenge of bridging deep convolutional neural networks (CNNs) with traditional detection frameworks to achieve accurate and efficient generic object detection. We introduced Dense Neural Patterns (DNPs), dense local features derived from discriminatively trained deep CNNs, which demonstrated effectiveness in the Regionlets detection framework, significantly improving performance on the PASCAL VOC datasets. In image classification, key advancements include the development of Latent CNN for handling multi-label images, Multiple Instance Learning Convolutional Neural Networks (MILCNN) for leveraging deep learning with limited labeled data, and the Residual Networks of Residual Networks (RoR) architecture for enhancing optimization. Despite these contributions, there remains room for improvement: enhancing detection speed through CNN-generated bounding box proposals, incorporating unsupervised learning to align with natural learning processes, and employing RNNs with LSTM units for generating more effective image regions in classification tasks.
Downloads
References
Pedro F. Felzenszwalb, Ross B. Girshick, David A. McAllester, and Deva Ra- manan. Object detection with discriminatively trained part-based models. IEEE Trans. Pattern Anal. Mach. Intell.,2010.
Koen E. A. vande S and e, Jasper R. R. Uijlings, The o Gevers, and Arnold
W. M. Smeulders. Segmentation as selective search for object recognition. In
ICCV, 2011.
Bogdan Alexe, Thomas Deselaers, and Vittorio Ferrari. Measuring the object- nessofimagewindows.IEEETrans.PatternAnal.Mach.Intell.,34:2189–2202, 2012.
Andrea Vedaldi, Varun Gulshan, Manik Varma, and Andrew Zisserman. Mul- tiple kernels for object detection. In ICCV,2009.
Xiaoyu Wang, Ming Yang, Shenghuo Zhu, and Yuanqing Lin. Regionlets for generic object detection. In ICCV,2013.
Ross Girshick, Jeff Donahue, Trevor Darrell, and Jitendra Malik. Rich feature hierarchies for accurate object detection and semantic segmentation. In CVPR, 2014.
D. Lowe. Distinctive image features from scale-invariant keypoints. In IJCV, 2004.
Navneet Dalal and Bill Triggs. Histograms of oriented gradients for human detection. In CVPR,2005.
Timo Ojala, Matti Pietik¨ainen, and David Harwood. A comparative study of texture measures with classification based on featured distributions. Pattern Recognition, 29:51–59,1996.
G. Csurka, C. Dance, L. Fan, J. Willamowski, and C. Bray. Visual categorization with bagsofkeypoints. In ECCV Workshop, 2004.
Svetlana Lazebnik, Cordelia Schmid, and Jean Ponce. Beyond bags of fea- tures: Spatial pyramid matching for recognizing natural scene categories. In Proceedings of Computer Vision and Pattern Recognition, pages2169–2178, Washington, DC, USA, 2006. IEEE Computer Society.
Chang Chih-Chung and Chih-Jen Lin. LIBSVM: A library for support vector machines. ACM Transactions on Intelligent Systems and Technology, 2:27:1– 27:27,2011.
Tin KamHo. R and omdecision forests. In Proceeding softhe Third International Conference on Document Analysis and Recognition (Volume1)-Volume1, ICDAR’95,pages278, Washington, DC, USA, 1995. IEEE Computer Society.
Paul Viola, Michael J Jones, and Robert A Iannucci. Robust real-time object detection. InIJCV.
N. Dalal and B. Triggs. Histograms of oriented gradients for human detection. In CVPR,2005.
Pedro F. Felzenszwalb, Ross B. Girshick, David McAllester, and DevaRa- manan. Object detection with discriminatively trained part based models. In IEEE Transactions on Pattern Analysis and Machine Intelligence, volume32, pages 1627–1645,2010.
M. Everingham, L. Van Gool, C. K. I. Williams, J. Winn, and A. Zisserman. The PASCAL Visual Object Classes Challenge 2007 (VOC2007) Results.http://www.pascal-network.org/challenges /VOC/voc2007/ workshop/index.html,2007.
Long Zhu, Yuanhao Chen, Alan L. Yuille, and William T. Freeman. Latent hierarchical structural learning for object detection. In CVPR,2010.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
