Outdoor Natural Scene Object Classification Using Probabilistic Neural Network
DOI:
https://doi.org/10.26438/ijcse/v6si1.2631Keywords:
Color feature, Statistical texture features, Horizontal line texture feature, Image classification, PNNAbstract
Region labeling for outdoor scenes to identify sky, green land, water, snow etc. facilitates content-based image retrieval systems. This paper presents use of multiple features to classify various objects of the outdoor natural scene image. Proposed system aims to classify images of the sky, water and green land. As all these nature components are irregular in shape, they can be classified using color and texture features. Color features of the object are extracted by using segmentation in La*b* color space. In the process of texture feature calculation, the image is initially divided into smaller grids. Global GLCM based statistical texture features are calculated using statistical features of these local grids. Results show that color and statistical texture features are not sufficient to differentiate sky and water body. To achieve discrimination between these two objects, a new edge-based horizontal line texture feature is proposed. The proposed feature is used to differentiate between sky and water objects based on the density of horizontal lines. All these features are used together to train probabilistic neural network for classification. The system has achieved improvement of 5% to 8% in F-measure, when all these features are used together for classification of natural scene objects.
References
Da Silva Júnior, João Augusto, Rodiney Elias Marçal, and Marcos Aurélio Batista. "Image Retrieval: Importance and Applications." Workshop de Vis~ ao Computacional-WVC. 2014.
http://www.leeds.ac.uk/educol/documents/00001240.htm#_Toc442192675
Bora, Dibya Jyoti, Anil Kumar Gupta, and Fayaz Ahmad Khan. "Comparing the performance of L* A* B* and HSV color spaces with respect to color image segmentation." arXiv preprint arXiv:1506.01472 (2015).
He, Zhen, et al. "Robust road detection from a single image using road shape prior." Image Processing (ICIP), 2013 20th IEEE International Conference on. IEEE, 2013.
Bappy, Jawadul H., et al. "Real Estate Image Classification." Applications of Computer Vision (WACV), 2017 IEEE Winter Conference on. IEEE, 2017.
Jomaa, Hadi S., Yara Rizk, and Mariette Awad. "Semantic and Visual Cues for Humanitarian Computing of Natural Disaster Damage Images." Signal-Image Technology & Internet-Based Systems (SITIS), 2016 12th International Conference on. IEEE, 2016.
Park, Soo Beom, Jae Won Lee, and Sang Kyoon Kim. "Content-based image classification using a neural network." Pattern Recognition Letters 25.3 (2004): 287-300.
Varior, Rahul Rama, and Gang Wang. "A data-driven color feature learning scheme for image retrieval." Acoustics, Speech and Signal Processing (ICASSP), 2015 IEEE International Conference on. IEEE, 2015.
Kang, Sanggil, and Sungjoon Park. "A fusion neural network classifier for image classification." Pattern Recognition Letters30.9 (2009): 789-793.
Chow, Tommy WS, and M. K. M. Rahman. "A new image classification technique using tree-structured regional features." Neurocomputing 70.4 (2007): 1040-1050.
Aditya Vailaya, Anil K. Jain, "Detecting sky and vegetation in outdoor images", Proc. SPIE 3972, Storage and Retrieval for Media Databases 2000.
Luo, Jiebo, and Andreas Savakis. "Indoor vs outdoor classification of consumer photographs using low-level and semantic features." Image Processing, 2001. Proceedings. 2001 International Conference on. Vol. 2. IEEE, 2001.
Serrano, Navid, Andreas Savakis, and A. Luo. "A computationally efficient approach to indoor/outdoor scene classification." Pattern Recognition, 2002. Proceedings. 16th International Conference on. Vol. 4. IEEE, 2002.
Feng, Xiaojuan, Christopher KI Williams, and Stephen N. Felderhof. "Combining belief networks and neural networks for scene segmentation." IEEE Transactions on Pattern Analysis and Machine Intelligence 24.4 (2002): 467-483.
Boutell, Matthew R., Jiebo Luo, and Christopher M. Brown. "Improved semantic region labeling based on scene context." Multimedia and Expo, 2005. ICME 2005. IEEE International Conference on. IEEE, 2005.
Quelhas, Pedro, et al. "A thousand words in a scene." IEEE transactions on pattern analysis and machine intelligence 29.9 (2007).
Perronnin, Florent. "Universal and adapted vocabularies for generic visual categorization." IEEE Transactions on pattern analysis and machine intelligence 30.7 (2008): 1243-1256.
Mylonas, Phivos, et al. "Using visual context and region semantics for high-level concept detection." IEEE Transactions on Multimedia 11.2 (2009): 229-243.
Patra, Prashant Kumar, et al. "Probabilistic neural network for pattern classification." Neural Networks, 2002. IJCNN'02. Proceedings of the 2002 International Joint Conference on. Vol. 2. IEEE, 2002.
Othman, Mohd Fauzi, and Mohd Ariffanan Mohd Basri. "Probabilistic neural network for brain tumor classification." Intelligent Systems, Modelling and Simulation (ISMS), 2011 Second International Conference on. IEEE, 2011.
Sawant, Shreepad S., and Preeti S. Topannavar. "Introduction to Probabilistic Neural Network─ Used For Image Classifications." International Journal of Advanced Research in Computer Science and Software Engineering 5.4 (2015): 279-283.
Sridhar, D., and IV Murali Krishna. "Face image classification using combined classifier." Signal Processing Image Processing & Pattern Recognition (ICSIPR), 2013 International Conference on. IEEE, 2013.
Beale, Mark Hudson, Martin T. Hagan, and Howard B. Demuth. "Neural network toolbox 7." User’s Guide, MathWorks 2 (2010): 77-81.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors contributing to this journal agree to publish their articles under the Creative Commons Attribution 4.0 International License, allowing third parties to share their work (copy, distribute, transmit) and to adapt it, under the condition that the authors are given credit and that in the event of reuse or distribution, the terms of this license are made clear.
