We propose a method for indoor versus outdoor scene classification using a probabilistic
neural network (PNN). The scene is initially segmented (unsupervised) using fuzzy
-means clustering (FCM) and features based on color, texture, and shape are extracted
from each of the image segments. The image is thus represented by a feature set, with
a separate feature vector for each image segment. As the number of segments differs
from one scene to another, the feature set representation of the scene is of varying
dimension. Therefore a modified PNN is used for classifying the variable dimension
feature sets. The proposed technique is evaluated on two databases: IITM-SCID2 (scene
classification image database) and that used by Payne and Singh in 2005. The performance
of different feature combinations is compared using the modified PNN.
References
-
E Saber, AM Tekalp, Integration of color, edge, shape, and texture features for automatic region-based image annotation and retrieval. Journal of Electronic Imaging 7(3), 684–700 (1998). Publisher Full Text
-
A Payne, S Singh, Indoor vs. outdoor scene classification in digital photographs. Pattern Recognition 38(10), 1533–1545 (2005). Publisher Full Text
-
AK Jain, A Vailaya, Image retrieval using color and shape. Pattern Recognition 29(8), 1233–1244 (1996). Publisher Full Text
-
A Vailaya, A Jain, HJ Zhang, On image classification: city images vs. landscapes. Pattern Recognition 31(12), 1921–1935 (1998). Publisher Full Text
-
Q Iqbal, JK Aggarwal, Image retrieval via isotropic and anisotropic mappings. Proceedings of IAPR Workshop on Pattern Recognition in Information Systems, July 2001, Setubal, Portugal, 34–49
-
Q Iqbal, JK Aggarwal, Applying perceptual grouping to content-based image retrieval: building images. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR '99), June 1999, Fort Collins, Colo, USA 1, 42–48
-
RM Haralick, LG Shapiro, Computer and Robot Vision (Addison-Wesley, Reading, Mass, USA, 1992)
-
H Yu, WEL Grimson, Combining configurational and statistical approaches in image retrieval. Proceedings of the 2nd IEEE Pacific Rim Conference on Multimedia: Advances in Multimedia Information Processing, October 2001, Beijing, China, Lecture Notes in Computer Science 2195, 293–300
-
JZ Wang, J Li, G Wiederhold, Simplicity: semantics-sensitive integrated matching for picture libraries. IEEE Transactions on Pattern Analysis and Machine Intelligence 23(9), 947–963 (2001). Publisher Full Text
-
J Luo, M Boutell, Natural scene classification using overcomplete ICA. Pattern Recognition 38(10), 1507–1519 (2005). Publisher Full Text
-
MM Gorkani, RW Picard, Texture orientation for sorting photos "at a glance". Proceedings of the 12th International Conference on Pattern Recognition (ICPR '94), October 1994, Jerusalem, Israel 1, 459–464
-
AS Navid Serrano, J Luo, A computationally efficient approach to indoor/outdoor scene classification. Proceedings of the International Conference on Pattern Recognition (ICPR '02), August 2002, Quebec City, Quebec, Canada 4, 146–149
-
SG Rao, M Puri, S Das, Unsupervised segmentation of texture images using a combination of gabor and wavelet features. Proceedings of the 4th Indian Conference on Computer Vision, Graphics and Image Processing (ICVGIP '04), December 2004, Kolkata, India, 370–375
-
MFA Fauzi, PH Lewis, A fully unsupervised texture segmentation algorithm. Proceedings of the British Machine Vision Conference (BMVC '03), September 2003, Norwich, UK, 519–528
-
E Salari, Z Ling, Texture segmentation using hierarchical wavelet decomposition. Pattern Recognition 28, 1819–1824 (1995). Publisher Full Text
-
IE Gordon, Theories of Visual Perception, 3rd edn. (Psychology Press, New York, NY, USA, 2004)
-
C-S Lu, P-C Chung, C-F Chen, Unsupervised texture segmentation via wavelet transform. Pattern Recognition 30(5), 729–742 (1997). Publisher Full Text
-
C Carson, M Thomas, M Belongie, J Hellerstein, J Malik, Blobworld: a system for region based image indexing and retrieval. Proceedings of the 3rd International Conference on Visual Information Systems, June 1999, Amsterdam, The Netherlands
-
F Mokhtarian, M Bober, Curvature Scale Space Representation: Theory, Applications and MPEG-7 Standarization (Kluwer Academic, Boston, Mass, USA, 2003)
-
DF Specht, Probabilistic neural networks. Neural Networks 3(1), 109–118 (1990). Publisher Full Text
-
PEH Richard, O Duda, DG Stork, Pattern Classification (John Wiley & Sons, New York, NY, USA, 2004)
-
IIT Madras Scene Classification Image Database (SCID) (http://vplab), . cs.iitm.ernet.in/SCID/ webcite




