Adaptive object recognition model using incremental feature representation and hierarchical classification. (English) Zbl 1259.68176
Summary: This paper presents an adaptive object recognition model based on incremental feature representation and a hierarchical feature classifier that offers plasticity to accommodate additional input data and reduces the problem of forgetting previously learned information. The incremental feature representation method applies adaptive prototype generation with a cortex-like mechanism to conventional feature representation to enable an incremental reflection of various object characteristics, such as feature dimensions in the learning process. A feature classifier based on using a hierarchical generative model recognizes various objects with variant feature dimensions during the learning process. Experimental results show that the adaptive object recognition model successfully recognizes single and multiple-object classes with enhanced stability and flexibility.
MSC:
| 68T10 | Pattern recognition, speech recognition |
| 62H30 | Classification and discrimination; cluster analysis (statistical aspects) |
Keywords:
adaptive object recognition; incremental feature representation; hierarchical feature classifier; incremental learning; variant feature dimensionsReferences:
| [1] | Bilmes, J. A., A gentle tutorial of the EM algorithm and its application to parameter estimation for Gaussian mixture and hidden Markov models, International Computer Science Institute, 4, TR-97-021 (1997) |
| [2] | Fei-Fei, L. 2006. Knowledge transfer in learning to recognize visual objects classes. In Proceedings of the International Conference on Development and Learning.; Fei-Fei, L. 2006. Knowledge transfer in learning to recognize visual objects classes. In Proceedings of the International Conference on Development and Learning. |
| [3] | Fei-Fei, L., Fergus, R., & Perona, P. 2004. Learning generative visual models from few training examples: an incremental Bayesian approach tested on 101 object categories. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Workshop on Generative-model based vision.; Fei-Fei, L., Fergus, R., & Perona, P. 2004. Learning generative visual models from few training examples: an incremental Bayesian approach tested on 101 object categories. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Workshop on Generative-model based vision. |
| [4] | Fei-Fei, L.; Fergus, R.; Perona, P., One-Shot learning of object categories, IEEE Transaction on Pattern Analysis and Machine Intelligence, 28, 4, 594-611 (2006) |
| [5] | Fei-Fei, L., & Perona, P. 2005. A Bayesian hierarchical model for learning natural scene categories. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (pp. 524-531).; Fei-Fei, L., & Perona, P. 2005. A Bayesian hierarchical model for learning natural scene categories. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (pp. 524-531). |
| [6] | Fergus, R., Perona, P., & Zisserman, A. 2003. Object class recognition by unsupervised scale-invariant learning. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (pp. 264-271).; Fergus, R., Perona, P., & Zisserman, A. 2003. Object class recognition by unsupervised scale-invariant learning. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (pp. 264-271). |
| [7] | Fritzke, B., Growing cell structures — A self-organizing network for unsupervised and supervised learning, Neural Networks, 7, 1441-1460 (1994) |
| [8] | Fukushima, K., Neocognitron: a self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position, Biological Cybernetics, 36, 193-202 (1980) · Zbl 0419.92009 |
| [9] | Fukushima, K., Neocognitron for handwritten digit recognition, Neurocomputing, 51, 161-180 (2003) |
| [10] | Hofmann, T. 1999. Probabalistic latent semantic analysis. In Proceedings of the Conference on Uncertainty in Artificial Intelligence.; Hofmann, T. 1999. Probabalistic latent semantic analysis. In Proceedings of the Conference on Uncertainty in Artificial Intelligence. |
| [11] | Hubel, D. H.; Wiesel, T. N., RFs and functional architecture of monkey striate cortex, Journal of Physiology, 148, 574-591 (1968) |
| [12] | Itti, L.; Koch, C.; Niebur, E., A model of saliency-based visual attention for rapid scene analysis, IEEE Transaction on Pattern Analysis and Machine Intelligence, 20, 11, 1254-1259 (1998) |
| [13] | Jeong, S.; Ban, S.-W.; Lee, M., Stereo saliency map considering affective factors and selective motion analysis in a dynamic environment, Neural networks, 21, 1420-1430 (2008) |
| [14] | Kadir, T.; Brady, M., Scale, saliency and image description, International Journal of Computer Vision, 45, 2, 83-105 (2001) · Zbl 0987.68597 |
| [15] | Kirstein, S., Wersing, H., Gross, H., & Körner, E. 2008. A vector quantization approach for life-long learning of categories. In Proceedings of the International Conference on Neuro- Information Processing, Special Session. Lifelong Incremental Learning for Intelligent Systems.; Kirstein, S., Wersing, H., Gross, H., & Körner, E. 2008. A vector quantization approach for life-long learning of categories. In Proceedings of the International Conference on Neuro- Information Processing, Special Session. Lifelong Incremental Learning for Intelligent Systems. |
| [16] | Marsland, S.; Shapiro, J.; Nehmzow, U., A self-organising network that grows when required, Neural Networks, 15, 1041-1058 (2002) |
| [17] | Nishikawa, H., Ozawa, S., & Roy, A. 2008. A neural network model for sequential multitask pattern recognition problems. In Proceedings of the International Conference on Neuro- Information Processing, Special Session, Lifelong Incremental Learning for Intelligent Systems.; Nishikawa, H., Ozawa, S., & Roy, A. 2008. A neural network model for sequential multitask pattern recognition problems. In Proceedings of the International Conference on Neuro- Information Processing, Special Session, Lifelong Incremental Learning for Intelligent Systems. |
| [18] | Ozawa, S.; Roy, A.; Roussinov, D., A multitask learning model for online pattern recognition, IEEE Transaction on neural networks, 20, 430-445 (2009) |
| [19] | Park, S. J.; An, K. H.; Lee, M., Saliency map model with adaptive masking based on independent component analysis, Neurocomputing, 49, 417-422 (2002) |
| [20] | Park, S. J.; Shin, J. K.; Lee, M., Biologically inspired saliency map model for bottom-up visual attention, Lecture Notes in Computer Science, 2525, 418-426 (2002) · Zbl 1033.68882 |
| [21] | Riesenhuber, M.; Poggio, T., Hierarchical models of object recognition in cortex, Nature Neuroscience, 2, 11, 1019-1025 (1999) |
| [22] | Serre, T., Wolf, L., & Poggio, T. 2005. Object recognition with features inspired by visual cortex. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 994-1000.; Serre, T., Wolf, L., & Poggio, T. 2005. Object recognition with features inspired by visual cortex. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 994-1000. |
| [23] | Sivic, J., Russell, B., Efros, A., Zisserman, A., & Freeman, W. 2005. Discovering object categories in image collections. In Proceedings of the International Conference on Computer Vision.; Sivic, J., Russell, B., Efros, A., Zisserman, A., & Freeman, W. 2005. Discovering object categories in image collections. In Proceedings of the International Conference on Computer Vision. |
| [24] | Tsunoda, K.; Yamane, Y.; Nishizaki, M.; Tanifuji, M., Complex objects are represented in macaque inferotemporal cortex by the combination of feature columns, Nature neuroscience, 4, 8, 832-838 (2001) |
| [25] | Ulusoy, L., & Bishop, C.M. 2005. Generative versus discriminative methods for object recognition. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2, 258-265.; Ulusoy, L., & Bishop, C.M. 2005. Generative versus discriminative methods for object recognition. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2, 258-265. |
| [26] | Vailaya, A., & Jain, A. 1999. Incremental learning for Bayesian classification of images. In Proceedings of the International Conference on Image Processing, 2, 585-589.; Vailaya, A., & Jain, A. 1999. Incremental learning for Bayesian classification of images. In Proceedings of the International Conference on Image Processing, 2, 585-589. |
| [27] | Woo, J.-W., Lim, Y.-C., & Lee, M. 2010. Dynamic obstacle identification based on global and local features for a driver assistance system. Neural Computing & Applications [On-line serial].; Woo, J.-W., Lim, Y.-C., & Lee, M. 2010. Dynamic obstacle identification based on global and local features for a driver assistance system. Neural Computing & Applications [On-line serial]. |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
