Indexing Colored Surfaces in Images - Pattern Recognition, 1996., Proceedings of the 13th International Conference on
نویسندگان
چکیده
I n th i s paper we present a method of indexing color im.ages based o n color surface reflectance classes. Specifically. we analyse the d i s t r ibu t iom f r o m m e m bers of a surface color class in a chrominance-based color space and show tha t they fo rm, collinear clusters under identical i l luminat ion . W e also design a n optima l color space based o n the Fisher d iscr iminant criter ion t o max imal l y separate members of diflerent color surface classes. F inal ly , color index ing i s achieved by f ind ing regions in unsegmented images tha t belong to a queried color surface class using the location and orien ta t ion in format ion of the color distributions in the optimal color space. Resul t s are s h o w n that indicate that us ing both location and or ien ta t ion in format ion of surface color in the opt imal color space lowers the n u m ber of fa l se posit ives and negatives in indexing.
منابع مشابه
Visual Input for Pen-Based Computers - Pattern Recognition, 1996., Proceedings of the 13th International Conference on
Handwriting may be captured using a video camera: rather than the customary pressure-sensitive tablet. This paper presents a simple system based on correlation and recursive prediction methods that can track the tip of the pen in real time with SUBcient spatio-temporal resolution and accuracy to enable handwritten character recognition. The system is tested on a large and heterogeneous set of e...
متن کاملTexture Classification Using N-Tuple Pattern Recognition - Pattern Recognition, 1996., Proceedings of the 13th International Conference on
This paper presents a novel approach to real-time texture classification, derived from the n-tuple method of Bledsoe & Browning, for use in industrial applications. In recent years, various approaches have been presented for the texture classifcation problem. However, few have the computational tractability needed in an automated environment. In this paper, methods for texture classijkation bas...
متن کاملLearning Bidimensional Context-Dependent Models Using a Context-Sensitive Language - Pattern Recognition, 1996., Proceedings of the 13th International Conference on
Automatic generation of models from a set of positive and negative samples and a-priori knowledge {if available) is a crucial issue for pattern recognition applications. Grammatical inference can play an important role in this issue since it can be used to generate the set of model classes, where each class consists on the rules to generate the models. In this paper we present the process of le...
متن کاملProceedings of the 6th International Conference on Science and Social Research (CSSR)(Malaysia)
متن کامل
United States Patent Hull et al
and pp. 5/1-5/2. Langley "An Analysis of Bayesian Classifiers," Proceedings of the Tenth National Conference on Artificial Intelligence, pp. 223-228, 1992. Langley "Induction of Selective Bayesian Classifiers," Proceedings of the Tenth National Conference on Uncertainty in Artificial Intelligence, pp. 400-406, (1994). Li et al. "Automatic Text Detection and Tracking in Digital Video," IEEE Tran...
متن کامل