OBJECT CLASSIFICATION USING VARIOUS SEGMENTATION METHODS BASED ON COLOR HISTOGRAM
Keywords:
object recognition, classification methods, confusion matrixAbstract
This study evaluates color-based classification for beverage recognition using various segmentation and histogram-based methods. We implement five segmentation approaches, four vector creation methods, and five classification metrics on a dataset of beverage categories. After refining the dataset, our solution achieves 87.5% accuracy using threshold segmentation with average vector creation and KL divergence classification.
References
Srivastava D., Wadhvani R., Gyanchandani M. A Review: Color Feature Extraction Methods for Content Based Image Retrieval. International Journal of Computational Engineering & Management. 2015. Vol. 18(3). P.9-13.
Liu Y., Liu G., Liu C., Sun C. A Novel Color-Texture Descriptor Based on Local Histograms for Image Segmentation. IEEE Access. 2019. Vol. 7. P. 160683-160695.
Dong Y. An Improved Image Retrieval Algorithm Based on Color Histogram. International Conference on Advances in Mechanical Engineering and Industrial Informatics. 2015. P. 1110-1114.
Huang J., Kumar S. R., Mitra M., Zhu W. J., Zabih R. Image indexing using color correlograms. In IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 1997. P. 762-768.
Lin C. H., Chen R. T., Chan Y. K. A smart content-based image retrieval system based on color and texture feature. Image and Vision Computing. 2009. Vol. 27(6). P. 658-665.
