A novel approach for feature quantization using one-dimensional histogram

A new approach for quantizing feature vectors of interest points is proposed in this study. The method utilizes the histograms which work as a dimensionality reduction algorithm for quantizing the local and global features. The performance of activity recognition is generally depend upon the quantity of significant features but with proper feature quantization one can delivered the same performance with less number of features. The basic characteristics of algorithm are discussed and demonstrated by experiment. It is scalable in nature and work efficiently under varying conditions. In an experiment section, we show that our novel feature quantization approach takes less number of features in compared to standard quantization, while delivering the same performance.