Method for Character Segmentation of Shopping Receipts of POS Machine
Wu Zheng, Xiang Nian Huang, Ying Yan · Applied Mechanics and Materials · 2014
This paper is focused on multiclass character segmentation for image of shopping receipt from POS machine, especially the Chinese characters. A secondary analysis method based on projection histogram is proposed, where the histogram is regarded as waveform signal, through filtering processing, it is to find trough point for the line segmentation. As for the word segmentation, this paper proposes rules for mergence of Chinese character components to solve issue about segmentation of Chinese characters with left and right components. The experimental results demonstrated that the segmentation accuracy is above 96%.