摘要：Many Text Extraction methodologies have been proposed, but none of them are suitable to be part of a real system implemented on a device with low computational resources, either because their accuracy is insufficient, or because their performance is too slow. In this sense, we propose a Text Extraction algorithm for the context of language translation of scene text images with mobile phones, which is fast and accurate at the same time. The algorithm uses very efficient computations to calculate the Principal Color Components of a previously quantized image, and decides which ones are the main foreground-background colors, after which it extracts the text in the image. We have compared our algorithm with other algorithms using commercial OCR, achieving accuracy rates more than 12% higher, and performing two times faster. Also, our methodology is more robust against common degradations, such as uneven illumination, or blurring. Thus, we developed a very attractive system to accurately separate foreground and background from scene text images, working over low computational resources devices.
关键词：Text Extraction; Color Quantization; Text Binarization; Language Translation
