An Energy Efficient Binarization Algorithm Based on 2-D Intelligent Block Detection for Complex Texture and Gradient Color Images

Image binarization involves converting gray-level images into binary ones, which has significantly impacted on intelligent portable devices in recent years. Given the limited memory space and computational power of portable devices, reducing the computational complexity of algorithms which work on embedded systems is of priority concern. This paper proposes a 2-D intelligent block detection algorithm with more accurate region segmentation for document image binarization. By combining merits of global and local algorithms, the proposed approach provides an effective outcome and a low computational cost. As demonstrated by the experimental results, the proposed algorithm is slower than Otsu's method but 275 times faster than local methods.