This paper proposes an efficient content adaptive screen image scaling schemefor the real-time screen applications like remote desktop and screen sharing.In the proposed screen scaling scheme, a screen content classification step isfirst introduced to classify the screen image into text and pictorial regions.Afterward, we propose an adaptive shift linear interpolation algorithm topredict the new pixel values with the shift offset adapted to the content typeof each pixel. The shift offset for each screen content type is offlineoptimized by minimizing the theoretical interpolation error based on thetraining samples respectively. The proposed content adaptive screen imagescaling scheme can achieve good visual quality and also keep the low complexityfor real-time applications.
展开▼