Digital Image Processing By a Parallel Selective Model

The digital image processing has been used on many research segments as an instrument for pattern recognition and image filtering. However, depending on the image size and filtering type, the response time can take forever. In this context, this work shows a parallel selective model of a digital image processing algorithm. Two selection and three estimation policies are proposed in conjunction with the algorithm. The basic idea is to select the pixels that will be processed and reduce the execution time even if there is an acceptable loss of quality. The results confirm the advantages of the parallel selective model where the performance reaches 6.39 and the efficiency 80% in the cases evaluated in this work.