A region proposal approach for cells detection and counting from microscopic blood images

In this paper, we propose a novel and efficient method for detecting and quantifying red cells from a microscopic blood image. The proposed system is based on a region proposal approach, namely the Edge Boxes, considered as the state-of-art region proposal method. Incorporating knowledge-based constraints into the detection process by Edge Boxes we can find cells proposals rapidly and efficiently. Experimental results on a well-known public dataset show both improved accuracy and increased over the state-of-art.