Support vector machine and morphological processing algorithm for red blood cell identification

Hyperspectral imaging is an emerging imaging modality for medical applications. It provides more information than traditional optical image for owning two spatial dimensions and one spectral dimension. Multi dimension information of hyperspectral images can be used to classify different tissues and cells, while it’s difficult to distinguish them by traditional methods. The processing method presented in this paper is composed of two main blocks: Support Vector Machine (SVM) algorithm is adopted to identify different components of blood cells through the spectral dimension. In order to make it easy for blood cell counting, some morphological processing methods are used to process images through the spatial dimensions. This strategy, applying SVM and morphological processing methods, has been successfully tested for classifying objects among erythrocytes, leukocytes and serums in raw samples. Experimental results show that the proposed method is effective for red blood cells identification.