Sickle cell anemia is an inherited disorder of the red blood cells in which there is an insufficient number of healthy red blood cells to transport oxygen effectively throughout the body. When observed under a microscope, the blood cells of an individual with sickle cell anemia exhibit a crescent or sickle-like shape. Image segmentation and classification techniques are necessary for detecting sickle cell anemia from microscopic images. Segmentation of the images is performed to distinguish between healthy and sickle (unhealthy) red blood cells. A mask of the microscopic image is first generated, which aids in the classification of cells. The mask generated is then further classified into circular, elongated and other cells, with the help of image processing. The erythrocytesIDB dataset is used for the detection of cells, which was provided by Universitat de les Illes Balears and available at http://erythrocytesidb.uib.es/. Upon the successful classification of cells into their respective types, it is concluded that circular cells are representative of healthy red blood cells, whereas elongated cells are characteristic of sickle cells. However, cells classified as "others" are indeterminate, and their association with sickle cells is uncertain, hence presenting a degree of ambiguity. In terms of performance evaluation, the proposed method achieved an accuracy of 94.907% in cell classification.