Hodgkin's disease is a cancer of the lymphatic system, which is part of the immune system. For an accurate diagnosis, a pathologist examines a slide of a sample of lymph node tissue stained with hematoxylin and eosin to find a tumoral cell called Reed-Sternberg cell. The diagnosis is subjective and prone to inter/intra-observer variations. Furthermore, it is a time-consuming task. Therefore, there is a necessity to provide an automatic system for better diagnosis and detection. In this paper, a method for identifying Reed-Sternberg cell nuclei in histopathological images of lymph nodes stained with (H&E) is presented. In the preprocessing stage, noise and annoying structures are removed. Then, we identify RS cell nuclei using three different segmentation algorithms based on morphological, color, and textural features. Using the Chan-Vese Active Contour model, we find the exact boundary of the RS cell nuclei in the histopathological image and distinguish them from other objects in the image with high accuracy. The proposed scheme is tested on an actual dataset containing 98 Reed-Sternberg cell images. The experiments' results show a high correlation between the results of the proposed algorithm and the ground-truth described by the pathologists. Moreover, a comparative study with other cell nuclei segmentation methods on histopathological images demonstrates the proposed method's efficiency. It gives the highest average accuracy rate (93.80 %) compared to recent approaches.