Wounds that do not follow a predictable course of healing within a specified period of time develop into ulcers causing severe pain and discomfort to the patients. One of the most prominent changes during wound healing is the colour of the tissues. Describing the tissues in terms of percentages of each tissue colour is an approved clinical method of wound healing assessment. The growth of the red granulation tissue marks the beginning of ulcer healing. Granulation tissue appears red in colour due to haemoglobin content in the blood capillaries. An approach based on utilizing haemoglobin content in chronic ulcers as an image marker to detect the growth of granulation tissue is investigated in this study. Independent Component Analysis is employed to extract grey-level haemoglobin images from RGB colour images of chronic ulcers. Extracted haemoglobin images indicate areas of haemoglobin distribution reflecting detected regions of granulation tissue. Data clustering techniques are implemented to classify and segment detected regions of granulation tissue from the extracted haemoglobin images. Results obtained indicate that the developed algorithm performs fairly well with an average sensitivity of 88.24 and specificity of 98.82 when compared to the dermatologist's assessment. The ultimate aim of this research work is to develop an objective non-invasive wound healing assessment system capable of evaluating the healing status of chronic ulcers in a more precise and reliable way. © 2012 IEEE.