Transitional appearance-based motion tracking for real-time breast self-examination supervision.

Despite much research and clinical trials, breast cancer still presents a serious threat of premature death to women. Early detection of the lumps in the breast is a key contributing factor to the successful treatment of this potentially fatal disease. Performing breast self-examination (BSE) in an accurate manner can assist a woman in detecting any abnormalities in her breasts, which may mark the onset of potential disease. This is also an essential tool used to enhance breast awareness. Using the hand, in a specific configuration, and palpating the entire breast in a certain movement pattern can optimise her feeling of the breast, In this paper we describe an intelligent automated algorithm for tracking the finger pads of a moving hand with the movement videos captured by a common web camera. The algorithm employs the principle of HCRA (hand configuration recognition algorithm) and its refinement through a simple but novel transitional appearance-based model. A novel hand motion recognition algorithm (HMRA) is developed to recognise the motion pattern. Desirable tracking and recognition results have been achieved and the robustness of this algorithm is demonstrated in this paper.

Hand motion segmentation against skin colour background in breast awareness applications.

Skin colour modelling and classification play significant roles in face and hand detection, recognition and tracking. A hand is an essential tool used in breast self-examination, which needs to be detected and analysed during the process of breast palpation. However, the background of a woman's moving hand is her breast that has the same or similar colour as the hand. Additionally, colour images recorded by a web camera are strongly affected by the lighting or brightness conditions. Hence, it is a challenging task to segment and track the hand against the breast without utilising any artificial markers, such as coloured nail polish. In this paper, a two-dimensional Gaussian skin colour model is employed in a particular way to identify a breast but not a hand. First, an input image is transformed to YCbCr colour space, which is less sensitive to the lighting conditions and more tolerant of skin tone. The breast, thus detected by the Gaussian skin model, is used as the baseline or framework for the hand motion. Secondly, motion cues are used to segment the hand motion against the detected baseline. Desired segmentation results have been achieved and the robustness of this algorithm is demonstrated in this paper.