Identification of acne lesions, scars and normal skin for acne vulgaris cases

Acne affects 85% of adolescents at some time during their lives. There are various causes for acne including genetic, hormonal, sebaceous activity, bacteria, climate, chemical and psychological. Till now, dermatologists use manual methods such as direct visual assessment and ordinary flash photography to assess the acne. These methods are very time consuming and tedious. To address these issues, researchers in recent years have proposed computational imaging methods for aiding in the acne diagnosis. This paper proposes an algorithm to identify acne lesions, scars and normal skin features from photographs taken by Digital Single-Lens Reflex (DSLR) cameras. The images are converted from RGB to CIELAB color space, thresholded to three clusters and segmented using minimum Euclidean distance. The segmentation results from randomly selected images show sensitivity and specificity of greater than 80%.