Abstract Skin cancer is the type of cancer with the highest incidence in the world. The alterations of temperature in the skin are organic indicators of the presence of several types of skin cancer, mainly squamous cell carcinomas and melanomas. In this work, thermographic images of lesions of this type were analyzed in order to find indicators of the presence of this neoplasm that allow the future development of a detection algorithm. The digital processing used consists of identification of areas of interest, color segmentation, quantitative discrimination according to color tonality and analysis by histograms. The results showed that lesions with skin cancer have values in the red component above 100 under the RGB color space on a scale of 0 to 255. Also, when segmenting, by the k-means algorithm, a thermography containing a melanoma, the area that contains the lesion has a higher average value in the red component with respect to the other areas. Taking these results into account, a non-invasive tool for prediagnosing skin cancer can be developed that reduces unnecessary clinical procedures and simplifies the diagnosis.