| 摘要 |
A method and apparatus for enhancing a digital image. First, human faces are located within a digital image. The digital image is then analyzed, including analysis of the regions determined to be human faces and the analysis of the digital image as a whole. A tone mapping function is then determined for enhancing the image quality of the digital image. The tone mapping function is determined using both the analysis of detected faces and the analysis of the image as a whole to obtain a tone mapping function that incorporates both psychological factors (e.g., average face region lightness and average picture lightness) and signal factors (e.g., digital resolution, face region contrast, histogram uniformity, and noise issue). The tone mapping function is then applied to the digital image so as to produce an enhanced digital image. The present invention is automatic and does not require that the user provide any input. In addition, because the method and apparatus of the present invention incorporates both psychological factors and signal factors, the resulting enhanced images are perceived to be of good image quality.
|
