Reducing noise in digital images

1. An apparatus comprising

a device to acquire target digital images (T) of skin lesions on patients, and

a software processing facility to:

for each of at least some of the pixels in each of the target digital images (T), determine an unknown amplitude (A) of noise that contaminates at least some of the pixels of the target digital image, the amplitude being possibly different in different ones of the target digital images, the determination being based on the target digital image and on a reference digital image that is representative of the contaminating noise and is obtained by the same sensor,

the determination being made from a decorrelation condition: Correlation (T−A*{the reference digital image}, {the reference digital image})=0,

the determination being made over pixels in some regions of the target digital image and the reference digital image, to estimate the amplitude of the noise for each of at least some pixels of T,

produce a noise reduced version of the target digital image using the determined noise amplitudes A of the pixels,

analyze features of the noise reduced version of the target digital image,

determine a malignancy state of the lesion based on the analysis, and

report the malignancy state to a user of the apparatus.

2. The apparatus of claim 1 in which the device comprises a CMOS sensor.

3. The apparatus of claim 1 in which the device comprises a CCD sensor.

4. The apparatus of claim 1 in which the noise comprises dark current noise.

5. The apparatus of claim 1 also including providing the noise reduced target digital image to a processor for use in analyzing features of an image captured by the sensor.

6. The apparatus of claim 5 in which the images include possibly malignant lesions.