Noise Measurement for Raw-Data of Digital Imaging Sensors by Automatic Segmentation of Nonuniform Targets

In this paper, we present a new method for measuring the temporal noise in the raw-data of digital imaging sensors [e.g., CMOS and charge-coupled device (CCD)]. The method is specially designed to estimate the variance function which describes the signal-dependent noise found in raw-data. It gives the standard-deviation of the noise as a function of the expectation of the pixel raw-data output value. In contrast with established methods (such as the ISO 15739), our method does not require the use of a specific target or a particular calibration. This is possible due to an automatic segmentation embedded in the data analysis. We show experimental results for the raw-data from two different CMOS sensors of commercial cameraphones.