Enhancing digital cephalic radiography with mixture models and local gamma correction

Abstract

Abstract-We present a new algorithm, called the soft-tissue filter, that can make both soft and bone tissue clearly visible in digital cephalic radiographies under a wide range of exposures. It uses a mixture model made up of two Gaussian distributions and one inverted lognormal distribution to analyze the image histogram. The image is clustered in three parts: background, soft tissue, and bone using this model. Improvement in the visibility of both structures is achieved through a local transformation based on gamma correction, stretching, and saturation, which is applied using different parameters for bone and soft-tissue pixels. A processing time of 1 s for 5 Mpixel images allows the filter to operate in real time. Although the default value of the filter parameters is adequate for most images, real-time operation allows adjustment to recover under-and overexposed images or to obtain the best quality subjectively. The filter was extensively clinically tested: quantitative and qualitative results are reported here.

A new and reliable Poisson noise estimator for radiographic images

“…Although these processes can introduce different kinds of noise, photon counting noise is often considered to be predominant [3], [4], [7]- [9]. However, the likelihood function (7) can be easily extended to mixtures of different noises: for instance, quantization, impulsive or additive Gaussian noise could also be considered beyond the photon counting one [15].…”

“…Different types of noise can be accommodated inside (6), by substituting P(b n,j |b), with an adequate additive mixture of the noise probability densities [15].…”

A new real time filter for local exposure correction in panoramic radiographs

“…where p͑x͒ is the probability of the gray level x to occur in the image. 20 A decrease of H after filtering is interpreted as a loss of information, since the image can be encoded using a smaller number of bits. On the other hand, an increase of H can be associated to the introduction of artifacts, which add new, spurious information to the image.…”

Adaptive Segmentation based on a Learned Quality Metric

“…Segmentation represents a key processing step in many applications, ranging from medical imaging (Sun, 2013;Frosio, 2006;Achanta, 2012) to machine vision (Sungwoong, 2013;Alpert, 2012) and video compression (Bosch, 2011). Segmentation algorithms aggregate sets of perceptually similar pixels in an image (Achanta, 2012;Kaufhold, 2004).…”