IP core name

Input

Output

LINEAR FILTERING
Image noise reduction by convolving the input image with a 2D NxM Gaussian kernel.

MEDIAN FILTERING
Non-linear filtering for removing impulsive (salt and pepper) noise. Each pixel in the image is replaced with the median grey level of its neighborhood

 MORPHOLOGICAL FILTERING
This core provides a set of morphological operators for binary images such as cleaning, dilation, erosion. They can be used in cascade to produce more complex operations.

 GRADIENT EXTRACTION
It extracts the two partial derivatives of the image with Sobel operator and estimates the magnitude and the phase of the gradient.

HISTOGRAM STRETCHING
It enhances the contrast of the image by stretching its histogram in order to exploit the overall range of the gray scale.

 IMAGE SEGMENTATION
It produces a binary map that distinguishes between background and foreground regions. The segmentation threshold is adaptive and computed with respect to the image histogram. The algorithm works under the hypotesis of bimodal image.

 EDGE DETECTION
It computes the edge map of the input image on the basis of the gradient. Thinning is applied to obtain 1-pixel thick contour. The optimal threshold can be automatically estimated by the core analyzing the cumulative histogram of the gradient magnitude.