FFT Plugin Performs 2D Fast Fourier Transform of images of any dimension
(MIT's FFTW based, with source code). User can extend the plugin to develop frequency domain filters.

This link describes how the FFTW version 3.0.1 based Plugin for Image Apprentice works. For this, I have developed an easy to use wrapper class around FFTW named CFFTWWrapper. At the time of writing, the latest version of Image Apprentice available is version 0.5.0.3.

Gamma Correction is used to compensate for non-linearities in imaging systems, in particular those of CRTs in TV, computer displays & photography.

Histogram equalization is used to enhance local contrast i.e. in images with bright backgrounds and bright foregrounds, or dark backgrounds and dark foregrounds.

Maximum Filter is used to eliminate the pepper grain noise from the image, comparing gray levels of the pixel with its neighbouring pixels in the mask.

Minimum Filter is used to eliminate the salt grain noise from the image, comparing gray levels of the pixel with its neighbouring pixels in the mask.

This filter reduces noise in an image. It compares each pixel with its neighbours in the mask and if the pixel is larger or smaller in value than all , replaces it by the largest or smallest of the neighbours. This is good for removing single noisy pixels from an image.

Sepia is a color dark grayish yellow brown to dark or moderate olive brown in tone. This plugin converts an RGB image to Sepia in 2 steps (RGB > Greyscale > Sepia). This is one among a couple of acceptable Sepia conversion routines.

At times it is desired to get the contribution of individual bits made to the total image. Bit Plane Slicing Plugin for Image Apprentice does the same wherein the user can choose one or more among the 8 bits for each grey value(or RGB channel) to see the contribution by the chosen bits.

Average Filter Plugin for Image Apprentice replaces the value of every pixel in an image by the average of the gray levels in the n*n neighborhood.

Averaging Filter is used for blurring and for noise reduction. Blurring is used in preprocessing steps, such as removal of small details from an image prior to object extraction and bridging of small gaps in lines or curves.

In image processing, lookup tables are often called LUTs, and they link index numbers to output values. One common LUT, called the colormap, is used to determine the colors and intensity values with which a particular image will be displayed.
This Plugin loads an LUT over an RGB Image. Included in the download is a set of existing LUTs (link: http://rsb.info.nih.gov/ij/download/luts/) in a separate folder.

The median filter is non-linear spacial filter, normally used to reduce noise (particularly effective in salt and pepper noise) in an image. It is implemented by replacing the pixel by median of the grey levels (separately on RGB channels in case of color images) in the neighbourhood. Current implementation doesn't handle even numbered mask size.

Thresholding is the simplest and most commonly used method of segmentation (division of an image into regions or categories which correspond to different objects). Given a single threshold, 't', the pixel located at (i,j) with greyscale value f(i,j) is allocated to category 1 if f(i,j) < t. Otherwise, the pixel is allocated to category 2.

This plugin for Image Apprentice implements 3 different thresholding techniques - Iso-Data, Otsu and Triangle Symmetry.

Halftoning is the transformation of a grayscale or color image to a pattern of small spots with a limited number of colors (e.g. just black spots on white background), in order to make it printable.

This implementation uses the Floyd-Steinberg Error Diffusion Algorithm.

This plugin extends the MIT's FFTW based plugin by D. Rathore to implement a Gaussian High Pass Filter. It demonstratess how to perform convolution in Frequency Domain.

A high-pass filter is a filter that passes high frequencies well, but attenuates (or reduces) frequencies lower than the cutoff frequency [Reference: Wikipedia]. High values of the input parameter (distance from the origin/center) result in edge detection.

Canny edge detection uses linear filtering with a gaussian kernel to smooth the noise and then computes the edge strength and direction for each pixel in the smoothed image. This is done by dividing the image in two orthogonal directions. The Canny edge detector asks the user to input three parameteres : SIGMA, Threshold (LOW) and Threshold (HIGH).

Reference: http://marathon.csee.usf.edu/edge/edge_detection.html ; M. Heath, S. Sarkar, T. Sanocki, and K.W. Bowyer, "A Robust Visual Method for Assessing the Relative Performance of Edge-Detection Algorithms" IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 19, No. 12, December 1997, pp. 1338-1359.

This plugin discusses Clustering-based methods, where the gray-level samples are clustered in two parts as background and foreground object, or alternately are modeled as a mixture of two Gaussians. It discusses Riddler Thresholding, Yanni Thresholding, Otsu Thresholding and Kittler Algorithms (see code and pdf link for details). Reference: www.busim.ee.boun.edu.tr/~sankur/SankurFolder/Threshold_survey.pdf ; Mehmet Sezgin and Bülent Sankur, "Survey over image thresholding techniques and quantitative performance evaluation" Journal of Electronic Imaging 13(1), 146–165 (January 2004).

This plugin covers Morphological Operations, namely, Erode, Dialate, Opening and Closing. It further utilizes these operations to demonstrate Interior and Exterior Outlines of regions. Sobel and Prewitt Edge Detectors are also covered.