You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
title: 2016-01-05 - ImageScience is moving to an update site
4
4
---
5
5
6
-
Resulting from [a discussion](https://github.com/imagescience/ImageScience/pull/1) with {% include person id='emeijering' %}, the [ImageScience](/plugins/imagescience) plugins have moved to their own dedicated [update site](/update-sites), and will no longer be distributed as part of core [Fiji](/software/fiji).
6
+
Resulting from [a discussion](https://github.com/imagescience/ImageScience/pull/1) with {% include person id='emeijering' %}, the [ImageScience](/libs/imagescience) plugins have moved to their own dedicated [update site](/update-sites), and will no longer be distributed as part of core [Fiji](/software/fiji).
Copy file name to clipboardExpand all lines: _pages/plugins/featurej.md
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -18,6 +18,6 @@ categories: [ImageScience]
18
18
{% endcapture %}
19
19
{% include info-box software='ImageScience' name='FeatureJ' maintainer=maintainer author=author source=source status='' category='[Plugins](/plugin-index)' website='http://imagescience.org/meijering/software/featurej/' %}The [FeatureJ](http://imagescience.org/meijering/software/featurej/) suite of plugins offers extraction of differential features of images.
20
20
21
-
FeatureJ is available from the [ImageScience](/plugins/imagescience) update site.
21
+
FeatureJ is available from the [ImageScience](/libs/imagescience) update site.
Copy file name to clipboardExpand all lines: _pages/plugins/randomj.md
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -18,6 +18,6 @@ categories: [ImageScience]
18
18
{% endcapture %}
19
19
{% include info-box software='ImageScience' name='RandomJ' maintainer=maintainer author=author source=source status='' category='[Plugins](/plugin-index)' website='http://imagescience.org/meijering/software/randomj/' %}The [RandomJ](http://imagescience.org/meijering/software/randomj/) suite of plugins offers sophisticated application of noise to images.
20
20
21
-
RandomJ is available from the [ImageScience](/plugins/imagescience) update site.
21
+
RandomJ is available from the [ImageScience](/libs/imagescience) update site.
Copy file name to clipboardExpand all lines: _pages/plugins/tws/index.md
+9-9Lines changed: 9 additions & 9 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -154,28 +154,28 @@ Each of the 6 resulting images is a feature. Hence pixels in lines of similarly
154
154
-**Lipschitz filter**: from [Mikulas Stencel plugin](/ij/plugins/lipschitz.html). This plugin implements Lipschitz cover of an image that is equivalent to a grayscale opening by a cone. The Lipschitz cover can be applied for the elimination of a slowly varying image background by subtraction of the lower Lipschitz cover (a top-hat procedure). A sequential double scan algorithm is used. We use down and top hats combination, with slope $$s = 5, 10, 15, 20, 25$$.
155
155
-**Kuwahara filter**: another noise-reduction filter that preserves edges. This is a version of the [ Kuwahara filter that uses linear kernels](/plugins/linear-kuwahara) rather than square ones. We use the membrane patch size as kernel size, 30 angles and the three different criteria (Variance, Variance / Mean and Variance / Mean^2).
156
156
-**Gabor filter**: at the moment this option may take some time and memory because it generates a very diverse range of {% include wikipedia title='Gabor filter' text='Gabor filters'%} (**22**). *' This may undergo changes in the future*'. The implementation details are included in this [script](/tutorials/gabor-filter). The Gabor filter is an edge detection and texture filter, which convolves several kernels at different angles with an image. Each point in a kernel is calculated as $$\frac{\cos \left(2\pi f \frac{x_p}{s_x}+\psi \right) e^{-0.5 \left( \frac{x_p^2}{\sigma_x^2} + \frac{y_p^2}{\sigma_y^2} \right)} }{ 2\pi \sigma_x \sigma_y }$$. Gabor filters are band-pass filters and therefore implement a frequency transformation.
157
-
-**Derivatives filter**: calculates high order derivatives of the input image ($$\frac{d^4}{dx^2dy^2},\frac{d^6}{dx^3dy^3},\frac{d^8}{dx^4dy^4},\frac{d^{10}}{dx^5dy^5}$$) using [FeatureJ](/plugins/featurej) (it requires enabling the [ImageScience](/plugins/imagescience) update site in the updater).
158
-
-**Laplacian filter**: computes the Laplacian of the input image using [FeatureJ](/plugins/featurej) (it requires enabling the [ImageScience](/plugins/imagescience) update site in the updater). It uses smoothing scale $$\sigma$$.
159
-
-**Structure filter**: calculates for all elements in the input image, the eigenvalues (smallest and largest) of the so-called structure tensor using [FeatureJ](/plugins/featurej) (it requires enabling the [ImageScience](/plugins/imagescience) update site in the updater). It uses smoothing scale $$\sigma$$ and integration scales 1 and 3.
157
+
-**Derivatives filter**: calculates high order derivatives of the input image ($$\frac{d^4}{dx^2dy^2},\frac{d^6}{dx^3dy^3},\frac{d^8}{dx^4dy^4},\frac{d^{10}}{dx^5dy^5}$$) using [FeatureJ](/plugins/featurej) (it requires enabling the [ImageScience](/libs/imagescience) update site in the updater).
158
+
-**Laplacian filter**: computes the Laplacian of the input image using [FeatureJ](/plugins/featurej) (it requires enabling the [ImageScience](/libs/imagescience) update site in the updater). It uses smoothing scale $$\sigma$$.
159
+
-**Structure filter**: calculates for all elements in the input image, the eigenvalues (smallest and largest) of the so-called structure tensor using [FeatureJ](/plugins/featurej) (it requires enabling the [ImageScience](/libs/imagescience) update site in the updater). It uses smoothing scale $$\sigma$$ and integration scales 1 and 3.
160
160
-**Entropy**: draws a circle of radius $$r$$ around each pixel; gets the histogram of that circle split in numBins chunks; then calculates the entropy as $$\sum_{p~\mathrm{in}~\mathrm{histogram}} -p*\mathrm{log}_2(p)$$, where $$p$$ is the probability of each chunk in the histogram. numBins is equal to $$32, 64, 128, 256$$. $$r$$ is equal to $$\sigma$$.
161
161
-**Neighbors**: shifts the image in 8 directions by an certain number of pixel, $$\sigma$$. Therefore creates $$8n$$ feature images.
162
162
163
163
When using grayscale images, the input image will be also included as a feature. In the case of color (RGB) images, the **Hue, Saturation and Brightness** will be as well part of the features.
164
164
165
165
The detailed implementation of these 2D filters can be found in the [source code](https://github.com/fiji/Trainable_Segmentation/blob/master/src/main/java/trainableSegmentation/FeatureStack.java).
166
166
167
-
**<spanstyle="color:#f80000">NOTE**: The features named *Derivatives*, *Laplacian* and *Structure* belong to the [ImageScience](/plugins/imagescience) suite and need to be activated [by enabling the ImageScience update site in the updater](/update-sites/following).
167
+
**<spanstyle="color:#f80000">NOTE**: The features named *Derivatives*, *Laplacian* and *Structure* belong to the [ImageScience](/libs/imagescience) suite and need to be activated [by enabling the ImageScience update site in the updater](/update-sites/following).
168
168
169
169
##### Training features (3D)
170
170
171
171
{% include thumbnail src='/media/plugins/tws/tws-3d-settings-dialog.png' title='Settings dialog for the Trainable Weka Segmentation 3D plugin.'%}When calling the plugin from the menu command {% include bc path='Plugins | Segmentation | Trainable Weka Segmentation 3D'%} the set of available image features will be as follows:
172
172
173
173
-**Gaussian blur**: performs $$n$$ individual 3D convolutions with Gaussian kernels with the normal $$n$$ variations of $$\sigma$$. The larger the radius the more blurred the image becomes until the pixels are homogeneous.
174
-
-**Hessian**: using [FeatureJ](/plugins/featurej) it computes for each image element (voxel) the eigenvalues of the Hessian, which can be used for example to discriminate locally between plate-like, line-like, and blob-like image structures. More specifically, it calculates the magnitude of the largest, middle and smallest eigenvalue of the Hessian tensor. It requires enabling the [ImageScience](/plugins/imagescience) update site in the updater. It uses smoothing scale $$\sigma$$.
175
-
-**Derivatives**: calculates high order derivatives of the input image ($$\frac{d^4}{dx^2dy^2dz^2},\frac{d^6}{dx^3dy^3dz^3},\frac{d^8}{dx^4dy^4dz^4},\frac{d^{10}}{dx^5dy^5dz^5}$$) using [FeatureJ](/plugins/featurej) (it requires enabling the [ImageScience](/plugins/imagescience) update site in the updater).
176
-
-**Laplacian**: computes the Laplacian of the input image using [FeatureJ](/plugins/featurej) (it requires enabling the [ImageScience](/plugins/imagescience) update site in the updater). It uses smoothing scale $$\sigma$$.
177
-
-**Structure**: calculates for all elements in the input image, the eigenvalues (smallest and largest) of the so-called structure tensor using [FeatureJ](/plugins/featurej) (it requires enabling the [ImageScience](/plugins/imagescience) update site in the updater). It uses smoothing scale $$\sigma$$ and integration scales 1 and 3.
178
-
-**Edges**: detects edges using Canny edge detection, which involves computation of the gradient magnitude, suppression of locally non-maximum gradient magnitudes, and (hysteresis) thresholding. Again, this feature uses [FeatureJ](/plugins/featurej) so it requires enabling the [ImageScience](/plugins/imagescience) update site in the updater. It uses smoothing scale $$\sigma$$.
174
+
-**Hessian**: using [FeatureJ](/plugins/featurej) it computes for each image element (voxel) the eigenvalues of the Hessian, which can be used for example to discriminate locally between plate-like, line-like, and blob-like image structures. More specifically, it calculates the magnitude of the largest, middle and smallest eigenvalue of the Hessian tensor. It requires enabling the [ImageScience](/libs/imagescience) update site in the updater. It uses smoothing scale $$\sigma$$.
175
+
-**Derivatives**: calculates high order derivatives of the input image ($$\frac{d^4}{dx^2dy^2dz^2},\frac{d^6}{dx^3dy^3dz^3},\frac{d^8}{dx^4dy^4dz^4},\frac{d^{10}}{dx^5dy^5dz^5}$$) using [FeatureJ](/plugins/featurej) (it requires enabling the [ImageScience](/libs/imagescience) update site in the updater).
176
+
-**Laplacian**: computes the Laplacian of the input image using [FeatureJ](/plugins/featurej) (it requires enabling the [ImageScience](/libs/imagescience) update site in the updater). It uses smoothing scale $$\sigma$$.
177
+
-**Structure**: calculates for all elements in the input image, the eigenvalues (smallest and largest) of the so-called structure tensor using [FeatureJ](/plugins/featurej) (it requires enabling the [ImageScience](/libs/imagescience) update site in the updater). It uses smoothing scale $$\sigma$$ and integration scales 1 and 3.
178
+
-**Edges**: detects edges using Canny edge detection, which involves computation of the gradient magnitude, suppression of locally non-maximum gradient magnitudes, and (hysteresis) thresholding. Again, this feature uses [FeatureJ](/plugins/featurej) so it requires enabling the [ImageScience](/libs/imagescience) update site in the updater. It uses smoothing scale $$\sigma$$.
179
179
-**Difference of Gaussian**: calculates two {% include wikipedia title='Gaussian blur' text='Gaussian blur'%} images from the original image and subtracts one from the other. $$\sigma$$ values are varied as usual, so $$\frac{n(n-1)}{2}$$ feature images are added to the stack.
180
180
-**Minimum, Maximum, Mean, Variance, Median**: the voxels within a radius of $$\sigma$$ voxels from the target pixel are subjected to the pertinent operation (mean/min etc.) and the target voxel is set to that value.
0 commit comments