Displaying Eigenfaces with negative values - image-processing

After implementing the Eigenfaces algorithm for python using numpy, I noticed that the normalized eigenvectors contained negative values. How are these negative values represented when the eigenface is displayed as an image, like this? I thought that images consisted of positive intensity values. Are these eigenface images generated by histogram equalization on the eigenvector?

The plotting of negative values depends on the implementation of the plotting function. Matlab's imagesc, for example, scales image data to the full range of the current colormap and displays the image. This is simpler than histogram equalization.

Yes, for visualization purposes, just map min(eigenface) to 0 and max(eigenface) to 255. Your linked image appears to be doing that. (Note how each eigenface occupies the full dynamic range.)
Eigenfaces (or eigenvectors, in general) will likely have positive and negative elements.

Related

What's the theory behind computing variance of an image?

I am trying to compute the blurriness of an image by using LaplacianFilter.
According to this article: https://www.pyimagesearch.com/2015/09/07/blur-detection-with-opencv/ I have to compute the variance of the output image. The problem is I don't understand conceptually how do I compute variance of an image.
Every pixel has 4 values for every color channel, therefore I can compute the variance of every channel, but then I get 4 values, or even 16 by computing variance-covariance matrix, but according to the OpenCV example, they have only 1 number.
After computing that number, they just play with the threshold in order to make a binary decision, whether the image is blurry or not.
PS. by no means I am an expert on this topic, therefore my statements can make no sense. If so, please be nice to edit the question.
On sentence description:
The blured image's edge is smoothed, so the variance is small.
1. How variance is calculated.
The core function of the post is:
def variance_of_laplacian(image):
# compute the Laplacian of the image and then return the focus
# measure, which is simply the variance of the Laplacian
return cv2.Laplacian(image, cv2.CV_64F).var()
As Opencv-Python use numpy.ndarray to represent the image, then we have a look on the numpy.var:
Help on function var in module numpy.core.fromnumeric:
var(a, axis=None, dtype=None, out=None, ddof=0, keepdims=<class 'numpy._globals$
Compute the variance along the specified axis.
Returns the variance of the array elements, a measure of the spread of a distribution.
The variance is computed for the flattened array by default, otherwise over the specified axis.
2. Using for picture
This to say, the var is calculated on the flatten laplacian image, or the flatted 1-D array.
To calculate variance of array x, it is:
var = mean(abs(x - x.mean())**2)
For example:
>>> x = np.array([[1, 2], [3, 4]])
>>> x.var()
1.25
>>> np.mean(np.abs(x - x.mean())**2)
1.25
For the laplacian image, it is edged image. Make images using GaussianBlur with different r, then do laplacian filter on them, and calculate the vars:
The blured image's edge is smoothed, so the variance is little.
First thing first, if you see the tutorial you gave, they convert the image to a greyscale, thus it will have only 1 channel and 1 variance. You can do it for each channel and try to compute a more complicated formula with it, or just use the variance over all the numbers... However I think the author also converts it to greyscale since it is a nice way of fusing the information and in one of the papers that the author supplies actually says that
A well focused image is expected to have a high variation in grey
levels.
The author of the tutorial actually explains it in a simple way. First, think what the laplacian filter does. It will show the well define edges here is an example using the grid of pictures he had. (click on it to see better the details)
As you can see the blurry images barely have any edges, while the focused ones have a lot of responses. Now, what would happen if you calculate the variance. let's imagine the case where white is 255 and black is 0. If everything is black... then the variance is low (cases of the blurry ones), but if they have like half and half then the variance is high.
However, as the author already said, this threshold is dependent on the domain, if you take a picture of a sky even if it is focus it may have low variance, since it is quite similar and does not have very well define edges...
I hope this answer your doubts :)

Kmeans clustering on different distance function in Lab space

Problem:
To cluster the similar colour pixels in CIE LAB using K means.
I want to use CIE 94 for distance between 2 pixels
Formula of CIE94
What i read was Kmeans work in "Euclidean space" where the positional cordinates are minimised by cost function which is (sum of squared difference)
The reason of not Using kmeans in space other than euclidean is
"""algorithm is often presented as assigning objects to the nearest cluster by distance. The standard algorithm aims at minimizing the within-cluster sum of squares (WCSS) objective, and thus assigns by "least sum of squares", which is exactly equivalent to assigning by the smallest Euclidean distance. Using a different distance function other than (squared) Euclidean distance may stop the algorithm from converging""(source wiki)
So how to use distance CIE 94 in LAB SPACE for similar colour clustering ?
So how to approach the problem ? What should be the minimisation function here ? HOW to map euclidean space to lab space if for the k mean euclidean formula to work ? Any other approach here ?
The reason that CIE LAB is often used for clustering is because it reduces the color to 2 dimensions (as opposed to RGB with 3 color channels). You can easily think of the color for each pixel in a Cartesian coordinate system, instead of points (x,y) you have points (a,b) From here you simply perform a 2d kmeans.
Exactly how you implement kmeans is up to you. The nice thing about reducing colors to a 2d space is we can imagine the data on a grid, and now we can use any regular distance measure we want. Mahalonobis, euclidean, 1 norm, city block, etc. The possibilities are really endless here.
You don't have to use CIELAB, you can just as easily use YCbCr, YUV, or any other colorspace that represents color in 2 dimensions. IF you wanted to try a 3d kmeans you could use rgb, hsv, etc. One problem with higher dimensionality is sparsity of clusters (large variance) and most importantly, increased computation time.
Just for fun I've included two images clustered using kmeans, one in LAB and one in YCbCr, you can see the clustering is nearly identical (except that the labels are different), just proving that the exact color space is irrelevant, the main point is to match the dimensionality of your kmeans with that of your data
EDIT
You made some good points in your comments. I was merely demonstrating that by abstracting the problem you can imagine many variations for the same basic clustering algorithm. But you are right, there are advantages to using CIELAB
Back to the distance measure. Kmeans has two steps, assignment, and update (it is very similar to the Expectation Maximization algorithm). This distance is used in assignment step of k-means. Here is some psuedo code
for each pixel 1 to rows*cols
for each cluster 1 to k
dist[k] = calculate_distance(pixel, mu[k])
pixel_id = index k of minimum dist
you would create a function calculate_distance that uses the delta_e calculation from cielab94. This formula uses all 3 channels to calculate distance. Hopefully this answers your questions
NOTE
My examples only use the 2 color channels, ignoring the luminance channel. I used this technique since often the goal is group colors despite lighting disparities(such as shadows). The delta_E measure is not lighting invariant. This may or may not be a concern for your application, but it is something to keep in mind.
results using square euclidean distance
results using cityblock distance
There are k-means variations for other distance functions.
In particular k-medoids (PAM) works with arbitrary distance functions.

Find input image (ID,passport) in imagesDB based on similarity

I would like to decide if an image is present in a list stored in a DB (e.g. pictures of IDs, passport, Stu. card, etc). I thought about using a KNN algorithm, that will plot the K closest images.
Options for distance metric:
sum of Euclidean distance between each relative pixels (img1[pixel_i], img2[pixel_i])
sum of Euclidean distance betwen each pixel to each other, multiplied by some factor decreasing with distance (pixel to pixel)
same as above, but with manhattan...
Do you know/think of a better way to deal with the image similarity subject?
I think that using raw graylevel values in computing distances is a very bad idea. This is not invariant to illumination, to translation and to rotation (although I don't think that rotation is a big issue in face images).
Try to use some robust and invariant descriptor extracted from each image (e.g. SIFT on keypoints) and then compute distances between those features. K-NN could work. Alternatively, look for image retrieval literature for more advanced approaches.
Hope this helps!
If you have a large number of images in your database, it will get rather unwieldy calculating the similarity between a given image and every single image in your database every time. Instead, I would consider something like a Perceptual Hash (pHash) where you could pre-compute a parameter ONCE for each image in your database and store it, and then , when you want to compare an image you calculate just its single pHash and compare that with all the stored ones in your database.

Is "color quantization" the right name for color quantization in OpenCV?

I'm looking for a way to get a complete list of all the RGB values for each pixel in a given image using OpenCV, now i call this "color quantization".
The problem is that according to what I have found online, at least at this point, this "color quantization" thing is about histograms or "color reduction" or similar discrete computation solutions.
Since I know what I want and the "internet" seems to have a different opinion about what this words mean, I was wondering: maybe there is not a real solution for this ? a workable way or a working algorithm in the OpenCV lib.
Generally speaking, quantization is an operation that takes an input signal with real (mathematical) values to a set of discrete values. A possible algorithm to implement this process is to compute the histogram of the data, then retaining the n values that correspond to the n bins of the histogram with the higher population.
What you are trying to do would be called maybe color listing.
If you ar eworking with 8 bits quantized images (type CV_8UC3), my guess is that you do what you desire by taking the histogram of the input image (bin width equal to 1) then searching the result for non-empty bins.
Color quantization is the conversion of infinite natural colors in the finite digital color space. Anyway to create a full color 'histogram' you can use opencv's sparse matrix implementation and write your own function to compute it. Of course you have to access the pixels one by one, if you have no other structural or continuity information about the image.

Noise reduction using histograms in opencv

I want to implement a simple noise correction scheme for RGB images. The image contain some garbage pixels at random locations. So, I am thinking of doing this:
Segment the image.
Calculate histograms for each segment.
Analyze the histogram and dump the pixels which are negligible in histogram distribution over a segment.
I am using openCV. I have implemented steps 1 and 2, but I am not able to find out the number of pixels in each histogram bin. Please help
In order to analyze a histogram, you have to make a few assumptions about it. One good assumption is that the histogram will be roughly modeled as noise + gaussian bell curves.
Check this out.
http://en.wikipedia.org/wiki/Root-finding_algorithm
Finding the roots of the derivative function of the histogram will give you the location of the peaks. You can then find the boundaries of each peak, possibly by finding the roots of the second derivative function.
After you identify the location and span of the histogram peaks, you can classify pixels as being signal or noise pixels.

Resources