I have an image of a glossy surface:
My goal is to detect anomalies on that image. The same image with marked anomalies I show you here:
As we can see from images above, anomalies have bad contrast (or at least not the best), and they are also changing from image to image by their shape, contrast, orientation...
I was trying to increase anomalies contrast by using tophat filtering. The result is here:
Now I anomalies are much more visible on the image, I want to segment them out from the image. The aim is to binarize image and use connectedComponents function to calculate areas, dimensions, positions of anomalies...
What kind of segmentation do you suggest? What would be the best way to binarize image? Should I even use tophat filtering to increase anomalies contrast or should I try to segment anomalies directly from first image?
You can:
try several top hat filters of different sizes and parameters, to see which one highlights the anomalies best while suppressing the finger prints.
or
go directly to thresholding and adjust parameters there to make sure that none of the anomalies are lost in the process. Then use the features of connected components to extract the actual anomalies.
An increasingly popular approach is to train a deep neural network using lots of images of anomalies and then using the network to identify them.
Related
I am trying to do image alignment like posted on adrian blog like this image or in this link.
I want to do image alignment on this kind of image. The problem is I want to automatically detect the 4 point edges which are hard to detect in this kind of images with contour detection like in the tutorial.
Now I can do alignment just fine with manually input edge coordinates. Some of my friends suggest me to detect the edges with dlib landmark detection, but as far as I can see it mostly uses shape in which dlib automatically marking the landmark.
Do I miss something here? Or is there any tutorial or even basic guide about how to do that?
Maybe you can try to detect edges on a Gaussian pyramid. You can find an explanation here https://en.wikipedia.org/wiki/Pyramid_(image_processing). The basic idea is that by filtering with Gaussian filters of increasing size, the small objects are blurred. Thus at some scale, we get only edges of the showcase (maybe need further processing).
Here is the tutorial of opencv on image pyramid: https://opencv-python-tutroals.readthedocs.io/en/latest/py_tutorials/py_imgproc/py_pyramids/py_pyramids.html.
I think wavelet pyramid (do wavelet transform several times) may work for your problem, since wavelet can reduce the details in image.
My objective is to recognize the footprints of buildings on aerial photos. Having heard about recent progress in machine vision (ImageNet Large Scale Visual Recognition Challenges) I though I could (at least) try to use neural networks for this task.
Can anybody give me the idea what should be the topology of such a network? I guess it should have as many outputs as inputs (which means all the pixels in picture) since I want to recognize the outlines of buildings with their (at least approximate) placement on the picture.
I guess the input pictures should be of standard size, with each pixel normalized to grey scale or YUV color space (1 value per color) and maybe normalized resolution (each pixel should represent fixed size in reality). I am not sure if the picture could be preprocessed in any other way before inputting into net, maybe by extracting the edges first?
The tricky part is how the outputs should be represented and how to train the net. Using just e.g. output=0 for the pixel within building footprint and 1 for the pixel outside of it, might not be the best idea. Maybe I should teach the network to recognize edges of the building instead so the pixels which represent building edges should have 1's and 0's for the rest of pixels?
Can anybody throw in some suggestions about network topology/inputs/outputs formats?
Or maybe this task is hopelessly difficult and I have 0 chances to solve it?
I think we need a better definition of "buildings". If you want to do building "detection", that is detect the presence of a building of any shape/size, this is difficult for a cascade classifier. You can try the following, though:
Partition a set of known images to fixed-size blocks.
Label each block as "building", "not building", or
"boundary(includes portions
of both)"
Extract basic features like intensity histograms, edges,
hough lines, HOG, etc.
Train SVM classifiers based on these features (you can try others, too, but I recommend SVM by experience).
Now you can partition your images again and use the trained classifier to get the results. The results will have to be combined to identify buildings.
This will still need some testing to get the parameters(size of histograms, parameters of SVM classifier etc.) right.
I have used this approach to detect "food" regions on images. The accuracy was below 70%, but my guess is that it will be better for buildings.
I am doing a project on face recognition, for that I have already used different methods like eigenface, fisherface, LBP histograms and surf. But these methods are not giving me an accurate result. Surf gives good matches for exact same images, but I need to match one image with it's own different poses(wearing glasses,side pose,if somebody is covering his face) etc. LBP compares histogram of images, i.e., only color informations. So when there is high variation on lighting condition it is not showing good results. So I heard about neural networks, but I don't know much about that. Is it possible to train the system very accurately by using neural networks. If possible how can we do that?
According to this OpenCV page, there does seem to be some support for machine learning. That being said, the support does seem to be a bit limited.
What you could do, would be to:
User OpenCV to extract the face of the person.
Change the image to grey scale.
Try to manipulate so that the face is always the same size.
All the above should be doable with OpenCV itself (could be wrong, haven't messed with OpenCV in a while) so that should save you some time.
Next, you take the image, as a bitmap maybe, and feed the bitmap as a vector to the neural network. Alternatively, as #MatthiasB recommended, you could feed the features instead of individual pixels. This would simplify the data being passed, thus making the network easier to train.
As for training, you manipulate these images as above, and then feed them to the network. If a person uses glasses occasionally, you could have cases of the same person with and without glasses, etc.
Some background:
Hi all! I have a project which involves cloud imaging. I take pictures of the sky using a camera mounted on a rotating platform. I then need to compute the amount of cloud present based on some color threshold. I am able to this individually for each picture. To completely achieve my goal, I need to do the computation on the whole image of the sky. So my problem lies with stitching several images (about 44-56 images). I've tried using the stitch function on all and some subsets of image set but it returns an incomplete image (some images were not stitched). This could be because of a lack of overlap of something, I dunno. Also the output image has been distorted weirdly (I am actually expecting the output to be something similar to a picture taken by a fish-eye lense).
The actual problem:
So now I'm trying to figure out the opencv stitching pipeline. Here is a link:
http://docs.opencv.org/modules/stitching/doc/introduction.html
Based on what I have researched I think this is what I want to do. I want to map all the images to a circular shape, mainly because of the way how my camera rotates, or something else that has uses a fairly simple coordinate transformation. So I think I need get some sort of fixed coordinate transform thing for the images. Is this what they call the homography? If so, does anyone have any idea how I can go about my problem? After this, I believe I need to get a mask for blending the images. Will I need to get a fixed mask like the one I want for my homography?
Am I going through a possible path? I have some background in programming but almost none in image processing. I'm basically lost. T.T
"So I think I need get some sort of fixed coordinate transform thing for the images. Is this what they call the homography?"
Yes, the homography matrix is the transformation matrix between an original image and the ideal result. It warps an image in perspective so it can fit in stitching to the other image.
"If so, does anyone have any idea how I can go about my problem?"
Not with the limited information you provided. It would ease the problem a lot if you know the order of pictures (which borders which.. row, column position)
If you have no experience in image processing, I would recommend you use a tutorial covering stitching using more basic functions in detail. There is some important work behind the scenes, and it's not THAT harder to actually do it yourself.
Start with this example. It stitches two pictures.
http://ramsrigoutham.com/2012/11/22/panorama-image-stitching-in-opencv/
I have images that I am using for a computer vision task. The task is sensitive to image quality. I'd like to remove all images that are below a certain threshold, but I am unsure if there is any method/heuristic to automatically detect images that are heavily compressed via JPEG. Anyone have an idea?
Image Quality Assessment is a rapidly developing research field. As you don't mention being able to access the original (uncompressed) images, you are interested in no reference image quality assessment. This is actually a pretty hard problem, but here are some points to get you started:
Since you mention JPEG, there are two major degradation features that manifest themselves in JPEG-compressed images: blocking and blurring
No-reference image quality assessment metrics typically look for those two features
Blocking is fairly easy to pick up, as it appears only on macroblock boundaries. Macroblocks are a fixed size -- 8x8 or 16x16 depending on what the image was encoded with
Blurring is a bit more difficult. It occurs because higher frequencies in the image have been attenuated (removed). You can break up the image into blocks, DCT (Discrete Cosine Transform) each block and look at the high-frequency components of the DCT result. If the high-frequency components are lacking for a majority of blocks, then you are probably looking at a blurry image
Another approach to blur detection is to measure the average width of edges of the image. Perform Sobel edge detection on the image and then measure the distance between local minima/maxima on each side of the edge. Google for "A no-reference perceptual blur metric" by Marziliano -- it's a famous approach. "No Reference Block Based Blur Detection" by Debing is a more recent paper
Regardless of what metric you use, think about how you will deal with false positives/negatives. As opposed to simple thresholding, I'd use the metric result to sort the images and then snip the end of the list that looks like it contains only blurry images.
Your task will be a lot simpler if your image set contains fairly similar content (e.g. faces only). This is because the image quality assessment metrics
can often be influenced by image content, unfortunately.
Google Scholar is truly your friend here. I wish I could give you a concrete solution, but I don't have one yet -- if I did, I'd be a very successful Masters student.
UPDATE:
Just thought of another idea: for each image, re-compress the image with JPEG and examine the change in file size before and after re-compression. If the file size after re-compression is significantly smaller than before, then it's likely the image is not heavily compressed, because it had some significant detail that was removed by re-compression. Otherwise (very little difference or file size after re-compression is greater) it is likely that the image was heavily compressed.
The use of the quality setting during re-compression will allow you to determine what exactly heavily compressed means.
If you're on Linux, this shouldn't be too hard to implement using bash and imageMagick's convert utility.
You can try other variations of this approach:
Instead of JPEG compression, try another form of degradation, such as Gaussian blurring
Instead of merely comparing file-sizes, try a full reference metric such as SSIM -- there's an OpenCV implementation freely available. Other implementations (e.g. Matlab, C#) also exist, so look around.
Let me know how you go.
I had many photos shot to an ancient book (so similar layout, two pages per image), but some were much blurred, to the point that the text could not be read. I searched for a ready-made batch script to find the most blurred one, but I didn't find any useful, so I used another part of script got on the net (based on ImageMagick, but no longer working; I couldn't retrieve the author for the credits!), useful to assessing the blur level of a single image, tweaked it, and automatised it over a whole folder. I uploaded here:
https://gist.github.com/888239
hoping it will be useful for someone else. It works on a Linux system, and uses ImageMagick (and some usually command line installed tools, as gawk, sort, grep, etc.).
One simple heuristic could be to look at width * height * color depth < sigma * file size. You would have to determine a good value for sigma, of course. sigma would be dependent on the expected entropy of the images you are looking at.