The use of OpenCV is fairly simple- create a FaceRecognizer object, train it, give it a source of images and then check your given image against those images with regards to the trained Eigenimage.
The problem is, the predict method has only two modes- find a match, or find a match and get the confidence of that match.
What I'd like to do is instead get a list of, say, the top ten matches along with the confidences of them (often my reference images are of low quality/lighting and therefore I don't expect there to be many high-confidence matches, but rather many low-quality matches).
If your opencv_contrib version is newer than 19 Jan, you can. This was merged in 19 Jan (#465).
To use it:
Mat testImage = ...; // load your test image
Ptr<TopNPredictCollector> collector = TopNPredictCollector.create(10, THRESH);
model->predict(testImage, collector);
Ptr<std::list<std::pair<int,double>>> result = collector.getResult();
Before that, the only colletor available was MinDistancePredictCollector(), that's why you could only get the closest match (see here).
Related
I am working on a project where my task is to identify machine part by its part number written on label attached to it or engraved on its surface. One such example of label and engraved part is shown in below figures.
My task is to recognise 9 or 10 alphanumerical number (03C 997 032 D in 1st image and 357 955 531 in 2nd image). This seems to be easy task however I am facing problem in distinguishing between useful information in the image and rest of the part i.e. there are many other numbers and characters in both image and I want to focus on only mentioned numbers. I tried many things but no success as of now. Does anyone know the image pre processing methods or any ML/DL model which I should apply to get desired result?
Thanks in advance!
JD
You can use OCR to the get all characters from the image and then use regular expressions to extract the desired patterns.
You can use OCR method, like Tesseract.
Maybe, you want to clean the images before running the text-recognition system, by performing some filtering to remove noise / remove extra information, such as:
Convert to gray scale (colors are not relevant, aren't them?)
Crop to region of interest
Canny Filter
A good start can be one of this tutorial:
OpenCV OCR with Tesseract (Python API)
Recognizing text/number with OpenCV (C++ API)
I have been following the Turicreate tutorial link here
I am able to train a model successfully as per instructions. I am also able to consume the model in the iOS app with the help of the code provided over there. But I am not able to figure out how could I get the most similar actual images based on the distances this model returns. Also when I run it on iPhone, it returns me offset and element which I am not able to interpret. Please see the screenshot.
My aim in the iOS application is to input an image, pass that input image to the model and then show the actual output 5 or 10 most similar images and not just the distances.
Be sure that you have an id column or have added the id column to your SFrame using:
reference_data = reference_data.add_row_number()
Here is a code snippet to create the image_similarity model and get the ten most similar images for a sample image. I use fifty as a k value to demonstrate that how to pull out the n most similar from a larger group in your similarity graph.
similarity_graph = model.similarity_graph(k=50)
similar_images = similarity_graph.edges
# pick a sample image from reference_data
sample_index = 3
sample_similar_images = similar_images[similar_images["__src_id"]==sample_index].sort("rank")
# get 10 most similar images
most_similar_ids = sample_similar_images["__dst_id"][0:10]
most_similar_images = reference_data.filter_by(most_similar_ids, "id")
For details on interpreting the distance MultiArray from the CoreML model, see the sample code in the Turi Create documentation. The element value corresponds to the distance.
I am trying to determine when a food packaging have error or not error. Example
the logo " McDonald's " have error misprints or not, as the wrong label, wrong color..( i can not post picture )
What should I do, please help me!!
It's not a trivial task by any stretch of the imagination. Two images of the same identical object will always be different according to lightning conditions, perspective, shooting angle, etc.
Basically you need to:
1. Process the 2 images into "digested" data - dominant color, shapes, etcw
2. Design and run your own similarity algorithm between the 2 objects
You may want to look at Feature detectors in OpenCV: Surf, SIFT, etc.
Along a result I just found your question, so I think I come too late.
If not I think your problem car easily be resolved, it exists since years and is called Sikuli .
While it's for testing purposes, I have been using it in the same way as you need : compare a reference and a production image. Based on OpenCV it does it very well.
EDIT:
I have continued working on my problem among other things and have made significant process. Using one Dr. Ashby's macro provided on ImageJwiki, and using some of my own makeshift code I can now do batch processing of images taken of Hoescht, Calcein AM, and Ethidium Homodimer stains and get decent recognition of objects. Reducing exposure time and levels of stain used (specifically calcein AM) has helped with the pixel value cut offs I was dealing with earlier. The macro still has problems with distinguishing clumped cells from one another though. To address this issue I want to implement a command in my macro that divides clusters of cells that it identifies as one cell based on the average size of our cells. The only problem is that in all my reading I haven't seen anything that mentions this. Does anyone have any thoughts on how I could implement this code? I have copied the macro below.
//get appropriate directories from user
dir1 = getDirectory("Choose Source Directory ");
dir2 = getDirectory("Choose Destination directory");
list = getFileList(dir1);
//give user an opportunity to adjust default parameters to better fit their application
Dialog.create("Adjust for objective magnification");
Dialog.addNumber("Objective Magnification (use 10 if unknown)", 10);
Dialog.addMessage("\tIf needed particle size limits can be adjusted below \nLeave mag. at 10 if customizing particle size limits\n");
Dialog.addNumber("Minimum particle size (pixels^2)",420);
Dialog.addNumber("Maximum particle size (pixels^2)",1600);
Dialog.addMessage("\tIn the following dialogs select \n first the Source Directory, \nthen a Destinaion directory for Results");
Dialog.show();
//Assigning the entered values to variables
magnification=Dialog.getNumber();
userMin=Dialog.getNumber();
userMax=Dialog.getNumber();
sMin=magnification*magnification/100*userMin;
sMax=magnification*magnification/100*userMax;
setBatchMode(true);
for (i=0; i<list.length; i++){
//print (list[i]);
open(dir1+list[i]);
name=File.nameWithoutExtension;
//Prepare the image by removing any scale and making 8-bit
run("Set Scale...", "distance=0 known=0 pixel=1 unit=pixel");
run("8-bit");
saveAs("Tiff", dir2+i+" Original "+name);//Saving with this naming scheme is required for the MeLast macro to function
//run("Brightness/Contrast...");
setMinAndMax(50, 255);
setOption("BlackBackground", false);
run("Make Binary", "method=Yen background=Light calculate black");
run("Watershed", "stack");
//Analyze particles
run("Analyze Particles...", "size="+sMin+"-"+sMax+" circularity=0.50-1.00 show=[Count Masks] display exclude include summarize");
//Save the masks file
saveAs("Tiff", dir2+i+" CountMask "+name);//Saving with this naming scheme is required for the MeLast macro to function
close();
//Save the thresholded image
saveAs("Tiff", dir2+i+" Thresholded "+name);//Saving with this naming scheme is required for the MeLast macro to function
}
//Save the results
selectWindow("Results");
saveAs("Results", dir2+"ZZ Results.xls");
//Save the summary
selectWindow("Summary");
saveAs("Text", dir2+"Z Summary.txt");
You need to find those clusters and analyze each to guess how many cells might belong to that cluster, using spatial information of the cells and other specific information in your problem domain. I believe that's an usual image analysis task.
As for cut-off pixel values, I guess you can consider the cut-off pixels as censored data. But I am not sure how meaningful it would be for 8 bit depth images.
There is another free, open-source program called CellProfiler (http://www.cellprofiler.org) that has some more specialized methods for separating cells -- more advanced than the standard watershed. See, for example, part of the manual here: http://www.cellprofiler.org/CPmanual/IdentifyPrimaryObjects.html.
Perhaps CellProfiler can do the job, or point you to the right algorithms to bring into the ImageJ macro.
I'm trying to reduce the calculation time of my stitching algorithm. I got some images which I want to stitch in a defined order but it seems like cv::stitcher.stitch() function tries to stitch every image with every other image.
I feel like I might find the solution in the parameters of OpenCV Stitcher. If not maybe I have to modify the function or try something else to reduce calculation time. But since I'm pretty much a beginner, I don't know how. I know that using GPU might be a possibility but I just don't get CUDA running on Ubuntu at the moment.
It would be great if you could give me some advice!
Parameters for OpenCV Stitcher module:
Stitcher Stitcher::createDefault(bool try_use_gpu) {
Stitcher stitcher;
stitcher.setRegistrationResol(0.6);
stitcher.setSeamEstimationResol(0.1);
stitcher.setCompositingResol(ORIG_RESOL);
stitcher.setPanoConfidenceThresh(1);
stitcher.setWaveCorrection(true);
stitcher.setWaveCorrectKind(detail::WAVE_CORRECT_HORIZ);
stitcher.setFeaturesMatcher(new detail::BestOf2NearestMatcher(try_use_gpu));
stitcher.setBundleAdjuster(new detail::BundleAdjusterRay());
from stitcher.cpp:
https://code.ros.org/trac/opencv/browser/trunk/opencv/modules/stitching/src/stitcher.cpp?rev=7244
I want to stitch in a defined order but it seems like
cv::stitcher.stitch() function tries to stitch every image with every
other image.
cv::stitcher does not have a parameter to fulfil your requirement.
However, in the stitching_detailed.cpp sample you have the --rangewidth parameter. By setting it to 1, the algorithm will only consider adjacent image pairs (e.g. for pair 1-2 matches would be computed but not for pair 1-3)