I am evaluating a Vertex AI IOD model with roughly 3000 images and have found some of the testing images determined to be "false positives" contain true positives. I would like to extract the image/file name of these images in order to correct the annotation dataset.
Is there a way to do this?
Thanks for any help!
Best
Related
I got a classifier with my training set containing images of three types following this guide: https://ch.mathworks.com/help/vision/examples/image-category-classification-using-bag-of-features.html
Now I want to use this classifier to classify the images of another dataset. Outputs are supposed to give me the predicted types of the images and corresponding probabilities.
I found the function "predict" to do the prediction.
Link: https://ch.mathworks.com/help/vision/ref/imagecategoryclassifier.predict.html
However, I have two questions
First, it says:
[labelIdx,score] = predict(categoryClassifier,imds) returns the predicted label index and score for the images specified in imds.
I don't understand this "score". It says: "The score provides a negated average binary loss per class". And the outputs of "score" are negative. So is there any way I can obtain the probability(should be [0,1]) from this "score"?
Second, my testing datasets contains images of 6 types, that is, 3 more types than my classifier. But with the function "predict", it will give a label from one of three types to each images. How can I add an extra label to point out the images that cannot be classified into any of the three types?
I think this one could be solved if I can get the probabilities from my first question. At least I could set a threshold to change the labels manually.
Any suggestions that could help solve these problems? Thanks a lot!
I am working on video classification. So let's say, I sub-sample the video temporally. So for each sub-sample, I engineer some features out of it. Let's say I can represent these features with a two dimensional matrix.
So, these values of the matrix are time-Dependant. So for each video, I have a set of matrices, which are time dependent.
So I need to use a RNN to model these time dependent matrix values and represent the video. This representation should classify the video in to classes. In other words, the RNN should be able to classify the video in to classes, depending on these time dependent matrix values.
I need to know, Is this possible with RNNs? would it be a good practice? If so, what are the guide lines anyone could provide me. What is a good library to use? What would be good tutorials? Thanks.
You flatten the images of the video and use them as an element of the sequence.
You will have to put a convnet under the RNN, most likely, to get reasonable results.
As such, you feed the image to a convnet, then flatten the activation map and feed it to the RNN cell.
https://stackoverflow.com/a/36992625/447599
I'm currently working on my thesis on the neural networks. I'm using the CIFAR10 as a reference dataset. Now I would like to show some example results in my paper. The problem is, that the images in the dataset are 32x32 pixels so it's really hard to recognize something on them when printed on paper.
Is there any way to get hold of the original images with higher resolution?
UPDATE: I'm not asking for image processing algorithm, but for the original images presented in CIFAR-10. I need some higher resolution samples to put in my paper.
I now have the same problem and I just found your question.
It seems that CIFAR was built from labeling the tinyimages dataset, and are kind enough to share the indexing from CIFAR to tinyimages. Now tinyimages contain metadata file with URL of the original images and a toolbox for getting for any image you wish (e.g. those included in the CIFAR index).
So one may write a mat file which does this and share the results...
They're just small:
The CIFAR-10 and CIFAR-100 are labeled subsets of the 80 million tiny images dataset.
You could use Google reverse image search if you're curious.
The scenario is,
There are two images and we are required to say whether one image is a subset of another image. In other words, image A is present within or part of image B.
We tried to use traditional bit by bit comparison, but it looks too time consuming.
Is there any other image comparison algorithm in place that can help us?
Thanks in advance for your responses.
Check out SIFT and SURF descriptors to find keypoints in the images, and then match them across the two images.
I am working on a software that will match a captured image (face) with 3/4 images (faces) of same person. Now there are 2 possibilities
1- That the captured image (face) is of the same person whose 3/4 images (faces) are already stored in database
2. Captured image is of a different person
Now i want to get the results of the above 2 scenarios, i.e matched in case 1 and not matched in case 2. I used 40 Gabor filters so that i can get good results. Moreover i get the results in an array (histogram). But It don't seems to work fine and environment conditions like light also have influence on the matching process. Can any one suggest me a good and efficient technique for this thing to achieve.
Well, This is basically face identification problem.
You can use LBP(Local Binary Pattern) to extract features from images.LBP is very robust and llumination invariance method.
You can try following steps-
Training:-
Extract face region (using OpenCV HaarCascade)
Re-size all the extracted face regions to equal size
Divide resized face into sub regions(Ex: 8*9)
Extract LBP features from each region and concatenate them, , because localization of feature is very important
Train SVM by this concatenated feature, with different label to each different person's image
Testing:-
Take a face image and Follow step 1 to 4
Predict using SVM(about which person's image this is)