I was given a task to process image files, and analyze data on them.
Imagine an exam paper with A, B, C, D answers to fill in (Picture1).
A vision sensor inspects this paper, and saves an image file of it on the computer. I would like to have this image file analyzed (check for the correct filled in circles) and create a document with the results.
With close to no programming skills, I am kind of clueless on how to even start this project. I basically need something to detect if the red circles are filled in or at least have some % of the area filled (Picture2), and the others in the row are not, and give scores accordingly.
I don't know that this could help you and I even do not know that is the right answer but I can not make comments yet.
So basically you should make some application where you can process every picture and check pixels in some area that covers your template with good answers. Then you store that there was true/false result in inspection and sum this up to store the score.
Maybe this will be helpful: Images and Pixels by Daniel Shiffman
But also I think that with no programming skills this could be very hard to accomplish your task.
Related
What i'm doing is GPGPU on WebGL and I don't know the access pattern which I'd be talking about applies to general graphics and gaming programs. In our code, frequently, we come across data which needs to be summarized or reduced per output texel. A very simple example is matrix multiplication during which, for every output texel, your return a value which is a dot product of a row of one input and a column of the other input.
This has been the sore point of our performance because of not so much the computation but multiplied data access. So I've been trying to find a pattern of reads or data layouts which would expedite this operation and I have been completely unsuccessful.
I will be describing some assumptions and some schemes below. The sample code for all these are under https://github.com/jeffsaremi/webgl-experiments
Unfortunately due to size I wasn't able to use the 'snippet' feature of StackOverflow. NOTE: All examples write to console not the html page.
Base matmul implementation: Example: [2,3]x[3,4]->[2,4] . This produces in a simplistic form 2 textures of (w:3,h:2) and (w:4,h:3). For each output texel I will be reading along the X axis of the left texture but going along the Y axis of the right texture. (see webgl-matmul.html)
Assuming that GPU accesses data similar to CPU -- that is block by block -- if I read along the width of the texture I should be hitting the cache pretty often.
For this, I'd layout both textures in a way that I'd be doing dot products of corresponding rows (along texture width) only. Example: [2,3]x[4,3]->[2,4] . Note that the data for the right texture is now transposed so that for each output texel I'd be doing a dot product of one row from the left and one row from the right. (see webgl-matmul-shared-alongX.html)
To ensure that the above assumption is indeed working, I created a negative test also. In this test I'd be reading along the Y axis of both left and right textures which should have the worst performance ever. Data is pre-transposed so that the results make sense. Example: [3,2]x[3,4]->[2,4]. (see webgl-matmul-shared-alongY.html).
So I ran these -- and I hope you could do as well to see -- and I found no evidence to support existence or non-existence of such caching behavior. You need to run each example a few times to get consistent results for comparison.
Then I came along this paper http://fileadmin.cs.lth.se/cs/Personal/Michael_Doggett/pubs/doggett12-tc.pdf which in short claims that the GPU caches data in blocks (or tiles as I call them).
Based on this promising lead I created a version of matmul (or dot product) which uses blocks of 2x2 to do its calculation. Prior to using this of course I had to rearrange my inputs into such layout. The cost of that re-arrangement is not included in my comparison. Let's say I could do that once and run my matmul many times after. Even this scheme did not contribute anything to the performance if not taking something away. (see webgl-dotprod-tiled.html).
A this point I am completely out of ideas and any hints would be appreciated.
thanks
first time user of this forum - guidance on how to provide enough information is very appreciated. I am trying to replicate the presentation of data used in the Medical education field. This will help improve the quality of examiners' marking of trainees in a Clinical Exam. What I would like to communicate will be similar to what is already communicated in the College of General Practitioners regarding one of their own exams, please see www.gp10.com.au/slides/thursday/slide29.pdf to help understand what it is I want to present. I have access to Excel, SPSS and R, so any help with any of these would be great. However as a first attempt I have used SPSS and created 3 variables: dummy variable, a "station score" and a "global rating score"(GRS). The "station score"(ST) is a value between 0 and 10 (non-integers) and is on the y-axis similar to the pdf presentation of "Candidate Final Marks". The x-axis is the "global rating scale", an integer from 1 to 6 and is represented in the pdf as the "Overall Performance Scale". When I use SPSS's boxplot I get a boxplot as depicted.
.
What I would like to do is overlay a single examiners own scoring of X number of examinees. So for one examiner (examiner A) provided the following marks:
ST: 5.53,7.38,7.38,7.44,6.81
GRS: 3,4,4,5,3
(this is transposed into two columns).
Whether it be SPSS, Excel or R how would I be able to overlay the box and whisker plots with the individual data points provided by the one examiner? This would help show the degree to which the examiners' marking styles are in concordance with the expected distribution of ST scores across GRS. Any help greatly appreciated! I like Excel graphics but I have found it very difficult to work with when choosing the examiners' data as a separate series - somehow the examiners' GRS scores do not line up nicely on the x-axis. I am very new to R but am also very interested in R, and would expend time to get a good result in R if a good result is viable. I understand JMP may be preferable for this type of thing but access to this may not be possible.
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.
I would like to perform a binary classification of documents (.txt, .pdf, .jpeg, .img, etc.) into two categories: printable and non-printable. Essentially our school runs a free printing service for clubs, but the reality is that many clubs abuse the free printing and end up printing their homework, papers, etc., which amounts to thousands of dollars in ink and paper. Thus we would like to take some unsupervised methods to help limit this by determining whether a document is with high probability not club related (e.g. Biophysics paper, there is no biophysics club!).
So this is a very simple binary classification problem. I am not looking for low-level implementation details or which ML algorithms I should use, but rather how I should discover the relevant features that will then be fed to the training, etc.
My first idea was to gather all the documents that students print in the library. The idea is that if you have actual club printing, you'll do it for free at the club printing center rather than pay for it at the library. That would be a massive dataset, assuming every document printed at the library is assigned the non-printable/club material category. Unfortunately, the school is very liberal and opposed to allowing this due to privacy concerns, so it is not really an option without legal risks.
A similar-minded option would be to collect documents that are tied to courses / school work, e.g. course syllabi, available course documents online (homeworks, papers, etc.) and do feature extraction / selection on these. The assumption is that students would be abusing the printing to generally print material relevant to their studies.
While for .pdf and .txt based document this approach should have reasonable performance, I am at a loss at how to classify image based documents, besides perhaps using the title of the document and other meta data. A clever violator could simply convert all their text documents to image format to circumvent this system. However that is outside the scope of this question and should be saved for a future question / research. For now the scope is just text based documents.
Note that there are previous questions on topics similar to this, but mine is very specific and I believe it may pose challenges that something like movie review classification might not have to face.
I just wanted to leave a comment but it ended way longer than what I imagined.
While this is an interesting problem I'm not sure ML will get you what you need easily.
Firstly your classification problem is of the type A vs the World and A isn't strictly defined. Unless you know exactly what kind of stuff the clubs print you can't really say that new material belong or no to that class.
This will prove particularly difficult when you will need to assemble a large enough training set to be able to cover whatever can or cannot be printed. Such task will be extremely tedious, and as you said you won't have access to what the clubs usually print out so at best you will have a large class imbalance in your training set.
As the goal is to make the system automated (I mean if there is human interaction anyway, it's faster to check what will be printed than to make a ML algorithm that will provide a score that a human will have to investigate anyway) the number of false positives and false negatives will also be problematic. There will be cases where the clubs won't be able to print things they have the right to.
As you said you could simplify greatly the problem by classifying Course Material and Not Course Material. For that I will look towards BoW because some words are more present than others in papers or course material (everything remotely technical). The number of words as well as the overall size of the file seem like sensible things to extract. The structure is often also particular : it might be a good idea to extract such things : "number of lines with less than x words", "number of lines per page", "number of pictures" (if that's something you can extract from the file), ...
For pictures the major thing to check would be if this a scan of something (often they will scan and print course related things I guess), for that the format of the image is already a good indication but I don't see other things that would be particularly "course related".
So for me, if you can't really define precisely one of your two classes don't go with classification or reduce the problem to something you can really define (course related things).
If you are able to compile a "black list" of documents students are not allowed to print, you can then implement a several layers rejection mechanism.
I would suggest these 3 levels:
compare the md5 of the file they want to print with a database of all the md5 of the black-listed documents.
if the 1) is passed, compare repeat 1) but at a page level, rather than at document level (perhaps they want to print just few pages rather than the entire document).
if 2) is passed you can compare the page they want to print with the pages of the black-listed documents document using an image similarity method, like SSIM. if you get a high score between the page they want print and one of the black-listed items do not print, and update your md5 database accordingly.
if 3) is passed: print!
A few words about SSIM: this method is quite robust to noise, so even a smart student who added some sort of niose to the image will be caught
However:
you have to find a proper way to extract a region of interest (ROI) from the page and the db of documents (if the two ROIs are in two different area of the page, SSIM will be negative)
SSIM might be slow! definitely a C implementation is needed here.
I think SSIM is not rotational invariant, hence the check will fail if they print the page upside down (unless you have a smart way to rotate the page).
This is an idea I got in to my mind,
All the display devices(screens which have pixels etc...) have an upper bound for the amount of various images they can generate.
as an example 1024*728 - 32 bit pixel display can only show (2^32)^(1024*768) etc... number of identical frames without duplicating any scene(view).
funny thing is, It's like we could pre generate all the films all the windows we have ever seen in our lives through screens etc...
the question here is can anybody use this abstract idea to create something useful? :D
You're talking of a number about
(2^32)^(1024*768) ~~ ((2^4)^8)^(10^6) ~~ 10^8^(10^6) ~ 10^8000000.
The number of atoms in universe is about
10^80 // http://en.wikipedia.org/wiki/Observable_universe#Matter_content
I think that there is no way we could pre-generate all the screens in our life.
Let me formulate another question. From a number this big, what can we do to reduce it? How to aggregate similar pictures in order to reduce the complexity?
Another nice question is: what kind of data structure we need to store all this information? Suppose we reduce the number of similar images to 10^10. What kind of structure can handle so many different kinds of pictures in an efficient way?
So given some extra information about the scenes you could generate you might be able to pull apart the scenes that no-one has ever seen.
So if you could take all the pictures out on the internet and the statistics about what was popular or viewed a lot then compute your all possible screens you could pull apart that was not viewed much.
With some basic rules about complexity of the image you might be able to come up with images that have not been seen before. Think 80% flesh tones might produce something coupled with a variance to show range might render people naked. :-)
Of course the computation of such an idea is vastly outside our potential. 2^32^(1024*768) is in the superexponential range which is outside the bounds of reality. I tried to compute it in ruby, and it just died. It would have been fun if it had actually worked. :-)