I'm a ML newbie, and for the first time I'm trying
to do machine learning to my own handwriting.
Building a classifier.
I have enough pictures containing my handwriting and I have managed to separate characters from one another.
The result is that now I have around 25,000 samples of letters each is a 40X40 pixels image, In Binary - black or white.
The problem I'm trying to solve is the tagging of each picture, which now I do manually, but I think of a simpler solution to my problem must be exist out there.
What can be a way for solving this kind of problem in the machine learning world?
Did every picture in the MINST database tagged by someone manually?
Related
Newbee question here: right now I need a relatively large database of images, say a few thousand, for image recognition training purposes.
I found some good ways to get rough results, like playing with google images search terms e.t.c. and binge-downloading them. But the results (images) are still only like 50% representative of what I would need on the image (other images are either related things, or plain garbage). Picking by hand isn't really an option, because it would take a whole lot of time. So is there a quicker way of picking those images? Like using some other image recognition network, or specific software?
You can search Kaggle for image recognition competitions such as cdiscount-image-classification-challenge.
The data is usually available easily.
This might be a very broad question so I'm sorry in advance. I'd like to also point out I'm new in the CV field, so my insight in this field is minimum.
I am trying to find correspondences between points from a FLIR image and a VIS image. I'm currently building 40x40 pixels regions around keypoints, over which I'm applying the LoG. I'm trying to compare them to find the most similar regions.
For example, I have these data sets:
Where the columns represent, in this order:
the image for which I'm trying to find a correspondent
the candidate images
the LoG of the first column
the LoG of the second column
It is very clear, for the human eye, that the third image is the best match for the first set, while the first image is the best image for the second set.
I have tried various ways of expressing a similarity/disimilarity between these images, such as SSD, Cross Correlation, or Mutual Information, but they all fail to be consistent (they only work in some cases).
Now, my actual question is:
What should I use to express the similarity between images in a more semantic way, such that shapes would be more important in deciding the best match, rather than actual intensities of the pixels? Do you know of any technique that would aid me in my quest of finding these matches?
Thank you!
Note: I'm using OpenCV with Python right now, but the programming language and library is not important.
I have a problem statement to recognize 10 classes of different variations(variations in color and size) of same object (bottle cap) while falling taking into account the camera sees different viewpoint of the object. I have split this into sub-tasks
1) Trained a deep learning model to classify only the flat surface of the object and successful in this attempt.
Flat Faces of sample 2 class
2) Instead of taking fall into account, trained a model for possible perspective changes - not successful.
Perception changes of sample 2 class
What are the approaches to recognize the object even for perspective changes. I am not constrained to arrive with a single camera solution. Open to ideas in approaching towards this problem of variable perceptions.
Any help could be really appreciated, Thanks in advance!
The answer I want to give you is: CapsNets
You should definately check out the paper, where you will be introduced to some short comings of CNNs and how they tried to fix them.
That said, I find it hard to believe that your architecture cannot solve the problem successfully when the perspective changes. Is your dataset extremely small? I'd expect the neural network to learn filters for the riffled edges, which can be seen from all perspectives.
If you're not limited to one camera you could try to train a "normal" classifier, which you feed multiple images in production and average the prediction. Or you could build an architecture that takes in multiple perspectives at once. You have to try for yourself, what works best.
Also, never underestimate the power of old school image preprocessing. If you have 3 different perspectives, you could take the one that comes closest to the "flat" perspective. This is probably as easy as using the image with the largest colored area, where img.sum() is the highest.
Another idea is to figure out the color through explicit programming, which should be fairly easy and then feed the network a grayscale image. Maybe your network is confused by the strong correlation of the color and ignores the shape altogether.
I am building an iOS app that, as a key feature, incorporates image matching. The problem is the images I need to recognize are small orienteering 10x10 plaques with simple large text on them. They can be quite reflective and will be outside(so the light conditions will be variable). Sample image
There will be up to 15 of these types of image in the pool and really all I need to detect is the text, in order to log where the user has been.
The problem I am facing is that with the image matching software I have tried, aurasma and slightly more successfully arlabs, they can't distinguish between them as they are primarily built to work with detailed images.
I need to accurately detect which plaque is being scanned and have considered using gps to refine the selection but the only reliable way I have found is to get the user to manually enter the text. One of the key attractions we have based the product around is being able to detect these images that are already in place and not have to set up any additional material.
Can anyone suggest a piece of software that would work(as is iOS friendly) or a method of detection that would be effective and interactive/pleasing for the user.
Sample environment:
http://www.orienteeringcoach.com/wp-content/uploads/2012/08/startfinishscp.jpeg
The environment can change substantially, basically anywhere a plaque could be positioned they are; fences, walls, and posts in either wooded or open areas, but overwhelmingly outdoors.
I'm not an iOs programmer, but I will try to answer from an algorithmic point of view. Essentially, you have a detection problem ("Where is the plaque?") and a classification problem ("Which one is it?"). Asking the user to keep the plaque in a pre-defined region is certainly a good idea. This solves the detection problem, which is often harder to solve with limited resources than the classification problem.
For classification, I see two alternatives:
The classic "Computer Vision" route would be feature extraction and classification. Local Binary Patterns and HOG are feature extractors known to be fast enough for mobile (the former more than the latter), and they are not too complicated to implement. Classifiers, however, are non-trivial, and you would probably have to search for an appropriate iOs library.
Alternatively, you could try to binarize the image, i.e. classify pixels as "plate" / white or "text" / black. Then you can use an error-tolerant similarity measure for comparing your binarized image with a binarized reference image of the plaque. The chamfer distance measure is a good candidate. It essentially boils down to comparing the distance transforms of your two binarized images. This is more tolerant to misalignment than comparing binary images directly. The distance transforms of the reference images can be pre-computed and stored on the device.
Personally, I would try the second approach. A (non-mobile) prototype of the second approach is relatively easy to code and evaluate with a good image processing library (OpenCV, Matlab + Image Processing Toolbox, Python, etc).
I managed to find a solution that is working quite well. Im not fully optimized yet but I think its just tweaking filters, as ill explain later on.
Initially I tried to set up opencv but it was very time consuming and a steep learning curve but it did give me an idea. The key to my problem is really detecting the characters within the image and ignoring the background, which was basically just noise. OCR was designed exactly for this purpose.
I found the free library tesseract (https://github.com/ldiqual/tesseract-ios-lib) easy to use and with plenty of customizability. At first the results were very random but applying sharpening and monochromatic filter and a color invert worked well to clean up the text. Next a marked out a target area on the ui and used that to cut out the rectangle of image to process. The speed of processing is slow on large images and this cut it dramatically. The OCR filter allowed me to restrict allowable characters and as the plaques follow a standard configuration this narrowed down the accuracy.
So far its been successful with the grey background plaques but I havent found the correct filter for the red and white editions. My goal will be to add color detection and remove the need to feed in the data type.
We as human, could recognize these two images as same image :
In computer, it will be easy to recognize these two image if they are in the same size, so we have to make Preprocessing stage or step before recognize it, like scaling, but if we look deeply to scaling process, we will know that it's not an efficient way.
Now, could you help me to find some way to convert images into objects that doesn't deal with size or pixel location, to be input for recognition method ?
Thanks advance.
I have several ideas:
Let the image have several color thresholds. This way you get large
areas of the same color. The shapes of those areas can be traced with
curves which are math. If you do this for the larger and the smaller
one and see if the curves match.
Try to define key spots in the area. I don't know for sure how
this works but you can look up face detection algoritms. In such
an algoritm there is a math equation for how a face should look.
If you define enough object in such algorithms you can define
multiple objects in the images to see if the object match on the
same spots.
And you could see if the predator algorithm can accept images
of multiple size. If so your problem is solved.
It looks like you assume that human's brain recognize image in computationally effective way, which is rather not true. this algorithm is so complicated that we did not find it. It also takes a large part of your brain to deal with visual data.
When it comes to software there are some scale(or affine) invariant algorithms. One of such algorithms is LeNet 5 neural network.