I am working on a dataset (training + testing) which contains a different shopping cart items (eg: biscuits, soaps etc..) with different backgrounds and I need to predict the product id for all testing images (product ids are unique for each product, Let's say Good-day 10 rs is having product id 1 and so on... for different products )
My approach was to :
1) extract the foreground from the image.
2) Apply sift/surf algorithm for finding matching keypoints (or) train a faster RCNN...
I was thinking to build a Haar Cascade classifier, can anyone suggest an easy foreground extraction algorithm possible for this scenario in python ?
For real-time purposes I don't recommend the RCNN models since they are not built for realtime but for precision. Sift or surf can recognise scenes but if the object is deformed in some way they would fail easily. Haar cascade seems to be a good solution. I also recommend checking out Yolo or SSD models since they can be easily trained with transfer learning and they are very successfull at realtime object classification. Opencv also has a DNN module for running these kinds of neural networks.
Related
I have a pairs of images (input-output) but I don't know the transformation to going from A (input) to B (output). I want to record image A and get image B. Physically I can change the setup to get A or B, but I want to do it by software.
If I understood well, a trained Artificial Neural Network is able to do that, having an input can give the corresponding output, is it right?
Is there any software/ANN that just "training" it with entering a number of input-output pairs will be able to provide the correct output if the input is a new (but similar to the others) image?
Thanks
If you have some relevant amount of image pairs (input/output pair) and you don't know transformation between input and output you could train ANN on that training set to imitate that unknown transformation. You will be able to well train your ANN only if you have sufficient amount of training image pairs, but it could be pretty impossible when that unknown transformation is complicated.
For example if that transformation simply increases intensity values of pixels at input image by given value, ANN will very fast learn to imitate that behavior, but if that unknown transformation is some complicated convolution or few serial convolutions or something more complicated it will be very hard, near impossible to train ANN to imitate that transformation. So, more complex transformation will need bigger training set and more complex ANN design.
There are plenty of free opensource ANN libraries implemented in many languages. You could start for example with that tutorial: http://www.codeproject.com/Articles/13091/Artificial-Neural-Networks-made-easy-with-the-FANN
What you are asking is possible in principle -- in theory, an ANN with sufficiently many hidden units can learn an arbitrary function to map inputs to outputs. However, as the comments and other answers have mentioned, there may be many technical issues with your particular problem that could make it impractical. I would classify these problems as (a) mapping complexity, (b) model complexity, (c) scaling complexity, and (d) implementation complexity. They are all somewhat related, but hopefully this is a useful way to break things down.
Mapping complexity
As mentioned by Springfield762, there are many possible functions that map from one image to another image. If the relationship between your input images and your output images is relatively simple -- like increasing the intensity of each pixel by a constant amount -- then an ANN would be able to learn this mapping without much difficulty. There are probably many more transformations that would be similarly easy to learn, such as skewing, flipping, rotating, or translating an image -- basically any affine transformation would be easy to learn. Other, nonlinear transformations could also be feasible, such as squaring the intensity of each pixel.
As a general rule, the more complicated the relationship between your input and output images, the more difficult it will be to get a model to learn this mapping for you.
Model complexity
The more complex the mapping from inputs to outputs, the more complex your ANN model will be to be able to capture this mapping. Models with many hidden layers have been shown in the past 10 years to perform quite well on tasks that people had previously thought impossible, but often these state-of-the-art models have millions or even billions of parameters and take weeks to train on GPU hardware. A simple model can capture many simple mappings, but if you have a complex input-output map to learn, you'll need a large, complex model.
Scaling complexity
Yves mentioned in the comments that it can be difficult to scale models up to typical image sizes. If your images are relatively small (currently the state of the art is to model images on the order of 100x100 pixels), then you can probably just throw a bunch of raw pixel data at an ANN model and see what happens. But if you're using 6000x4000 images from your shiny Nikon DSLR, it's going to be quite difficult to process those in a reasonable amount of time. You'd be better off compressing your image data somehow (PCA is a common technique) and then trying to learn the mapping in the compressed space.
In addition, larger images will have a larger space of possible mappings between them, so you'll need more of your larger images as training data than you would if you had small images.
Springfield762 also mentioned this: If the mapping between your input and output images is simple, then you'll only need a few examples to learn the mapping successfully. But if you have a complicated mapping, then you'll need much more training data to have a chance at learning the mapping properly.
Implementation complexity
It's unlikely that a tool already exists that would let you just throw image data into an ANN model and have a mapping appear. Most likely you'll need, at a minimum, to implement some code that will pre-process your image data. In addition, if you have lots of large images you'll probably need to write code to handle loading data from disk, etc. (There are a lot of "big data" tools for things like this, but they all require some amount of work to get set up.)
There are many, many open source ANN toolkits out there nowadays. FANN (already mentioned) is a popular one in C++ with bindings in other languages. Caffe is quite popular, and is also implemented in C++ with bindings. There seem to be many toolkits that use Python and Theano or some other GPU acceleration library -- Keras, Lasagne, Hebel, Pylearn2, neon, and Theanets (I wrote this one). Many people use Torch, written in Lua. Matlab has at least one neural network toolbox. I'm less familiar with other ecosystems, but Java seems to have Deeplearning4j, C# has Accord, and even R has darch.
But with any of these neural network toolkits, you're going to have to write some code to load the data, process it into the appropriate input format, construct (or load) a network model, train the model, etc.
The problem you're trying to solve is a canonical classification problem that neural networks can help you solve. You treat the B images as a set of labels that you match to A, and once trained, the neural network will be able to match the B images to new input based on where the network locates new input in a high-dimensional vector space. I assume you'd use some combination of convolutional networks to create your features, and softmax for multinomial classification on the output layer. More here: http://deeplearning4j.org/convolutionalnets.html
Since this has been written there has been a lot of work in the realm of cgans ( conditional generative adversarial networks ) please refer to:
https://arxiv.org/pdf/1611.07004.pdf
I have got a new task(not traditional) from my client, It is something about machine learning.
As I have never been to "machine learning" except some little Data Mining stuff so I need your help.
My task is to Classify a product present on any Shopping Site, on the basis of gender(whom the product belongs to),agegroup etc, the training data we can have is the product's Title, Keywords(available in the html of the product page), and product description.
I did a lot of R&D , I found Image Recog APIs(cloudsight,vufind) that returned the details of the product image but that did not full fill the need, used google suggestqueries, searched out many machine learning algorithms and finally...
I came to know about the "Decision Tree Learning Algorithm" but cannot figure out, how it is applicable to my problem.
I tried out the "PlayingTennis" dataset but couldn't make the sense what to do.
Can you give me some direction that from where to start this journey? Should I focus on The Decision Tree Learning algorithm or Is there any other algorithm you would suggest I should focus on to categorize the products on the basis of context?
If you say , I would share in detail about what things I searched about to solve my problem.
I would suggest to do the following:
Go through items in your dataset and classify them manually (decide for which gender each item is). Store each decision so that you would be able to somehow link each item in an original dataset with a target class.
Develop an algorithm for converting each item from your dataset into a feature vector. This algorithm should be able to convert each item in your original dataset in a vector of numbers (more about how to do it later).
Convert all your dataset with appropriate classes into a dataset that would look like this:
Feature_1, Feature_2, Feature_3, ..., Gender
value_1, value_2, value_3, ... male
It would be a good decision to store it in CSV file since you would be able to load it and process in different machine learning tools (More about those later).
Load dataset you've created at step 3 in machine learning tool of your choice and try to come up with the best model that can classify items in your dataset by gender.
Store model created at step 4. It will be part of your production system.
Develop a production code that can convert an unclassified product, create feature vector out of it and pass this feature vector to the model you've saved at step 5. The result of this operation should be a predicted gender.
Details
If there too many items (say tens of thousands) in your original dataset it may be impractical to classify them yourself. What you can do is to use Amazon Mechanical Turk to simplify your task. If you are unable to use it (the last time I've checked you had to have a USA address to use it) you can just classify few hundreds of items to start working on your model and classify the rest to improve accuracy of your classification (the more training data you use the better the accuracy, but up to a certain point)
How to extract features from a dataset
If keyword has form like tag=true/false, it's a boolean feature.
If keyword has form like tag=42, it's a numerical one or ordinal. For example it can be price value or price range (0-10, 10-50, 50-100, etc.)
If keyword has form like tag=string_value you can convert it into a categorical value
A class (gender) is simply boolean value 0/1
You can experiment a bit with how you extract your features, since it may influence the result accuracy.
How to extract features from product description
There are different ways to convert a text into a feature vector. Look for TF-IDF algorithms or something similar.
Machine learning tools
You can use one of existing machine learning libraries and hack some code that loads your CSV dataset, trains a model and checks the accuracy, but at first I would suggest to use something like Weka. It has more or less intuitive UI and you can quickly start to experiment with different machine learning algorithms, convert different features in your dataset from string to categories, or from real values to ordinal values, etc. Good thing about Weka is that it has Java API, so you can automate all the process of data conversion, train models programmatically, etc.
What algorithms to choose
I would suggest to use decision tree algorithms like C4.5. It's fast and show good results on wide range of machine learning tasks. Additionally you can use ensemble of classifiers. There are various algorithms that can combine several algorithms like (google for boosting or random forest to find out more) usually they give better results, but work more slowly (since you need to run a single feature vector through several algorithms.
One another trick that you can use to make your algorithm more accurate is to use models that work on different sets of features (say one algorithm uses features extracted from tags and another algorithm uses data extracted from product description). You can then combine them using algorithms like stacking to come up with a final result.
For classification on the basis of features extracted from text, you can try to use Naive Bayes algorithm or SVM. They both show good results in text classification.
Do consider Support Vector Classifier (SVC), or for Google's sake the Support Vector Machine (SVM). If You have a large training set (which I suspect) search for implementations that are "fast" or "scalable".
I am working on age (or gender) classification using images of human faces. I have decided to use the LBP (Local Binary Patterns) approach for feature extraction and Support Vector Machines (SVM) for freature classification. The whole process is shown in Fig. 1. Below.
As I understand it, the procedure is as follows:
Start with a training set that includes 3 groups: Chidren, Young, Senior. Each group has 50 images (150 images total). Use LBP to prepare the 150 images for classification.
Train a SVM on 150 LBP images with labels:
0: Child
1: Young Adult
2: Senior
Test the system using a set of new images. If all goes according to plan, the system should properly classify images based on the groups defined in step 2.
The algorithm:
for i=1 to N //Assume N is number of image
LBP_feature[i]=LBP_extract(image_i)
end
//Training stage
SVM.train(LBP_feature,label);
//Test stage
face=getFromCamera
//Extract LBP from the face
face_LBP=LBP_extract(face)
label=SVM.predict(face_LBP)
if label=0 then Children
if label=1 then Young
if label=2 then Senior
Does the proposed system make sense for this task?
If you want to use support vector machines, and you also want to consider an image to be a "sample" of subregions, then so-called "support distribution machines" developed by Jeff Schneider and Barnabas Poczos might be best suited for your problem (paper and documentation available online). They actually showed that with some tweaks, support distribution machines outperformed all state-of-the-art methods for a certain popular image classification data set. They used SIFT (sp?) features and then each image was a collection of samples (subregion patches) from the feature space, and then "support distribution machines" are kernel-based SVMs that estimate a divergence kernel between two distributions by using a sample-based estimator.
If you want to use SVMs like support distribution machines, there is one final point to consider. SVMs are two-class classifiers. In order to extend to more than 2 classes, you can either train an SVM that classifies one class versus the union of the rest of the classes, for each choice of class (so N SVMs if you have N classes), and then you run each SVM and choose the class with the highest classification score. Another method, however, is to train an SVM for each pair of classes (so N(N-1)/2 SVMs for N classes) and then try to choose the best class by getting a "consensus" of all the pairwise comparisons. You can read about all this online and choose whichever method you think is best, or whichever method gives the best leave-one-out cross validation performance on the training data. (which should be easy to calculate because you only have 150 training points)
On paper, the approach makes sense. The most important point is whether the LBP is the right feature for this task. You can first extract the LBP using different parameters (image size, bin count if you are using LBP histogram, etc.) and observe the data using a tool like Weka or R to see if your sample data for different classes exhibit different distributions.
You can also refer to a few research papers on age estimation to see what other features are suitable. I have tried Radon transform with some success, for seniors. The wrinkles in faces are well represented in Radon transform.
I am new to sci-kit learn. I have viewed the online tutorials but they all seem to leverage existing data (e.g., digits, iris, etc). I need the information on how to process images so that they can be used by scikit learn.
Details of my Study: I have a webcam set up outside my office. It captures all of the traffic on my street that passes in the field of view. I have cropped several hundred images of sedans, trucks and SUV's. The goal is to predict whether a vehicle is one of these categories. I have applied Histogram Oriented Gradients (HOG) to these images which I have attached for your review to see the differences in the categories. This blog will not allow me to post any images but you can see them here https://stats.stackexchange.com/questions/149421/obtaining-a-hog-feature-vector-for-implementation-in-svm-in-python. I posted the same question at this site but no response. This post is the closest answer I have found. Resize HOG feature for Scikit-Learn classifier
I wish to train an SVM classifier based on these images. I understand that there are algorithms that exist in scikit-image that prepares the HOG images for use in scikit-learn. Can someone help me understand this process. I am also grateful for any thoughts based on your experience as to the probability of success of this classification study. I also understand that I need to train the model using a negative images ( ones with no vehicles. How is this done?
I know I am asking a lot but I am surprised no one that I am aware of has done a tutorial on these early steps. It seems like a fairly elementary study.
I am working on a feature matching project and i am using OpenCV Python as the tool for developed the application.
According to the project requirement, my database have images of some objects like glass, ball,etc ....with their descriptions. User can send images to the back end of the application and back end is responsible for matching the sent image with images which are exist in the database and send the image description to the user.
I had done some research on the above scenario. Unfortunately still i could not find a algorithm for matching two images and identifying both are matching or not.
If any body have that kind of algorithm please send me.(I have to use OpenCV python or JavaCV)
Thank you
This is a very common problem in Computer Vision nowadays. A simple solution is really simple. But there are many, many variants for more sophisticated solutions.
Simple Solution
Feature Detector and Descriptor based.
The idea here being that you get a bunch of keypoints and their descriptors (search for SIFT/SURF/ORB). You can then find matches easily with tools provided in OpenCV. You would match the keypoints in your query image against all keypoints in the training dataset. Because of typical outliers, you would like to add a robust matching technique, like RanSaC. All of this is part of OpenCV.
Bag-of-Word model
If you want just the image that is as much the same as your query image, you can use Nearest-Neighbour search. Be aware that OpenCV comes with the much faster Approximated-Nearest-Neighbour (ANN) algorithm. Or you can use the BruteForceMatcher.
Advanced Solution
If you have many images (many==1 Million), you can look at Locality-Sensitive-Hashing (see Dean et al, 100,000 Object Categories).
If you do use Bag-of-Visual-Words, then you should probably build an Inverted Index.
Have a look at Fisher Vectors for improved accuracy as compared to BOW.
Suggestion
Start by using Bag-Of-Visual-Words. There are tutorials on how to train the dictionary for this
model.
Training:
Extract Local features (just pick SIFT, you can easily change this as OpenCV is very modular) from a subset of your training images. First detect features and then extract them. There are many tutorials on the web about this.
Train Dictionary. Helpful documentation with a reference to a sample implementation in Python (opencv_source_code/samples/python2/find_obj.py)!
Compute Histogram for each training image. (Also in the BOW documentation from previous step)
Put your image descriptors from the step above into a FLANN-Based-matcher.
Querying:
Compute features on your query image.
Use the dictionary from training to build a BOW histogram for your query image.
Use that feature to find the nearest neighbor(s).
I think you are talking about Content Based Image Retrieval
There are many research paper available on Internet.Get any one of them and Implement Best out of them according to your needs.Select Criteria according to your application like Texture based,color based,shape based image retrieval (This is best when you are working with image retrieval on internet for speed).
So you Need python Implementation, I would like to suggest you to go through Chapter 7, 8 of book Computer Vision Book . It Contains Working Example with code of what you are looking for
One question you may found useful : Are there any API's that'll let me search by image?