I know this question is likely to be closed as "opinion based", but I could not find any resource online and every link pointed in asking on Stack Overflow, so please be patient.
I'm trying to understand if Tensorflow is the right tool for object detection. I'm not talking about classification, but real object detection and recognition.
My use case is the following: given image A (live photo), find the matching one inside a catalogue of thousand of different images.
For example: live scanning of a supermarket product, find the matching one inside an high res catalogue of images. I'm not interested to know if the product is a shoe or a toothpaste, I want to know the "most matching" image (ie Prada model X or Colgate mint flavoured).
I already have a working script developed few years ago with OpenCV, using SURF feature detection with FLANN, but I wanted to know if there's a better tool for the job.
Can anyone point me in the right direction?
While I'm unsure whether it provides a better solution than any you've already implemented, TensorFlow, and deep learning in general, can indeed be used for this purpose. A neural network can be created which takes an image as input and outputs a numeric vector. The Euclidean distance between vectors can be used to determine the similarity between different images, an approach which has been applied effectively for facial recognition (see this paper).
For a starting point in implementing this solution using TensorFlow, see this tutorial.
Related
I am currently testing out custom object detection using the Tensorflow API. But I don't quite seem to understand the theory behind it.
So if I for example download a version of MobileNet and use it to train on, lets say, red and green apples. Does it forget all the things that is has already been trained on? And if so, why does it then benefit to use MobileNet over building a CNN from scratch.
Thanks for any answers!
Does it forget all the things that is has already been trained on?
Yes, if you re-train a CNN previously trained on a large database with a new database containing fewer classes it will "forget" the old classes. However, the old pre-training can help learning the new classes, this is a training strategy called "transfert learning" of "fine tuning" depending on the exact approach.
As a rule of thumb it is generally not a good idea to create a new network architecture from scratch as better networks probably already exist. You may want to implement your custom architecture if:
You are learning CNN's and deep learning
You have a specific need and you proved that other architectures won't fit or will perform poorly
Usually, one take an existing pre-trained network and specialize it for their specific task using transfert learning.
A lot of scientific literature is available for free online if you want to learn. you can start with the Yolo series and R-CNN, Fast-RCNN and Faster-RCNN for detection networks.
The main concept behind object detection is that it divides the input image in a grid of N patches, and then for each patch, it generates a set of sub-patches with different aspect ratios, let's say it generates M rectangular sub-patches. In total you need to classify MxN images.
In general the idea is then analyze each sub-patch within each patch . You pass the sub-patch to the classifier in your model and depending on the model training, it will classify it as containing a green apple/red apple/nothing. If it is classified as a red apple, then this sub-patch is the bounding box of the object detected.
So actually, there are two parts you are interested in:
Generating as many sub-patches as possible to cover as many portions of the image as possible (Of course, the more sub-patches, the slower your model will be) and,
The classifier. The classifier is normally an already exisiting network (MobileNeet, VGG, ResNet...). This part is commonly used as the "backbone" and it will extract the features of the input image. With the classifier you can either choose to training it "from zero", therefore your weights will be adjusted to your specific problem, OR, you can load the weigths from other known problem and use them in your problem so you won't need to spend time training them. In this case, they will also classify the objects for which the classifier was training for.
Take a look at the Mask-RCNN implementation. I find very interesting how they explain the process. In this architecture, you will not only generate a bounding box but also segment the object of interest.
I'm a beginner in computer vision. Could anyone tell me whether what I'm considering to do is correct or not? I wanted to detect a certain cyst in teeth. So my dataset consists of a part of the dental x-ray that contains that cyst. I train my model with these pictures. The one with the colored area contains cyst (infected teeth), and the one below it is the uninfected teet.
Image with cyst
Uninfected teeth
After training my model, I want to use it on a full dental x-ray, and determine if this picture has the cyst or not. A full dental x-ray is shown below.
Full dental X-Ray
Does this work? Or I'm completely wrong?
Instead of treating this as an object detection problem, you would get far better results if you were to treat this as a classification problem.
There are already various architectures for such classification tasks.
There are various architectures in TensorFlow to get you started.
Take a look at this. If you have enough data you can train them from scratch instead of using pre-trained weights
Note - The architecture provided in TensorFlow will almost always give you better results than the architectures that you create.
Object detection is suitable for cases where you have well-defined objects. If you take a look at recently published research papers you can see that these types of problems are considered as classification problems instead of object detection problems.
I haven't tried Tensorflow yet but still curious, how does it store, and in what form, data type, file type, the acquired learning of a machine learning code for later use?
For example, Tensorflow was used to sort cucumbers in Japan. The computer used took a long time to learn from the example images given about what good cucumbers look like. In what form the learning was saved for future use?
Because I think it would be inefficient if the program should have to re-learn the images again everytime it needs to sort cucumbers.
Ultimately, a high level way to think about a machine learning model is three components - the code for the model, the data for that model, and metadata needed to make this model run.
In Tensorflow, the code for this model is written in Python, and is saved in what is known as a GraphDef. This uses a serialization format created at Google called Protobuf. Common serialization formats include Python's native Pickle for other libraries.
The main reason you write this code is to "learn" from some training data - which is ultimately a large set of matrices, full of numbers. These are the "weights" of the model - and this too is stored using ProtoBuf, although other formats like HDF5 exist.
Tensorflow also stores Metadata associated with this model - for instance, what should the input look like (eg: an image? some text?), and the output (eg: a class of image aka - cucumber1, or 2? with scores, or without?). This too is stored in Protobuf.
During prediction time, your code loads up the graph, the weights and the meta - and takes some input data to give out an output. More information here.
Are you talking about the symbolic math library, or the idea of tensor flow in general? Please be more specific here.
Here are some resources that discuss the library and tensor flow
These are some tutorials
And here is some background on the field
And this is the github page
If you want a more specific answer, please give more details as to what sort of work you are interested in.
Edit: So I'm presuming your question is more related to the general field of tensor flow than any particular application. Your question still is too vague for this website, but I'll try to point you toward a few resources you might find interesting.
The tensorflow used in image recognition often uses an ANN (Artificial Neural Network) as the object on which to act. What this means is that the tensorflow library helps in the number crunching for the neural network, which I'm sure you can read all about with a quick google search.
The point is that tensorflow isn't a form of machine learning itself, it more serves as a useful number crunching library, similar to something like numpy in python, in large scale deep learning simulations. You should read more here.
I am new to machine learning field and based on what I have seen on youtube and read on internet I conjectured that it might be possible to count pedestrians in a video using tensorflow's object detection API.
Consequently, I did some research on tensorflow and read documentation about how to install tensorflow and then finally downloaded tensorflow and installed it. Using the sample files provided on github I adapted the code related to object_detection notebook provided here ->https://github.com/tensorflow/models/tree/master/research/object_detection.
I executed the adapted code on the videos that I collected while making changes to visualization_utils.py script so as to report number of objects that cross a defined region of interest on the screen. That is I collected bounding boxes dimensions (left,right,top, bottom) of person class and counted all the detection's that crossed the defined region of interest (imagine a set of two virtual vertical lines on video frame with left and right pixel value and then comparing detected bounding box's left & right values with predefined values). However, when I use this procedure I am missing on lot of pedestrians even though they are detected by the program. That is the program correctly classifies them as persons but sometimes they don't meet the criteria that I defined for counting and as such they are not counted. I want to know if there is a better way of counting unique pedestrians using the code rather than using the simplistic method that I am trying to develop. Is the approach that I am using the right one ? Could there be other better approaches ? Would appreciate any kind of help.
Please go easy on me as I am not a machine learning expert and just a novice.
You are using a pretrained model which is trained to identify people in general. I think you're saying that some people are pedestrians whereas some other people are not pedestrians, for example, someone standing waiting at the light is a pedestrian, but someone standing in their garden behind the street is not a pedestrian.
If I'm right, then you've reached the limitations of what you'll get with this model and you will probably have to train a model yourself to do what you want.
Since you're new to ML building your own dataset and training your own model probably sounds like a tall order, there's a learning curve to be sure. So I'll suggest the easiest way forward. That is, use the object detection model to identify people, then train a new binary classification model (about the easiest model to train) to identify if a particular person is a pedestrian or not (you will create a dataset of images and 1/0 values to identify them as pedestrian or not). I suggest this because a boolean classification model is about as easy a model as you can get and there are dozens of tutorials you can follow. Here's a good one:
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/3_NeuralNetworks/neural_network.ipynb
A few things to note when doing this:
When you build your dataset you will want a set of images, at least a few thousand along with the 1/0 classification for each (pedestrian or not pedestrian).
You will get much better results if you start with a model that is pretrained on imagenet than if you train it from scratch (though this might be a reasonable step-2 as it's an extra task). Especially if you only have a few thousand images to train it on.
Since your images will have multiple people in it you have a problem of identifying which person you want the model to classify as a pedestrian or not. There's no one right way to do this necessarily. If you have a yellow box surrounding the person the network may be successful in learning this notation. Another valid approach might be to remove the other people that were detected in the image by deleting them and leaving that area black. Centering on the target person may also be a reasonable approach.
My last bullet-point illustrates a problem with the idea as it's I've proposed it. The best solution would be to alter the object detection network to ouput both a bounding box per-person, and also a pedestrian/non pedestrian classification with it; or to only train the model to identify pedestrians, specifically, in the first place. I mention this as more optimal, but I consider it a more advanced task than my first suggestion, and a more complex dataset to manage. It's probably not the first thing you want to tackle as you learn your way around ML.
I am a newbie in TensorFlow.
Currently, I am testing some classification's examples "Convolutional Neural Network" in the TensorFlow website, and it explains how to classify input images into pre-defined classes, but the problem is: I can't figure out how to locate multiple objects in the same image. For example, I had an input image with a cat and dog and I want my graph to display in the output that there are both of them "a cat and a dog" in the image.
Great question. Detecting multiple objects in the same image boils is essentially a "segmentation problem". Two nice and popular algorithms are
YOLO (You Only Look Once), and SSD(Single Shot Multibox Detector). I included links to them at the bottom.
I would watch a few videos on how YOLO works, and see if you grasp the idea. Then read the paper on SSD, and see if you get why this algorithm is even faster and more precise.
Both algorithms are single-pass: they only look at the image "once" and predict bounding boxes for the categories they spot. There are more precise algorithms, but they are slower (they first pick many spots they want to look, and then run a classifier on only that spot. The result is that they run this classifier many times per image, which is slow).
As you stated you are a newbie to Tensorflow, you can try this code other people made: https://github.com/thtrieu/darkflow . The very extensive readme shows you how to get started on your own dataset.
Good luck, and let us know if you have other questions, or if these algorithms do not fit your use-case.
YOLO 9000 (https://pjreddie.com/darknet/yolo/)
SSD (Single shot multibox detector) (https://arxiv.org/abs/1512.02325)
A naive approach for what you are trying to do would be to classify parts of the image independently.
But there are some better techniques for object detection. Actually, there is the TensorFlow Object Detection API, which gives you access to the most common object detection methods like Faster R-CNN or SSD.