The Stack Overflow podcast is back! Listen to an interview with our new CEO.

Questions tagged [image-recognition]

For questions related to image recognition in the context of AI.

Filter by
Sorted by
Tagged with
1
vote
0answers
44 views

Feature set out of grayscale Images for training a neural network?

Previously I had trained a Neural Networkupon 20,000 character images. This Neural Net generally works well, it uses ...
3
votes
1answer
448 views

Neural network returns about the same output(mean) for every input

I tried to build a neural network from scratch to build a cat or dog binary classifier using a sigmoid output unit. I seem to get the output value around 0.5(+/- 0.002) for every input. This seems ...
1
vote
0answers
37 views

Best way to predict future frame of movie or game?

Using a neural network the method seems to be that you end up with a probability for each possible outcome. To predict the next frame in a monochrome movie of size 400x400 with 8 shades of gray, it ...
12
votes
4answers
225 views

What are some tactics for recognizing artificially made media?

With the growing ability to cheaply create fake pictures, fake soundbites, and fake video there becomes an increasing problem with recognizing what is real and what isn't. Even now we see a number of ...
1
vote
1answer
82 views

Extracting one class from a pretrained Convolutional Neural Network

I am new to deep learning and computer vision. I have a problem where i use yolo algorithm (https://pjreddie.com/) to detect objects. In the original paper, they define the output to recognize 80 ...
1
vote
1answer
695 views

Intel Movidius Neural Stick vs TensorFlow

I wanted to start developing a project with image recognition. I want to know the difference between the Intel Movidius Neural Compute Stick and TensorFlow to develop this project Any help would ...
28
votes
8answers
24k views

In a CNN, does each new filter have different weights for each input channel, or are the same weights of each filter used across input channels?

My understanding is that the convolutional layer of a convolutional neural network has four dimensions: input_channels, filter_height, filter_width, number_of_filters. Furthermore, it is my ...
3
votes
1answer
243 views

Is color information only extracted in the first input layer of a convolutional neural network?

In a convolutional neural network (CNN), since the RGB values get multiplied in the first convolutional layer, does this mean that color is essentially only extracted in the very first layer? ...
2
votes
3answers
108 views

Create captions based on a series of images

I'd like to generate subtitles for a silent film. Is there an open source project out there capable of creating captions based on a series of images (such as a scene from a movie)? EDIT: thanks for ...
1
vote
0answers
30 views

How to apply EOT algorithm to 3d model

Many of you have probably seen the turtle from LabSix that gets mistaken for a rifle in Google's InceptionV3 image classifier. I read the paper and I understand how they apply EOT to 2d images and on ...
1
vote
1answer
31 views

Executing trained image classification model for video

I've been working with vanilla feed forward neural networks and have been researching the convolutional neural network literature. Thus far I've have not encountered how often the model is executed in ...
2
votes
1answer
43 views

In number classification using neural network, is training with edge image better than gray image?

i'm trying to identify numbers and letters in license plate. License plate images are taken at different lighting condtion and converted to gray image. My concern with type of data for training is: ...
0
votes
2answers
75 views

How to know what kind of memory is stored in the connection weights?

So, I have seen few pictures re-created by a Neural Network or some other Machine Learning algorithm after it has been trained over a data set. How, exactly is this done? How are the weights ...
5
votes
3answers
3k views

How can 3 same size CNN layers in different ordering output different receptive field from the input layer?

Below is a quote from CS231n Prefer a stack of small filter CONV to one large receptive field CONV layer. Suppose that you stack three 3x3 CONV layers on top of each other (with non-linearities ...
1
vote
1answer
494 views

How are kernel's input values initialized in a CNN network?

I am currently learning about CNN's and I am confused on how filter/kernels are initialized beside their size? Say if you want a filter of 3x3 how are the inner values initialized a the start? http:/...
3
votes
1answer
109 views

If neurons are only defined for values between 0 and 1, how does ReLU differ from the identity?

I'm struggling to understand the underlying mechanics of CNNs so any help is appreciated. I have a network with a ReLU activation function which does perform signifigantly better than one with sigmoid....
3
votes
1answer
74 views

How can computers beat humans at image recognition?

For supervised learning, humans have to label the images computers use to train in the first place, so the computers will probably get wrong the images that humans get wrong. If so can computers beat ...
4
votes
2answers
389 views

Viola Jones Algorithm

Can Viola Jones algorithm be used to detect the facial emotion. Actually it was used in creating harr-cascade file for object and facial detection, but what confused me is whether it can be used to ...
2
votes
2answers
91 views

Machine learning and machine generated content conflict problem

Machine learning and NN trainings as a part of ML is based on data that was gotten from real world and inserted into virtual space by humans. Meanwhile NN are also used for data generation. Each year ...
6
votes
2answers
3k views

How to implement an “unknown” class in NN classification?

For example I need to detect classes for MNIST data. But I want to have not 10 classes for digits but also I want to have 11th class "not a digit". So that any letter (except "O" of course:) ), any ...
2
votes
0answers
169 views

Extracting specific features using HOG

I am using HOG (Histogram of Oriented Gradients) for car detection from a video. I have used the Matlab function extractHOGFeatures() , it has given me a feature ...
1
vote
0answers
698 views

Object detection in video

I have a video which is capture from a moving car and video showing plenty of details like pools, human, cars/buses, roads, etc, etc. The video I am playing in unity3d and camera Showing that video ...
2
votes
1answer
89 views

Measuring logs from a picture

I am interested in learning more about the capabilities of AI, one of my ideas with practical functionality is using images of the rear of a log hauling truck to measure the individual logs using AI. ...
3
votes
1answer
750 views

Trying to understand VGG convolution neural networks architecture

Trying to understand the VGG architecture and I have these following questions. I understand the general understanding of increasing filter size is because we are using max pooling and so its image ...
4
votes
1answer
181 views

How to identify the face of a certain customer in a grocery store?

How would you solve the problem of identifying certain customer in a grocery store? Suppose our client is already signed-up on our website with an unique ID given to him. To come in to the store, ...
3
votes
1answer
552 views

Real time image processing for object recognition using security cameras

I was thinking, what if we could combine Artificial Intelligence (Neural network for image recognition), computer hardware and a security camera for identify any breaking into our backyard at 12:00am -...
2
votes
2answers
65 views

Identifying if an image contains an object with very small (five image) training data set

Let's suppose I have 5 images, all of which I assure you are of the same item, but from various angles and perhaps different lighting conditions. I now supply you with an additional image, and I want ...
3
votes
3answers
276 views

Would convolutional NN recognize patterns in encoded images?

I have a set of images that I already trained a CNN to classify successfully. I wonder if it would be possible to encode the images (using XOR in combination with a key of the same length as the image)...
4
votes
1answer
2k views

Reading a value of a real gauge

I have a simple gauge displaying analog values ranging from 0 to 4. Here is an image of the gauge. Unfortunately there is no way to get a analog or digital signal for the value. How do I read the ...
1
vote
1answer
55 views

Is there a technical name for image classification on amount instead of class?

Is there a technical term for an image classifier that classifies on a single class but is classifying on an amount like how full a glass of water is rather than different classes?
1
vote
0answers
47 views

Can Image Recognition used to find height of a person whole, torso, legs etc

Image recognition can be used to classify images. But I wanted to find few parameters like height of person, his legs, his hand etc. Will CNN helpful for this type of output ?
2
votes
3answers
208 views

How would AI prioritize situational ethics?

There's a real possibility that self driving cars become more than just a high tech novelty and they start changing the market. As seen in Logan, self driven commercial freight might be among the ...
2
votes
0answers
180 views

Can anybody explain such behavior of accuracy and loss of my Net(caffe)?

I used this project for example(framework - caffe, arhitecture of net - mod of AlexNet, 400 images are used for training). I have this result: or this: Solver: ...
3
votes
1answer
1k views

How to detect the empty parking spots?

I have some images of the empty parking as shown below. I 'd like to use deep learning to extract the parking spots. But in the beginning,am confused whether there are several ways to do the ...
2
votes
2answers
4k views

Cropping image using ML?

Is there a way to train AI to find aspecific line or symbol in a image and crop it? OpenCV scripts finds a face and crops it: how can I add my annotations? Lest say I have a image like this: ...
3
votes
1answer
481 views

Intuitively understanding translational invariance in CNNs

I'm currently in the process of learning about using CNNs in image recognition. Many of the different resources I read that were explaining the motivation referred to the fact that these networks are (...
14
votes
3answers
21k views

How to handle images of large sizes in CNN?

Suppose there are 10K images of sizes 2400 x 2400 are required to use in CNN.Acc to my view conventional computers the people use will be of use. Now the question is how to handle such large image ...
3
votes
1answer
591 views

Image Recognition and Orientation Detection

Hypothetically, the symbol (Triangle) is sticked to an item and i need to find and recognize that symbol and try to calculate the orientation of the item it is sticked into. In degrees. How would you ...
5
votes
2answers
265 views

How can I use Neural Network in motion identification

I'm quite new to image processing and AI. But I have the expertise to create a network that can be used in object detection and recognition. Most of the time I've used ANN or Naive Bayes. Now, I want ...
4
votes
2answers
151 views

As a starter: what is the form of training data for image processing

What we are doing in the image processing training. We are storing some form of data which is going to act as the knowledge or experience of the system. In which form can the system store it's ...
1
vote
0answers
126 views

Converting pictures into numerical values

I am working to make my first trained model for image recognition, using the programming language R. First I am attempting to make a function that takes a PNG-image as input, resizes it to 128x128 ...
1
vote
1answer
34 views

Do images submitted to a segmentation network after training need to be the same size as the training images?

I have not seen this explicitly stated anywhere so I was curious. Say I have network trained to meet my segmentation needs using 250x250 images. After this training is complete and I wish to submit ...
3
votes
2answers
297 views

Is there a computer vision service for classifying images on a fixed array of images provided by me?

I was checking services like Microsoft Azure's Cognitive Services Computer Vision API and Google's Vision API and they are amazing. I was wondering if these services, or any other cloud service for ...
0
votes
1answer
77 views

What are the pros and cons of using a spatial transformation network to predict the next video frame?

I've read through a few papers on next frame prediction from a sequence of frames and several of them use spatial transformations (STNs). See this as an example. I want to know what are the pros and ...
5
votes
2answers
138 views

Is algorithmic bias due to the training dataset used?

I recently read about algorithmic bias in facial recognition. Is algorithmic bias due to the training dataset used, or is it due to something else?
0
votes
2answers
240 views

Feature extraction other than convolutions for images?

Are there approaches other than convolutions to learn features from images? Has there been any research to use approaches such as hashing (e.g. p-hash, ...
7
votes
1answer
107 views

What algorithms are used for segmentation and classification of non solid regions in an image?

In the process of segmentation, pixels are assigned to regions based on features that distinguishes them from the rest of the image. Value Similarity and Spatial Proximity, for example, are two ...
1
vote
1answer
78 views

Web based face recognition [closed]

I am building a smart Mirror where it displays a website and the website would have voice recognition and face recognition. For voice recognition/voice commands I will be using a JavaScript library ...
5
votes
1answer
154 views

Is it feasible to train a Machine Learning Model (with image inputs) in an average personal computer?

There are lots of examples of machine learning systems that can recognize objects and extract other information from images with very high precision. To train the models of such systems is necessary (...
7
votes
3answers
5k views

How do we choose the kernel size depending on the problem?

Obviously, finding suitable hyper-parameters for a neural network is a complex task and very problem or domain-specific. However, there should be at least some "rules" that hold most times for filter ...