Questions tagged [image-recognition]

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

Filter by
Sorted by
Tagged with
63
votes
9answers
5k views

How is it possible that deep neural networks are so easily fooled?

The following page/study demonstrates that the deep neural networks are easily fooled by giving high confidence predictions for unrecognisable images, e.g. How this is possible? Can you please ...
28
votes
8answers
25k 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 ...
23
votes
8answers
4k views

Is there any research on the development of attacks against artificial intelligence systems?

Is there any research on the development of attacks against artificial intelligence systems? For example, is there a way to generate a letter "A", which every human being in this world can recognize ...
21
votes
4answers
316 views

Is the pattern recognition capability of CNNs limited to image processing?

Can a Convolutional Neural Network be used for pattern recognition in a problem domain where there are no pre-existing images, say by representing abstract data graphically? Would that always be less ...
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 ...
12
votes
4answers
230 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 ...
10
votes
3answers
508 views

Are there any textual CAPTCHA challenges which can fool AI, but not human?

Are there any modern techniques of generating textual CAPTCHA (so person needs to type the right text) challenges which can easily fool AI with some visual obfuscation methods, but at the same time ...
9
votes
1answer
321 views

How much of a problem is white noise for the real-world usage of a DNN?

I read that deep neural networks can be relatively easily fooled (link) to give high confidence in recognition of synthetic/artificial images that are completely (or at least mostly) out of the ...
9
votes
1answer
106 views

Can a single neural network handle recognizing two types of objects, or should it be split into two smaller networks?

In particular, an embedded computer (with limited resources) analyzes live video stream from a traffic camera, trying to pick good frames that contain license plate numbers of passing cars. Once a ...
8
votes
2answers
122 views

Can machine learning algorithms (CNNs?) be used/trained to differentiate between small differences in details between images?

I was wondering if machine learning algorithms (CNNs?) can be used/trained to differentiate between small differences in details between images (such as slight differences in shades of red or other ...
8
votes
3answers
250 views

Detect visual attention area in an image

I'm trying to detect the visual attention area in a given image and crop the image into that area. For instance, given an image of any size and a rectangle of say LxW dimension as an input, I would ...
7
votes
5answers
1k views

How can action recognition be achieved?

For example, I would like to train my neural network to recognize the type of actions (e.g. in commercial movies or some real-life videos), so I can "ask" my network in which video or movie (and at ...
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 ...
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 ...
6
votes
1answer
169 views

How good is AI at generating new, unseen [visual] examples?

By new, unseen examples; I mean like the animals in No Man's Sky. A couple of images of the animals are: So, upon playing this game, I was curious about how good is AI at generating visual ...
6
votes
2answers
103 views

How does rotating an image and adding new 'rotated classes' prevent overfitting?

From Meta-Learning with Memory-Augmented Neural Networks in section 4.1: To reduce the risk of overfitting, we performed data augmentation by randomly translating and rotating character images. ...
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 ...
6
votes
3answers
663 views

Machine Learning hardware usage in embedded applications

I've been reading a lot about hardware development and implementation for AI/ML, mainly about Deep Learning, and I have a question about its usage. From what I understand, there are 2 stages for DL: ...
5
votes
2answers
140 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?
5
votes
3answers
203 views

How to make convnets aware what the image actually is, not what is depicted on it?

I've uploaded a picture to Wolfram's ImageIdentify of graffiti on the wall, but it recognized it as 'monocle'. Secondary guesses were 'primate', 'hominid', and 'person', so not even close to 'graffiti'...
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 ...
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 (...
5
votes
2answers
216 views

Why is image recognition a key function of AI?

Image recognition, in the context of machine vision, is the ability of software to identify objects, places, people, writing and actions in images. Computers can use machine vision technologies in ...
5
votes
2answers
151 views

Predicting housing values with neural network (was: Variable Number of Inputs to Neural Networks)

A dataset is given which contains textual data (year, number of rooms, location) and visual data (an jpeg image of the house). The neural network has the task to predict the price of the property. As ...
5
votes
2answers
267 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
182 views

Image Classification

I am currently working on a project to classify snake types separately using an image of the snake. I need to train a module to classify snake images, but the problem is there are only a small number ...
4
votes
1answer
136 views

Are there any microchips specifically designed to run ANNs?

I'm interested in hardware implementation of ANNs (artificial neural networks). Are there any popular existing technology implementations in form of microchips which are purpose designed to run ...
4
votes
1answer
73 views

Is it possible to make a 'forked path' neural network?

I want to make a network, specifically a CNN for image recognition, that takes an input, processes it the same way for several layers, and then at some point splits before coming to two different ...
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 ...
4
votes
2answers
660 views

Image recognition

I am looking for a solution that I can use with identifying cars. So I have a database with images of cars. About 3-4 per car. What I want to do is upload a picture to the web of car(Picture taken ...
4
votes
2answers
393 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 ...
4
votes
1answer
57 views

Optimizing image recognition results for unknown labels

I’m training a network to do image classification on zoo animals. I’m a software engineer and not an ML expert, so I’ve been retraining Google’s Inception model and the latest models is trained ...
4
votes
1answer
321 views

Identifying car model via deep learing

Is there any project or example for a software identifying cars? Situation: I got multiple angle shots in high resolution from a car. I want the algorithm to tell me "This is a Mercedes SLK" or "This ...
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, ...
4
votes
1answer
44 views

How to compare the training performance of a model on different data input?

So I have a deep learning model and three data sets (images). My theory is that one of these data sets should function better when it comes to training a deep learning model (meaning that the model ...
4
votes
2answers
220 views

How good is facial recognition exployed in public surveillance

What methods are used for facial recognition in public surveillance? Ideally, an answer would point to the software, algorithms or specifications being used. How can those be fooled? Fake or ...
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 ...
4
votes
0answers
33 views

Get the position of an object, out of an image

I have some images with a fixed background and a single object on them which is placed, in each image, at a different position on that background. I want to find a way to extract, in an unsupervised ...
4
votes
0answers
39 views

How do I denoize a microscopic image?

I'm working in a computer vision project, where the goal is to detect some specific parasites, but now that I have the images, I noticed that they have a watermark that specifies the microscope ...
4
votes
1answer
27 views

An approach on reading musical notes from photos

I was looking around, a promising approach was this: https://github.com/mpralat/notesRecognizer the problem is: it doesn't seem good enough. One should be able to read musical notes with lower ...
3
votes
1answer
1k views

Is the QuickDraw with Google neural net a convolutional neural network?

Does anyone know, or can we deduce or infer with high probability from its characteristics, whether the neural network used on this site https://quickdraw.withgoogle.com/ is a type of convolutional ...
3
votes
2answers
120 views

What does it mean “derivative of an image”?

I am reading a book about OpenCV, it speaks about some derivative of images like sobel. I am confused about image derivative! What is derived from? How can we ...
3
votes
1answer
541 views

Regarding Yolo and Keras

I'm trying to implement YOLO (tiny version, v1) into Keras framework. For the past two days, I've been relentlessly digging through Github and the likes in order to ...
3
votes
3answers
281 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)...
3
votes
2answers
298 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 ...
3
votes
1answer
78 views

How to apply a kernel to an image?

As I know, if we consider a 3*3 kernel, we should add a padding of 1px to the source image(if we want to have effect on whole of the image), then we start to put the kernel in upper-left side of the ...
3
votes
1answer
489 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 (...
3
votes
1answer
551 views

Detect street and sidewalk surface in aerial imagery (neural network)

I would like to detect street and sidewalk surface in a very detailed (0.075m/pix) USGS High Resolution Orthoimagery which basically means image segmentation with two classes. Places in question are ...
3
votes
3answers
121 views

Is it possible for visual systems in AI to have Inattentional Blindness?

Inattentional Blindness is common in humans (see: https://en.wikipedia.org/wiki/Inattentional_blindness ). Could this also be common with machines built with artificial vision?
3
votes
1answer
49 views

Mnist CNN Architecture

In this tutorial from Jeremy Howard: What is torch.nn really? he has an example towards the end where he creates a CNN for mnist. In nn.Conv2d he makes the ...