Questions tagged [image-recognition]

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

Filter by
Sorted by
Tagged with
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 ...
3
votes
3answers
8k views

How to “combine” two images for CNN input (classification task)?

For a classification task (I'm showing a pair of exactly two images to a CNN that should answer with 0 -> fake pair or 1 -> real pair) I am struggling to figure out how to design the input. At the ...
1
vote
1answer
42 views

Can I limit the possible choices for a computer vision framework to recognize?

To risk giving away too much info, im building a piece of hardware with the job of identifying the object in front of it. If it can only be one of three different items, how can I tell the computer ...
3
votes
1answer
651 views

Image comparison algorithm, trying to figure out how similar two “binary” forms are

I'm a student I'm completely new to this technology maybe my approach could be completely wrong, I want to create an algorithm that compares the similarity between two binarized images. I'll explain: ...
0
votes
3answers
1k views

Neural network for detecting individual human face

In past few weeks, I have learned a lot about Neural Networks. Now, I am looking forward to create a Neural Network program that can recognize individual human faces. I tried searching it online but ...
2
votes
1answer
154 views

Training a convolutional network to recognize object location

I am beginning an image analysis project to recognize images with a particular object centered on the image. If the object is at the center, I give the image a positive label, and if it is anywhere ...
-2
votes
3answers
620 views

Java - A good place to begin if over all goal is ML and Ai?

I am currently studying Java (Se && EE). I am wondering if it is a good platform for developing ML algorithms for AI. Areas of interest: facial rec - Speech Rec - understanding conversation in ...
3
votes
1answer
544 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 ...
2
votes
4answers
377 views

Training neural network for good taste in art

I'm a newbie in machine learning, so excuse me in advance). I have an idea to make NN that can estimate visual pleasantness of arbitrary image. Like you have a bunch of images that you like, you train ...
6
votes
3answers
648 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: ...
4
votes
2answers
657 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 ...
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 ...
0
votes
3answers
3k views

SSD or YOLO on arm

Is it possible to run SSD or YOLO object detection on raspberry pi 3 for live object detection (2/4frames x second)? I've tried this SSD implementation but it takes 14 s per frame. Is there anything I ...
1
vote
1answer
361 views

Is there any way can teach AI creative painting (not convert photo to paint)?

I have already know AI can paint, by using genetic algorithm, there are already lots of works such as this and this.In addition, I also know AI can compose : Song from PI: A musically plausible ...
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 ...
2
votes
4answers
3k views

CNN for detecting not just the nature of the object, but position within image as well

Consider a typical convolutional neural network like this example that recognizes 10 different kinds of objects from the CIFAR-10 dataset: https://github.com/tflearn/tflearn/blob/master/examples/...
2
votes
1answer
96 views

Feasibility of sorting a basket of clothes in the real world

I'm wondering how feasible it is to create a machine that can separate clothing from a basket. At the most basic level it would distinguish between tops, pants, button downs and socks ...
3
votes
3answers
2k views

Are Convolutional Neural Networks better than existing image recognition libraries that don't use CNNs?

Are Convolutional Neural Networks summarily better than pattern recognition in all existing image processing libraries that don't use CNN's? Or are there still hard outstanding problems in image ...
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?
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 ...
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'...
0
votes
1answer
161 views

How does Wolfram's Image Identification Project work?

Wolfram Language Image Identification Project launched an Image Identify site demo which returns the top predicted tags for the photos. How does it work, briefly? I mean what type of learning vision ...
-1
votes
1answer
213 views

How does Pinterest decipher what's on unmarked pictures and categorize them?

According to this article, Pinterest acquired VisualGraph, an image recognition and visual search technology startup. How does Pinterest apply VisualGraph technology for machine vision, image ...
1
vote
2answers
306 views

How to achieve recognition of postures and gestures?

I'd like to investigate the possibility of achieving similar recognition as it's in Honda's ASIMO robotp.22 which can interpret the positioning and movement of a hand, including postures and gestures ...
7
votes
5answers
974 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 ...
-2
votes
1answer
223 views

How many neurons would a network have after a training of 100k small images?

Is there any way to estimate how big the neural network would be after training session of 100,000 unlabeled images for unsupervised learning (like in STL-10 dataset: 96x96 pixels and color)? Not the ...
1
vote
2answers
2k views

How successfully can convnets detect NSFW images?

For example, search engine companies want to classify their image searches into 2 categories (which they already do that) such as: NSFW (nudity, porn, brutality) and safe to view pictures. How can ...
3
votes
1answer
253 views

How do Google cars recognize the traffic signs?

The paper Multi-column Deep Neural Networks for Image Classification (pages 7-8) shows an attempt at recognizing the traffic signs, with lower error rates, by using multi-column deep neural networks. ...
1
vote
1answer
72 views

What are the most challenging tasks aiming to achieve the lowest error rate?

For example there is the MNIST database which is used to test artificial neural network (ANN), however it's not so challenging, because some hierarchical systems of convolutional neural networks ...
10
votes
3answers
502 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 ...
1
vote
1answer
51 views

Do you need single or multiple networks to detect multiple faces?

Given pictures with multiple features such as faces, can single AI algorithm detect all of them, or for better reliability is it preferred to use separate instances? In other words I'm talking about ...
2
votes
1answer
55 views

Is it possible for 'unsupervised learning' model to recognize features on unlabelled images?

Is it possible for unsupervised learning to learn about high-level, class-specific features given only unlabelled images? For example detecting human or animal faces? If so, how?
4
votes
1answer
135 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 ...
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 ...
21
votes
4answers
314 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 ...
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 ...