Data Science Stack Exchange
Data Science Stack Exchange

Questions tagged [image-classification]

For questions about image classification: a decision problem where an algorithm must decide to which class ('cat', 'chair', 'tree') an input image belongs.

752 questions
8
votes
2 answers

Are there any image classification algorithms which are not neural networks?

Image classification is the task of assigning one of $n$ previously known labels to a given image. For example, you know that you will be given a couple of photos and each single image has exactly one of $\{cat, dog, car, stone\}$ in it. The…
Martin Thoma
  • 18,880
  • 35
  • 95
  • 169
2
votes
0 answers

Classifying satellite data

I have a large data set of RGB satellite data that classifies 64x64 pixel images with a spatial resolution of 10m per pixel into 10 classes (e.g. highway, industrial, river, forest). Now I want to train a model (e.g. using resnet34 with fast.ai) on…
user87759
  • 21
  • 1
2
votes
1 answer

How to handle image classification network where output classes can be subsets of one another?

For instance, if I wanted a train network that can output van truck sedan vehicle pedestrian does it make sense to only train it on van, truck, sedan, and pedestrian and then make "vehicle" a synonym of van, truck, sedan? Or does it make sense to…
John Allard
  • 131
  • 4
2
votes
1 answer

When inputting image rgb values to MLP, should I divide by 255?

I have an MLP with 3072 input nodes which are for 1024 rgb pixels. My datasets is in an array with each row representing one image and looking like this: [red_pix1, red_pix2, ..., red_pix1024, green_pix1, green_pix2, ..., green_pix1024, blue_pix1,…
Sahand
  • 143
  • 1
  • 6
1
vote
0 answers

How can i classify only-text image(petition, invoice, page of a book) and a normal image(cat,person ) as a 2 different type?

I don't think detecting text on image does work because normal images can have text on them too(like traffic sign). Is there a way to do this? I couldn't come up with an answer.
Furkan Karabulut
  • 11
  • 3
1
vote
2 answers

Train classifier on synthetic images to recognise real images

I am trying to train a classifier (let's say to classify an object X or not X). But I don't have too much real images of object X which I want to classify. So I made some synthetic images of my own using some photo editing tools, but the problem is…
Deepak Sharma
  • 121
  • 2
1
vote
0 answers

Multiple Instance Ranking Algorithm

Can somebody explain me in a simple language how multiple instance ranking algorithm works? What is ranking function? how mathematically it is expressed?
Milan Amrut Joshi
  • 165
  • 3
  • 11
1
vote
0 answers

Classification of RGB images

What is the preferred way to specify the features for image classification when the input consists of RGB images? Is it a good approach to flatten the image into a single vector (where for instance 'red' is represented by every third number) and…
Vierni
  • 11
  • 1
0
votes
1 answer

Precision or Recall when dealing with critical cases?

I have to create an AI that classifies mutliple objects in order to accept them or not inside a machine. The problem is that some objects could be really harmful to the machine if they get accepted. Should I focus on an high Precision or an high…
Clément Chrétien
  • 3
  • 1
0
votes
1 answer

Negative Feedback to GradCam method

I use EfficientNetB0 for performing image classification with one of the class as "stone countertop table", the other class is "not stone countertop table". I use the reddest part in gradCAM to put a point saying that this is the "stone countertop…
william007
  • 775
  • 1
  • 10
  • 20
0
votes
1 answer

Image Classification with two very similar and random-ish classes

I am trying to build a neural network which takes a picture of a FOREX chart (currency exchange) and outputs an "up" or "down" prediction. I'm classifying up or down based on where the stock is after one hour, and currently I have 400 examples in…
user54162
0
votes
2 answers

Classifying encrypted images

I know this question is rather broad but hopefully on topic. Are there useful references on classifying encrypted images. For example classifying cat/no cat on encrypted images. Is there efficient and accurate software for this task? Thank you! EDIT…
Richi W
  • 165
  • 2
  • 11
0
votes
2 answers

How to use CIFAR 10 Vs. CIFAR 100 for Out-Of-Distribution (OOD) performance evaluation?

CIFAR 10 vs. CIFAR 100 is the most popular benchmark dataset for Out-of-Distribution (OOD) performance evaluation. Google in their 2022 post "towards-reliability-in-deep-learning"[1] used CIFAR 10 vs. CIFAR 100 to demo their new state-of-the-art…
Emad Ezzeldin
  • 79
  • 7
0
votes
1 answer

Why CIFAR 10 Vs. CIFAR 100 is the most popular for OOD benchmark?

CIFAR 10 Vs. CIFAR 100 is the most popular dataset for the task of Out-of-Distribution performance evaluation. On the infamous "Papers-with-code" [1] CIFAR 10Vs.100 is the most used Benchmark for OOD. Also on Google's blog announcing their new…
Emad Ezzeldin
  • 79
  • 7
0
votes
1 answer

How to measure image classification model robustness?

Image Classification models trained on animal classification data like iNaturalist or iWildcam sometimes developed spurious correlations with the background. How to measure model performance limitations caused only by such spurious correlations as…
Emad Ezzeldin
  • 79
  • 7