Questions tagged [image-recognition]

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

Filter by
Sorted by
Tagged with
1 vote
2 answers
49 views

How to detect outlier images?

Before I describe my challenge, I want to point out that I have searched extensively online for "outlier image detection", "anomaly images detection", etc., but all returned ...
  • 121
0 votes
2 answers
20 views

Higher accuracy in the test set than in the training set

Hi I'm trying to train an ANN model to classify images containing these characters: 0,1,2,3,4,T,X,S eg. etc... so something like the classification of records of the MNIST dataset but using my ...
0 votes
0 answers
11 views

How does FaceNet (or similar) bootstrap new faces?

In a metric learning system the system can be trained on known examples such that common classes (faces) are clustered together and separated from each other as much as possible. If triplet loss is ...
  • 121
0 votes
0 answers
24 views

Graph recognition with machine learning?

Let's say we have drawing of graphs (in the graph theory sense). Is it possible to use machine learning to convert such drawing into a format that is understandable by computers, such as a list of ...
  • 261
0 votes
0 answers
18 views

Best methods to square rectangular images for OR

I've read previous posts that assert using one of these solutions: crop and or resize nn input size independent In my case, I am using some tensorflow models and afaik they report a fixed size like ...
  • 79
1 vote
1 answer
35 views

How to deal with varying number of input images?

Im trying to use Deep-Learning to recognize breast cancer on Mammography Images. But in the dataset every patient has a different (1-4) number of images taken. How can i deal with that? Generally i ...
1 vote
1 answer
136 views

Should a CNN generalize to arbitrary positions in the data?

I have trained a CNN on one dimensional data that is the power spectral density (PSD) of a $N$ different classes of signals ($N=4$). Each of the $N$ signals has a different spectral shape (not shown ...
0 votes
1 answer
50 views

Why didn't my convolutional image classifier network learn anything?

So I am trying to make a CNN image classifier that has two classes, good and bad. The aim is to look at photoshoot pictures that can be found on fashion sites and find the "best one". I ...
  • 101
0 votes
1 answer
34 views

How can I use CNN to make a cumulative count of the number of occurrences of each of the different objects in all the images in the test set?

Let's say there are three images in the test set, the first with three triangles, the second with two triangles and two circles, the third with four circles and two squares, and the final tally is a ...
0 votes
0 answers
19 views

How to model a few shot image classification task similar to a traditional supervised one?

I want to train an image classification model. I have 10 classes with 15 images per class. Since the data is very less, I thought of modeling the problem as a few-shot image classification task and ...
2 votes
1 answer
101 views

Image classification problem with multiple right classes

I have a use case where the model needs to detect fabricdefects. There are 15+ different kinds of defects. In one image there can be multiple defects present. The straight forward solution for this ...
0 votes
1 answer
36 views

Are there metrics for image complexity for informing neural network design?

BACKGROUND: I am trying to think of rational approaches to designing deep learning models for image classification. One thought is to quantify the complexity of image datasets and use that to inform ...
2 votes
1 answer
162 views

Is there an image classification dataset where the class depends on spatial relations?

My question is pretty much the one asked above. To clarify a bit further: I have only found datasets that do object localization and that also have relations between the objects annotated (like: "...
0 votes
0 answers
11 views

Real-Time banknote recognition dataset

My project is about banknote recognition in real-time scenarios, so for the dataset, do I need to snap each banknote one by one, or do I need to record video and extract images from the videos I take?
0 votes
1 answer
30 views

What kind of neural network and GPU should I use to classify images into > 10 000 classes?

I am trying to developp an image classifier that would have more than 10 000 classes but I don't know what kind of neural network I should use ? Some Other questions arise from this one : How big ...
3 votes
2 answers
146 views

Examples where AI fails in revealing ways

For a short presentation about AI I am looking for examples where AI failed and therby shows the limits of itself. I remember there was one examples, where an image classifier was given an image of ...
  • 143
0 votes
0 answers
54 views

Mapping an image to a well defined object using OpenCV

I am completely new to computer vision and I am working on a small hobby project. The goal is to use camera footage of a foosball table to map the image to already well defined object geometry with ...
1 vote
1 answer
81 views

Why does my neural network perform different on the same images during training and testing?

I use tensorflow keras to build a neural network that classifies images of covid-19 rapid tests into three classes (Negative, Positive, Empty). During training the ...
0 votes
0 answers
43 views

At what size does a picture become unusable for facial recognition?

Lets say i have a portrait photo of which the face it contains covers about 90% of the entire photo. I want to be able to detect the face in this photo using facial recognition but i also want to ...
  • 123
0 votes
0 answers
13 views

Image suggestions using feature extractor + ANN index

I am trying to build an image suggestion engine using resnet151 as a feature extractor and right now I am testing Annoy and Faiss as the ANN. I am having some issues with images that have similar ...
0 votes
2 answers
577 views

ImageNet Dataset (for PyTorch VGG16 training)

Please can someone describe how to properly obtain the ImageNet dataset (to be precise the ImageNet 2012 Classification Dataset). What I attempted so far The ImageNet webpage refers the user to ...
0 votes
0 answers
38 views

Multiclass image classification - what approach to use and which models to consider?

I'm working on an image classification project and I need to train a multiclass, multilabel classifier. The dataset is large and some of the images are mislabeled (for a given class, some labels are ...
0 votes
0 answers
164 views

How should classification on small images be done?

I want to create an image classifier that classifies very small images (16-32 pixels/side) into around 200 categories. Every category has exactly one image that defines it. The classifier should ...
  • 101
0 votes
0 answers
30 views

Different Kernel Initializers in my prediction layer with Transfer Learning could affect performance?

So I have this model right here and the task is to classify 3 labels.: ...
1 vote
3 answers
343 views

Can an AI generated image (such as pic of human face) be detected that it's AI generated?

AIs are getting better and better at creating images and art. Some of the stuff is almost impossible to be detected by the naked eye. But what about programs and algorithms? Instead of creating an ...
0 votes
0 answers
41 views

Which layers are doing image segmentation on AutoEncoders/U-NET?

While I was researching for transfer learning, I saw that people are replacing encoders with VGG-16 weights and only training the decoder part of the network. But in some representations (like This) ...
  • 1
0 votes
0 answers
44 views

How to optimize input image tensor, to best fit image classifier, for specific target class?

Assume that we got pretrained image classifier, and we want to then optimize some input image tensor for it, that for given class, the output of classifier will match. How to do this for example in ...
  • 101
0 votes
1 answer
104 views

How can I reduce the loss? Why do I have the high loss and why do I have the gradient?

I want to classify some images (there are about 200.000 images) with a CNN. But I get a very high loss, see figures: Loss over the hole training run Loss for each epoch It's confused me, that there ...
0 votes
1 answer
482 views

For an image (of any object), how to find its location in the other image(s) which contains it, given there are no labels or annotations for any image

Problem Statement: I am given 2 sets of images. All the images in both sets are without annotations and labels. First set : a set of images of the grocery store shelves (captured in the grocery stores)...
0 votes
0 answers
67 views

How would you fine tune the model on images of larger size?

Let's say you have trained a model for image classification, on images of a defined size (H x W x Ch). How would you fine tune the model on images of larger size?
  • 1
1 vote
0 answers
236 views

How do I deal with a dataset of Images with variable sizes (width and height) when doing Image Classification?

I have a dataset in which the images which don't have the same width and height. How do I perform Image Classification with such images? I am trying as much as possible to steer away from image ...
0 votes
1 answer
41 views

Image Recognition Method, calculate deviation from rectangular grid

I have a set-up which creates pictures of a grid that is a bit bend towards the ends, and I need some kind of program that can calculate the deviation, resp. it just needs to be some kind of indicator,...
  • 11
0 votes
0 answers
57 views

How to convert prediction probabilities of 2D images (initially 3D image) to 3D image predictions?

Classification: binary Model: CNN (ResNet50V2) During our research we've had 91x109x91 images (3-dimensional). We've used 2D CNN to train and evaluate our images and make predictions on labelled cases,...
1 vote
1 answer
47 views

Does Using the Same Background for Binary Classification Improve Model Accuracy?

I am training a CNN that detects if a there is a pot of boiling water vs if there is a pot of boiling water with pasta inside. My hypothesis is that having the same background for both a positive and ...
1 vote
0 answers
28 views

Is AI able to detect major changes in pairs of images while ignoring minor changes (due to tree crown growth, color and perspectiv disstortions)?

I'm starting to get involved into machine learning but still have some troubles to select the approriate tool or algorithm. My basic task is to compare remotly sensed images of individual trees at two ...
  • 11
1 vote
2 answers
562 views

Musical notes interpretation [closed]

Musical notes Musical notes videos Piano Can AI, Machine learning, Data science, Computer vision, image processing technologies assist in interpreting musical notes ? Input dataset : Musical notes ...
1 vote
0 answers
71 views

Detecting cheats visually using AI

I really like to play my favorite 3D shooter game online. Unfortunately, it is really old and cheat protection isn't really common there, but cheaters are! It is very frustrating, because it really ...
  • 11
0 votes
1 answer
645 views

What's the best model to use for CNN(deep learning) regression task for small image dataset?

What are the best Deep learning models(with how many layers) to use in a regression task for a custom dataset containing around 100 images of only one object per image which is more or less ...
1 vote
1 answer
84 views

Validity of ImageNet for measurement of the model performance

ImageNet dataset is an established benchmark for the measurement of the performance of CV models. ImageNet involves 1000 categories and the goal of the classification model is to output the correct ...
1 vote
0 answers
179 views

What exactly do gradient-based saliency map tell us?

As far as I understand, gradients are supposed to tell us 1) the magnitude and 2) direction, to update a parameter such as to minimize the loss function. Regarding saliency maps, which use gradients ...
0 votes
0 answers
34 views

Why am I getting a very small number as CNN prediction?

I created a CNN using Tensorflow to identify pneumonia and sometimes it returns a very small number as a prediction. why is this happening? I have attached the link for the dataset Here I how I ...
0 votes
1 answer
76 views

For a task that searches for an image artifact within a picture, can existing tools can be used or do I need to design the process myself?

I am familiar only with basic AI/NN concepts but never worked with any libraries/tools as tensor flow. Currently, I have a task for which AI might be ideal: detection of a certain image artifact in a ...
  • 111
0 votes
1 answer
93 views

Multiple labels for the same rectbox?

My goal is to identify the horse in a photo. I'm dealing with about 500 unique horses. My feeling is that the best way to distinguish one horse from another is by its face. So I trained Yolov5 ...
0 votes
1 answer
89 views

Can I flip a video to generate more data for action recognition?

There are 8 distinct action classes and around 50+ videos per class. I was wondering if flipping videos from the training set can be a good option to generate additional data. Is it?
2 votes
1 answer
86 views

How do automatic high-beam headlights work on cars?

Modern cars can operate high-beam headlights automatically: They automatically switch from high-beam headlights to low-beam ones (less intense) when you enter a town or there is a car in front of you ...
1 vote
1 answer
233 views

What sort of out-of-the-box technology could be used to create work similar to artist Refik Anadol? [closed]

Refik Anadol has machines view actual pictures and then has the machine create its own images. This video shows some of the stuff he does. What kind of out-of-the-box tools (e.g. a Python package) or ...
  • 143
3 votes
1 answer
96 views

What is the purpose of hard distillation?

In order to get a smaller model, one often uses larger model, that performs reasonably well on the data as a teacher, and uses the information from large model to train the smaller one. There are ...
0 votes
0 answers
106 views

How to increase accuracy of image orientation classification (Left, Right, Center)?

I am working on classifying images in "Left", "Right", "Center", "Back". Training and Validation images look like this: The images are "Left", "...
  • 101
1 vote
0 answers
53 views

Is having near-duplicates in a training dataset a bad thing?

I am making a labeled dataset of images from web streams for a CNN classification. Pictures from the same stream are quite similar as far as background, but slightly different as far as the main ...
1 vote
0 answers
324 views

Image recognition neural network: scaling and rotation

Are there some effective and robust solutions for scaling and rotation for image recognition with the neural networks (NN)? I see tons of sources on the Web with explanation how neural network is used ...

1
2 3 4 5 6