Questions tagged [image-recognition]
For questions related to image recognition in the context of AI.
309
questions
0
votes
0
answers
12
views
Are there deepfake detection technologies available outside of the major companies?
I've been reading a lot about deepfakes lately and it's got me wondering about how we can detect them. I know big tech companies like Google and Facebook are working on this, but what about the rest ...
1
vote
3
answers
37
views
Is this video’s description of evolutionary learning correct?
In this video : How AIs, like ChatGPT, Learn, narrator describes a form of machine learning, specifically evolutionary algorithms or evolutionary machine learning.
Stating that, Initially, the builder ...
0
votes
0
answers
17
views
Training Image Classifier with 7 classes but my model is overfitting resulting the accuracy of the model to behave weirdly during training
I am training an image classifier for 7 different model types of a specific car engine parts. Each class has exactly 308 grayscale images with the same resolution of 1014x760. Those images consists ...
- 1
1
vote
0
answers
15
views
Automatic Image Annotation Based On Colour
I need to annotate a large corpus of images for image segmentation.
I can generate this corpus of images myself and I can choose to color whatever needs to be annotated with a specific colour.
I would ...
- 47
0
votes
1
answer
42
views
Best way to classify chess pieces on a chessboard (on a square) [more details in the post]?
Ok, so I am working on a project which classifies chess pieces. The input is just a chess piece from a specific chess set on a white / black square on the chessboard. So it's just an image of a chess ...
- 1
0
votes
0
answers
36
views
can Vision transformers be used to retain the relevant features (drop unrelated features from the clutter in image) and map to the specific query
Background, I have good understanding of ML 101 (supervised, unsupervised, tensorflow etc), however just getting into transformers & gen-AI.
I have recently started looking into Transformers/ViT ...
- 1
0
votes
0
answers
16
views
0
votes
0
answers
910
views
Uncensored auto-captioning libraries that work well for NSFW image datasets?
I have a large (>2.5 million files) dataset of NSFW images that I would like to auto-generate detailed (~100-150 token) captions for, using a visual language model similar to CogVLM or Llava.
I ...
1
vote
1
answer
91
views
Must a CNN (both 1D and 2D) take input of the same size?
I have the notion that CNN input data must always be of the same dimensions. If we are feeding 1D tabular data, columns must be of the same numbers; if we are feeding 2D image data, all the images ...
- 341
0
votes
0
answers
21
views
Enhancing Soil Moisture Predictions Using Multimodal Data Integration in Agriculture
I am exploring an interdisciplinary research area involving multimodal data, focusing on agriculture. My study incorporates both visual and tabular data: crop and soil images from three distinct ...
- 1
0
votes
0
answers
29
views
Does reducing the image dimensions before sending them to Language Models (LMs) significantly affect the processing time?
I am currently working on utilizing Language Models (LMs) to describe images in my project (Search Engine for AI images). However, I am wondering about the efficiency of the process, particularly in ...
- 101
1
vote
0
answers
101
views
Image classification for two categories: background and not background
Sorry, I have some background on AI, but very little experience.
I am facing an image classification problem:
I need to detect whether an image is background or not (images are always of the same size,...
2
votes
2
answers
90
views
Image classification of more than 60,000 classes
I am working on a problem that requires the classification of more than 60k classes. I have around 1k to 1.5k images per class. I am using synthetic data for training and want to evaluate it on real ...
- 21
0
votes
0
answers
11
views
Neural Net Convergence for Batch SGD
I've built a dynamically sized neural network framework with for multi class classification—just to strengthen my understanding of the deep networks. I'm training and predicting my network to classify ...
- 1
0
votes
0
answers
41
views
How to detect abnormal fetal head size with image classification?
I am a computer science student currently working on my final project, which involves finding a classification-based solution for predicting the head size of a fetus during its third month. Here is a ...
- 19
0
votes
0
answers
8
views
Cannot find appropriate model to classify hidden states
My input data is vector representing encoded image - 22 features, and I try to classify by 3 classes 0, 1, 2 (neutral, good, bad)
Original:
...
- 101
0
votes
1
answer
87
views
Is global pooling necessary in image classification models? [closed]
In many image classification models, the global pooling operation is performed before the classification layer (i.e. fully connected layer) to reduce model complexity. Is the global pooling layer a ...
- 19
0
votes
0
answers
45
views
High Fluctuations in Validation Curve
Below I attach an image of accuracy curves. I got a lot of suggestions regarding some improvement in below curves. Following are my experiments in order to make the curve stable-->
I used lr = 4....
0
votes
1
answer
302
views
How to accurately detect grid cell boundaries in Python image processing?
I'm working on a Python algorithm to detect individual cells of a grid passed by an image. Currently, I'm facing an issue where the values inside each cell are being selected as contours along with ...
- 101
0
votes
0
answers
14
views
How to create meaningful features that allow unsupervised image classification?
I would train features that can later be correlated with categories, once I have some examples for the categories. Let's say one has a set of training images sorted by artist, and wants to create some ...
- 310
0
votes
0
answers
25
views
What are general techniques of structuring an image classification Neural Network for very large numbers of output classes?
I am aware of Neural Networks that have 100K+ classes and I would like to build one myself (yes, I have lots of training data) but I am unsure which technique to use because most of the nets I have ...
0
votes
0
answers
13
views
Training ImageNet on Resnet - Dropping LR has little improvement on accuracy
I'm trying to train Resnet50 on Imagenet following this paper [1] as well as this one[2].
They say that at approximately every 30 epochs, I should drop the learning rate by 10.
Since I'm training on 8 ...
- 1
3
votes
0
answers
161
views
How do I balance context and history when creating prompts for LLM's?
A conversation through the OpenAI API looks something like this
...
- 131
1
vote
2
answers
311
views
How to do image classification with optional metadata?
I have a vanilla image classification problem. The image may optionally have some numerical metadata associated with it. We don't assume uniform availability of this metadata, i.e., the model should ...
0
votes
0
answers
15
views
What are some good pairs of transfer learning source and target datasets for image classification?
As the title says, I'm curious about some well used transfer learning tasks.
ImageNet to other datasets is common, but what are something good pairs I can try and mess around with ?
Like CIFAR10 to ...
- 21
-1
votes
1
answer
291
views
What is the best lightweight alternative to VGG16 for image fingerprinting?
I am using a VGG16 model with the classification layer stripped off to generate vectors for an intermediate stage of an image fingerprinting algorithm. It works well, but VGG16 is a little hefty, and ...
- 156
0
votes
0
answers
25
views
High Accuracy ML.NET Image differentiation model
I have a relatively big dataset (100+GB) that has 35 categories. All of them are microscopic images with slight differences. Although ML.NET documentation itself declares that training time should be ...
0
votes
0
answers
13
views
Challenges in Developing AI Algorithms for X-ray Image Analysis on Large Datasets
Hello everyone,
I'm currently working on a research project involving X-ray imaging
and the development of AI algorithms to detect diseases from large
...
- 134
0
votes
1
answer
119
views
How can CAPTCHAs be used for both user verification and ML training?
CAPTCHAs (e.g. requiring a site visitor to click all the images of traffic lights in a grid of images) are often used throughout to Internet to verify that a site visitor is a human rather than a bot.
...
- 101
-1
votes
1
answer
377
views
Empty space detection [closed]
I'm looking for a TensorFlow model detecting empty spaces on the images. I need to add my company logo to this empty area so there shouldn't be any faces or objects in this area.
Also, I would be ...
- 99
0
votes
1
answer
94
views
Can a neural network recognize cropped images?
I asked ChatGPT to list some algorithms for identifying if one image is a cropped version of another or not. It suggested four algorithms that I know won't work, plus one that amounted to "train ...
- 420
0
votes
0
answers
467
views
Tips for solving OpenAI/Faramas Gymnasium Car Racing Environment
Im quite new to ML and wanna solve Gyms Car Racing v2 using Q-Learning with a Q-Table.
But I am having problems approaching this. Thats why I am hoping someone more advanced in this field could give ...
2
votes
1
answer
402
views
Should I use pretrained model for image classification or not?
I have thousands of images similar to this.
I can classify them using existing metadata to different folders according to gravel product type loaded on the truck.
What would be optimal way to train a ...
- 121
1
vote
1
answer
96
views
Is it feasible to perform facial recognition on hundreds of thousands of individuals?
I came across a video with the title "you can buy things with your face in China". in the video, a woman scanned her face into a vending machine to buy a drink with only her face and without ...
- 584
0
votes
2
answers
923
views
Is the GPT-4 for text the same model that can input and output images?
Currently, the published GPT-4 can input and output text.
A version of GPT-4 that can input and output text and images exists, according to the technical report, but is not yet publicly available.
I ...
- 737
2
votes
1
answer
288
views
Out-of-domain generalization
Given $X$ the space of all $N \times N$-pixel images and $I=\{$airplane,clock,axe,...$\}$ a set of labels.
An image classification task is generally concerned to learn a map
$$F:X \rightarrow I$$
Let'...
- 123
2
votes
2
answers
1k
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 ...
- 131
0
votes
2
answers
81
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 ...
- 101
1
vote
1
answer
43
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
149
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
179
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
2
answers
148
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 ...
- 1
2
votes
1
answer
131
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
133
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 ...
- 987
2
votes
1
answer
226
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: "...
- 21
0
votes
1
answer
37
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
507
views
Examples where AI fails in revealing ways
For a short presentation about AI, I am looking for examples where AI failed and thereby shows the limits of itself.
I remember there was one example,where an image classifier was given an image of ...
- 143
0
votes
0
answers
108
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
1
vote
1
answer
175
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
94
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 ...
- 133