Last call to make your voice heard! Our 2022 Developer Survey closes in less than a week. Take survey.

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.

Filter by
Sorted by
Tagged with
0 votes
0 answers
14 views

extract features from parts of one image

I have several parts of one image that have one caption... I need to do image captioning by evaluating every part of the image to which the caption will belong so do I need to extract the features ...
user avatar
  • 1
0 votes
1 answer
30 views

Overfitting problem: high accurance and low accurancy validation for image classification

I want to define a model to predict 3 categories of images. I'm learnong on the field :-) I've 1500 images (500 for each category) in 3 directories. I've read in this blog many suggestions: use a ...
user avatar
0 votes
1 answer
14 views

Are labels associated with a model or a dataset?

I'm not sure if I have this backwards or not, so I'll explain a bit of what is going on. I want to use Unity's Barracuda api to use an onnx model for classification ...
user avatar
0 votes
0 answers
9 views

Searching for object detection PyTorch library (like Segmentation models)

I'm searching for something like SegmentationModels https://github.com/qubvel/segmentation_models.pytorch for the purpose of the classification (single packet that includes various models like Yolo, ...
user avatar
  • 101
0 votes
0 answers
12 views

Federated Learning: some clients with 0% accuracy

Suppose that I am doing a Federated Learning experiment using MNIST. As you know MNIST has 10 classes. Now, Federated Learning is useful especially in cases like hospitals, for collaborations, because ...
user avatar
0 votes
1 answer
15 views

Using CNNs to detect incorrect label images in dataset

What I want to do is to train a model to identify the images that are incorrectly labeled in my dataset, for example, in a class of dogs, I can find cats images and I want a model that detects all ...
user avatar
0 votes
0 answers
15 views

Is it possible to justify why one CNN architecture outperforms other models?

I am using several pre-trained models to solve my problem. These models are VGG-16, Resnet-101, Inception-ResNet-v2, Densenet-201, and Xception. Xception has outperformed all of these models; is it ...
user avatar
-1 votes
0 answers
8 views

image classfication from board

i have about 50 images i designed in illustrator , it is like cards have inside it words and the backgroung of cards it's colored (like scratch's card, i have on the board about 15 of them , look to ...
user avatar
0 votes
0 answers
22 views

How to make an ensemble model for classification with pytorch using trained models?

I am trying to make an ensemble model composed of two pre-trained models, using torch, in order to classify an image. Below is some code, based on this post. ...
user avatar
  • 111
0 votes
0 answers
10 views

Python image classification - number classification

I have a project where I want to use an existing ML model to classify images with numbers 1-50. My images will pretty much be white squares with a number in the middle or the corner. When I search for ...
user avatar
  • 1
1 vote
0 answers
12 views

Methods for combining instance observations for classification

I am working on a project where I classify tiny moving particles into a few classes (fibers, hairs, glass shards, bubbles). The particles are only a few pixels large and are observed in a few frames ...
user avatar
0 votes
0 answers
17 views

tensorflow predict gives same values for any input

I'm trying to create a classification model for images, using TensorFlow and Keras. For this classification problem, I've created a model like this: ...
user avatar
0 votes
0 answers
10 views

Adding L2 regularization on top of pretrained EfficientNet model causes fluctuating validation accuracy and loss

I've built a model on top of pretrained EfficientNetB2 which would achive ~50% validation accuracy after 3-4 epochs and then would start to overfit. In order to counter that I added l2 regularization ...
user avatar
0 votes
0 answers
8 views

Does it make sense to "stack" tensorflow models when I don't really care about the output of the top model?

let me try and explain the problem I'm trying to solve with an example. Suppose I have a set of images, half of which are of beaches and the other half are forests. I want to build a model which can ...
user avatar
0 votes
0 answers
11 views

Group multiple ImageNet labels into a more general label

I'm a beginner in the world of machine learning, and my goal is to produce a mobile app that can recognize, label and group your gallery picture to make it more organized. I started by digging into ...
user avatar
0 votes
0 answers
16 views

Defects classification

my task is to classify the defects type present in some images coming from optical inspection tools. Often the defects appear on a uniform colored background while some other times they appear on top ...
user avatar
0 votes
0 answers
14 views

How to save pixels after normalization

I want to normalize my images and use them in the training. But I couldn't find a way to save images after making changes below...How can I save it? ...
user avatar
1 vote
0 answers
13 views

How can I calculate de AUC PR of my classifiers in a multiclass scenario?

I'm developing image classifiers in a context with 25k images and 50 classes. The dataset is imbalanced. Some papers recommend AUC PR for comparing the performance of my classifiers in this setting. ...
user avatar
  • 127
0 votes
0 answers
18 views

Beginner needs guidance. Machine Learning, preparing training data

i try to dip my feet into the field of computer vision and want to avoid mistakes along the way. The problem I have to solve: Classifiy images of 3D dental scans. For example: I wrote a script to ...
user avatar
2 votes
1 answer
20 views

Data augmentation in images

Suppose there is a ML network that takes grayscale images as the input. The images that I have are RGB images. So, instead of converting these RGB images to grayscale, I treat each individual colour ...
user avatar
0 votes
0 answers
9 views

How to do Image forecasting with set of images as timeseries?

I am working on a problem with a dataset of a disease that progress with time. I am given set of images that shows the disease progression equally spaced over 1 week time interval.I want to predict ...
user avatar
1 vote
1 answer
10 views

Creating a map between N images and N labels using CNN

I have seen classification CNNs that train with numerous images for a subset of labels (i.e. Number of images >> Number of labels), however, is it still possible to use CNNs when the number of ...
user avatar
  • 11
0 votes
0 answers
29 views

Convert FER2013 dataset from grayscale to RGB

I am currently working on a Human Face Emotion detection project, my goal is to use transfer learning to build my model. When I tried it's been said that I cannot instantiate the base_model which is ...
user avatar
1 vote
1 answer
14 views

Multi-label Classifier underperforms individual classifiers

I originally trained multiple individual binary classifiers for each label of an image. Then, I realized I can train a single multilabel model for this task. I used binary_cross_entropy loss for this ...
user avatar
0 votes
0 answers
15 views

Generation of similar images with a neural network

Are there some known neural networks that, given an input image, can generate a similar image, with the same topic? Example: input = a photo of a cat on a green tablecloth, output = a generated photo ...
user avatar
0 votes
0 answers
17 views

Fine-grained image classification

I have a dataset which has 4 classes (say A,B,C,D). The task requires fine-grained image classification. The problem I am facing is that for 2 of the classes (C,D), the model's performance is not so ...
user avatar
0 votes
0 answers
15 views

What is meant by non-linearity in Convolutional Neural Networks? And why do we focus on removing it entirely?

I am aware of the working of ReLU that it turns every negative value to zero and does not effect any positive value, but what confuses me is this: what is actually meant by non-linearity in feature ...
user avatar
0 votes
0 answers
82 views

Comparing two images for similarity

Comparing two images for similarity What are the best softwares available for comparing two images having similarity and differences? Example: Margaret Thatcher & Enid Blyton.
user avatar
0 votes
0 answers
5 views

Recommended unsupervised learning model for categorizing stamps

I'm trying to solve the following problem: a program is given pictures of collections of stamps (e.g. those large unsorted boxes you find on eBay and other sites), and it then uses ML to scan the ...
user avatar
0 votes
1 answer
37 views

False positive in Multi class Image classification

I am training a neural network with some convolution layers for multi class image classification. I am using keras to build and train the model. I am using 1600 images for all categories for training. ...
user avatar
  • 1
1 vote
0 answers
34 views

Time series classification with difference in time

I'm trying to classify some time series data and my goal is to convert it to a wavelet image and just use novel image classification techniques. However, my problem is the fact that my data doesn't ...
user avatar
0 votes
0 answers
17 views

How to understand the workings of metric learning?

I need some help figuring out how to solve the problem below: There is one anchor category and two non-anchor categories. Now, given an item belonging to an anchor category, we need to find items from ...
user avatar
0 votes
0 answers
17 views

Is there a Machine Learning/AI model for recipe ingredients?

Working on a project that uses a mobile device camera to add ingredients to a users database, and im wondering if there exists a way/MLmodel that classifies ingredients into simple classifications or ...
user avatar
0 votes
1 answer
22 views

Floor plan analysis

Given an image of a floor plan, is there a known algorithm I can use to understand measurements of all apartments present ? (for example, that means in the attached picture understanding there are 4 ...
user avatar
  • 1
0 votes
0 answers
29 views

Reproducing research results - one-shot classification for MNIST and Fashion-MNIST

I have come across two pieces of research related to one-shot classification of MNIST and Fashion-MNIST images using a 1-nearest neighbour (1-NN) classifier: [1] G. Koch, "Siamese Neural ...
user avatar
  • 1
0 votes
0 answers
9 views

What computer vision task does describing the features of images comes under?

I have a very noob question - Is there a computer vision task category for the task when you describe the objective feature of the images like - brightness, focus, artefacts and hence classify the ...
user avatar
  • 198
0 votes
0 answers
12 views

Understanding last convolution of U-NET for image segmentation

I was trying to understand the last layer of Image segmentation architecture (U-NET). For example what will be the logits-probability distribution of pixels in each case? I know that its there as ...
user avatar
0 votes
0 answers
36 views

Image segmentation with U-net

I am trying to understand if Semantic segmentation with U-NET. Are we training kernels to extract features or are we training a fully connected layer at the end? Or both? If so, how are we training ...
user avatar
1 vote
1 answer
59 views

model.predict gives the same output for all images

I am trying to create a model using resnet50 to classify ct scan images as covid or not. However when using model.predict with a given image its giving the exact ...
user avatar
  • 11
1 vote
1 answer
42 views

Advice / Good practises | CNN poor image diversity

I am currenty working on a project that involves multiple cameras fixed on the ceiling. Each time I take a picture, I check whether there is a "cart" right under the camera. I would like to ...
user avatar
0 votes
0 answers
41 views

Choosing the best checkpoint of a model

As of now, the best way of choosing the "ideal" checkpoint is to select a certain KPI and based on that KPI selecting the checkpoint of the model. But as I go over the train/evaluation plots ...
user avatar
0 votes
1 answer
49 views

resnet50 based model classification loss increase

I'm trying to classify fonts in images into 7 classes. I wanted to use a pre-trained ResNet50 for the task and use its features to my classification. So I've followed some guide and came up with the ...
user avatar
  • 101
0 votes
1 answer
31 views

Determine postion of dart in dartboard

I'm new to machine learning and I want to built my first project. I decided to write an application which determines the postion of a dart in a dartboard. The neural network would have the following ...
user avatar
  • 1
0 votes
0 answers
25 views

Neural network training for two vs. many classes

Suppose I want to train a convolutional neural network to distinguish not between dogs and cats, but between images of dogs and images of any feline – cat, lion, tiger, leopard, cheetah, etc. ...
user avatar
1 vote
0 answers
20 views

how to train image classification with small difference in low-level feature

I would like to build the model that capable of doing classification for example 2 classes below : I tried alexnet, resnet50, resnet18, vgg16 but seem they are failed to differentiate between this ...
user avatar
0 votes
0 answers
23 views

Using Validation Set in Transfer Learning for Feature Extractor Preprocessor

I have a set of images of products. I am using transfer learning for images feature extraction in this way : I load a model (res-net, vgg) I add 2 dense layers, first one will be my features and the ...
user avatar
  • 101
1 vote
2 answers
49 views

How can I classify multiple images "simultaneously"?

I am dealing with a multiclass image classification problem with N classes. Particularly interesting is now that a single instance is NOT a single image as you would expect normally, but rather a set ...
user avatar
  • 63
1 vote
0 answers
27 views

Which model is used for document extraction (CamScanner, Microsoft Lens etc)

I want to start a small project where I'd create a model(s) that would extract document from a picture and rescale it, something like CamScanner or Microsoft Lens apps do. I've gathered a small ...
user avatar
0 votes
0 answers
20 views

Can PCA help to reduce false positives in image-based classification?

I'm working on a 2-class problem where cancer cells need to be accurately identified from a mixed population containing cancer cells + white blood cells (WBCs). The model I have been using - SVM with ...
user avatar
  • 1
0 votes
1 answer
12 views

Object detection or image classification? Each image has 3 shapes. I want to return 1 if they are all triangles, 0 otherwise

Question is in the title. Every image has three shapes, which can be either triangles or squares. I want to return 1 if all shapes are triangles, 0 otherwise. Which do you think would work better for ...
user avatar
  • 1

1
2 3 4 5
15