We’re rewarding the question askers & reputations are being recalculated! Read more.

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
1
vote
0answers
10 views

Why when I apply GaussianBlur in my images, my model overfit? CNN KERAS

I have 1400 images (700 each class), and i'm using vgg-16 to classificate between one and other class. But when I apply the preprocess method Gaussian Blur (which seem to be very much clear to see the ...
0
votes
1answer
11 views

Can the same CNN architecture be used for different data sets?

I have a CNN architecture that works well on 32x32x3 images. Can I use that same architecture for a data set made up of 28x28x1 images? (Both data sets have 10 classes). If this is possible, what ...
0
votes
0answers
11 views

Mixing unsupervised and supervised algorithms in image classification model

I am trying to replicate the general image classification model used in a paper that I cite later below. The following image is an extract from a paper that proposes a novel method of performing image ...
2
votes
1answer
17 views

Classifying objects in video without machine learning

Recently, Nick Bourdakos posted a series of videos demonstrating bottle detection in a video stream using Tensorflow.js. Specifically, he is using SSD-mobilenet. The problem could be summarised as ...
0
votes
0answers
16 views

TF/Keras: different results based on how I combine models

I'm trying to follow the Transfer learning with a pretrained ConvNet tutorial, using my own images and data. If I first run my images through the base model (MobileNetV2), and then take the results ...
0
votes
0answers
17 views

The model only improves Precision/Recall AUC

I have a CNN model for an imbalanced image classification problem. I'm experimenting with a theory that is supposed to improve the accuracy of the model. Since I'm dealing with imbalanced data, I'm ...
2
votes
0answers
26 views

Did I do the right thing in my CNN Keras (class imbalance - augmentation)

To implement my Binary CNN in keras, I had a dataset of ~~35000 images but only 700 is from one class and all the others are from the other class, so what I did: I get the 700 unique images from class ...
1
vote
1answer
46 views

How can I increase my accuracy avoiding overfitting? CNN-Keras-VGG16

As I asked in this question: Why are my predictions bad, if my accuracy in train is roughly 100% (Keras CNN) , my problem was Overfitting, so, I reduce the number of layers, and now I have this model: ...
1
vote
1answer
19 views

Medical Image Analysis

What are some good starting points for learning medical image analysis and combining it with deep learning? I would like to analyze images with bone cancers but not sure what is proper way to ...
0
votes
1answer
21 views

Why compressed image size is greater than original one in kmeans algorithm?

I have a png image as shown below. And I use kmeans algorithm to compress the image by color quantization. I compressed the ...
0
votes
2answers
20 views

Classifier design for website screenshots

I'm working on a project that requires determining if the page representing a hosted file on a third party platform (such as rapidgator or nitroflare) is still up or not. For example, here is a file ...
0
votes
0answers
10 views

The importance of testing data subsets for image classification

I have quite a conundrum that I'm trying to understand when you have classification problem, but your training data subsets are very biologically meaningful. I have a disease that has four slightly ...
1
vote
1answer
81 views

How to increase the accuracy of my predictions (CNN fine tuning VGG16 KERAS)

In my VGG16 fine-tuning, I have to classify retinal images in 2 classes (or 4th stage or not 4th stage) and I have 700 images each class to train. This is my code now: ...
0
votes
0answers
25 views

Multilabel image classification failure with a specific dataset

I'm having an issue with a specific dataset. My training for multilabel image classification is returning [class1 and or class2 and or class 3] (only 3 classes for every image) when there are 13 ...
0
votes
2answers
26 views

Why do we need convolutions over volume in convolutional neural networks for image recognition?

In convolutional neural networks, we make convolutions of three channels (red, green, blue) with a filter of dimensions $k\times k\times 3$, like in the picture: Each filter consists of adjustable ...
0
votes
3answers
46 views

Problem with overfitting

I make small CNN from scratch to classify barcodes. I have two classes: one for images with barcodes and second for all what isn't barcodes (items, animals, landscape, furniture, people). I got good ...
0
votes
0answers
21 views

Issue with multilabel image classification only returning a couple (incorrect) classes

I followed this tutorial: https://medium.com/@vijayabhaskar96/multi-label-image-classification-tutorial-with-keras-imagedatagenerator-cd541f8eaf24 and wrote some of my code for multilabel ...
0
votes
0answers
14 views

Image Classification approach for Text images

Let me introduce myself as a beginner to machine learning problems. We are trying to build a system to classify images of text-data like bills, orders, bank-statements etc. We started with the image ...
2
votes
3answers
65 views

How do I handle with my Keras CNN overfitting

In my CNN, I have 700 images of class 0, 700 images of class 1, and 72 validation images. My code: ...
0
votes
0answers
15 views

Need to apply Custom weights in case of semantic segmentation

I am solving a multi-class image segmentation problem. The following is my map of a fundus image: The correspondence is the following: ...
0
votes
1answer
13 views

What is the State of the art method for full body gesture recognition in images

I am working on gesture recognition in images and the best way that I am aware of, is whether using end to end approaches with deep neural networks or extracting body joint positions in an image and ...
1
vote
1answer
24 views

Metric/loss for bin classification

I have a model that has to classify inputs into one of 45 categories but those categories actually represent bins (e.g. bins 1, 2 and 3 are between 1 and 10, 11 and 20, 21 and 30 respectively). What I ...
1
vote
0answers
15 views

List of CNN for Emotion/Sentiment recognition on images with performance on main datasets (IAPS, GAPED, EmoPics, NAPS)

There are more and more databases of pictures classified or rated with emotions. For instance, I know of 4 databases (IAPS, GAPED, EmoPics, NAPS) rating pictures on 2 dimensions: Valance (positive vs ...
-1
votes
1answer
24 views

Deploy local deep learning web app to web

So I've built a (relatively) simple web app with a deep learning image classifier, and I have it running on localhost. How do I upload this to the web so that I can link to it from my website? The ...
1
vote
1answer
82 views

What I'm doing wrong with my CNN Keras?

In my project I have 700 images for each class (pdr and nonPdr) totalizing 1400 images. To validation I've put 28 samples. The problem is that my validation loss and accuracy is unstable. This is my ...
4
votes
2answers
69 views

Trained Tensorflow model performs poorly on inference

I trained an image classification model using Keras with Tensorflow backend. The model got good accuracy on validation dataset as well as on the testing data, I save the entire model to ...
1
vote
0answers
6 views

Bags of visual words - counter intuitive result

I'm reading the frequently-cited paper Bags of Binary words for Fast Place Recognition in Image Sequences and have found something strange in the paper. The similarity measure is presented as: $s(v_1,...
0
votes
1answer
58 views

My CNN model Accuracy doesn't increase (high loss and low acc)

Well, I need to do a CNN to classify if a Image is from one or another class. But my model return high losses (6.~8.) and low accuracies (0.50 on max). I tried to include more layers, change my ...
0
votes
1answer
42 views

ValueError: Error when checking input: expected conv2d_1_input to have 4 dimensions, but got array with shape (142, 1)

I'm trying to pass all my images (71 for each class) from folder 'train' to model.fit. The method ReadImages get these images and resize them (because are too big 4288x2848).... But when i run my ...
3
votes
1answer
58 views

How many model parameters did Microsoft's 2015 ImageNet-winner network have?

In 2015 a team of researchers from Microsoft won the ImageNet contest with a network of 152 layers. How many parameters did their model have?
0
votes
1answer
38 views

Why my Keras CNN model isn't learning

My project have to decide if a image is 'pdr' or 'nonPdr', and I have 391 images (22 of PDR class, and the 369 of nonPdr).. In my first model i was trying this: https://stackoverflow.com/questions/...
0
votes
1answer
46 views

How to prepare training data for deep learning models

I am working on a project which involves the application of deep learning models. I have collected training data. In collected images, I have more than one object in interest. I am not very clear how ...
0
votes
0answers
13 views

How to convert raster image + shape files to a segmentation problem?

I have a problem converting raster image + shape files containing polygons and the class of each one to a segmentation problem to be able to classify crops. The data I have is composed of a raster ...
0
votes
0answers
13 views

Multilabel Image classification via multiple binary datasets

I want to make a multilabel image classification model that can detect many different labels. For each label, I can get at least 5000 positive examples and 5000 negative examples. However, my question ...
0
votes
1answer
35 views

CIFAR-100: What is the difference between vehicles 1 and vehicles 2?

The superclasses in the CIFAR-100 dataset are mutually exclusive and all but the vehicle ones are quite well defined by its label. Example: It is very clear why bees belong to the superclass ...
0
votes
0answers
19 views

How to build an image classification model from raster images and shapefile that contains labels?

I will first explain the problem and the data that I have. I have a satellite raster image of a land taken from sentinel2 that is composed of 14 bands, a train shapefile that is composed of polygons ...
0
votes
1answer
13 views

Deploy pretrained model to simple web app

As a small personal project, I wanted to try and deploy this image classification model with a simple web app (input image, output classification and heatmap). There are a couple pretrained models on ...
0
votes
0answers
8 views

Validation of Images generated using DCGAN

I have trained a Deep Convolutional Generative Adversarial Network(DCGAN) model and generated some images. Now, I need to validate these images if generated images ...
0
votes
0answers
34 views

What kind of NN architecture should I use to my problem?

I'am new to Data Science, and I'am trying to figure out how to solve my learning problem: My data set is CIFAR-100. Each image in the set got a vector of properties, a vector on $\mathbb{R}^n$. My ...
0
votes
0answers
10 views

Increasing the no. of FC layers increases the size of the model … Image Classification

I have trained a model using Transfer Learning. There are 13 Image classes and around 2000 images in Total. I have trained various models varying the FC layers and their dimensions. For ex: 1 ...
0
votes
0answers
22 views

Setting Up Training Data to Perform Image classification

I want to use Orange for an Image Classification project I am working on. I have a training image set and separate .csv with columns corresponding to the image (by name) and classifier. Wondering ...
0
votes
2answers
41 views

Does high accuracy metrics with small (but equally sampled) dataset means a good model?

I have been training my CNN with 200 images per class for a classification problem. There problem is a binary classification one. And with the amount of test data ( 25 per class) I am getting good ...
-1
votes
1answer
24 views

What is a color blob? Is it possible to use clustering algorithm to color blob detection problem?

Wiki gives this definition of blob detection In computer vision, blob detection methods are aimed at detecting regions in a digital image that differ in properties, such as brightness or color, ...
3
votes
1answer
106 views

Why is training and validation loss steadily rising (eventually to NaN) in this CNN of mine?

Dear ML and data scientists: I have 4 layers of gray scale images for every single biological specimen in my dataset. I am trying to train a 4-convolution CNN (see pytorch architecture below) to ...
1
vote
0answers
97 views

Intuitive explanation of Lovasz Softmax loss for Image Segmentation problems

Lovasz Softmax is used a lot these days for segmentation problem and the original paper is really bad at explaining why it works.
2
votes
0answers
21 views

Does object detection do a better job at image classification than image classification

I read in an article that object segmentation can do object detection better than object detection algorithms. I assume this is because there is more detailed information in the annotation images. I ...
0
votes
1answer
90 views

Keras binary classification model is not learning anything. How to improve my model?

I am trying to train a binary image classifier on a an imbalanced dataset of images which are really small in dimensions(the largest dimension is 40*70). I am augmenting images by grayscale, rescaling ...
1
vote
0answers
29 views

App or Service to QA 80,000 classified images?

I've been reviewing services and apps for the past week and my head is exploding. I just haven't found the right one yet, but I know it has to be out there, so I'm turning to the collective wisdom ...
0
votes
0answers
7 views

How to unify all masks from Mask R-CNN into one?

I'm trying to unite all masks that we've got with Mask R-CNN into one mask that would give True/False for the whole picture. I have separate masks with True/False and corresponding boxes with ...
0
votes
1answer
41 views

“Stationarity of statistics” and “locality of pixel dependencies”

I'm reading the ImageNet Classification with Deep Convolutional Neural Networks paper by Krizhevsky et al, and came across these lines in the Intro paragraph: Their (convolutional neural networks') ...