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
0answers
3 views

Not sure how to use GLCM features to clasify large cuantities of textures

Im trying to create a script that given a texture returns similar textures. I have read some articles and I have found that, for textures, good ways to obtain features are to use LBP or GLCM. I have ...
0
votes
0answers
15 views

How do I export my data into .h5 format?

I am trying to make my data useful for to use in this model, i.e for Hierarchical Novelty Detection for Visual Object Recognition. I need to prepare my own dataset in a format like this: ...
0
votes
1answer
21 views

Classification problem using features with unequal sizes

I am relatively new to Machine Learning/ Deep Learning and currently I am working on a classification problem. I have many 2D images and each of them is a cross section of a specimen showing the ...
0
votes
0answers
8 views

How to correctly use depthwise convolutional layers

I am trying to speed up my CNN by replacing all convolutional layers with depthwise convolutional layers, which can require only as much as $10$% of the operations ...
0
votes
0answers
22 views

Multi-Model Learning | Text and Image | Mutually Differentiable Models | Is it possible?

Problem : Document classification of scanned financial documents using Text (OCR on the images) and Images. The documents are both structural (forms, tables), unstructured (letters, descriptions, ...
0
votes
1answer
10 views

Can we calculate iou and mean iou with only images and labels and without train and test csv file

Are train and test CSV files necessary for calculating IoU (Intersection over Union) and ...
0
votes
0answers
14 views

Similar image classification [closed]

I am a programmer who likes to take photos in my free time, and an issue that I have is that I take a lot of pictures(upwards of 5,000). As a result, I spend a lot of time sorting them into a good ...
0
votes
1answer
35 views

Is there an algorithm for categorizing unlabeled samples into K classes? [closed]

I am not sure if this would be considered unsupervised, or semi-supervised learning. I am looking for an algorithm that will take N input arrays of features, and then cluster samples(not features) ...
0
votes
1answer
25 views

after augmentation validation accuracy going down?

My main question is about augmentation. if I process the augmentation I believe it always better than less data but in my case the validation accuracy going down train : 7000 images , validation: ...
0
votes
1answer
20 views

predict numeric value from images

I have two questions: 1) I have images and I must predict a continuous value. What is the approach I must follow? Use for example a pretrained network like this? ...
1
vote
0answers
19 views

Combination of two CNN models outputs

I have an image data set that I want to classify into 3 classes: non-disease, disease-type 1, and disease-type2. I trained two separate CNN's models, one is classifying the 3 classes, and the second ...
0
votes
1answer
11 views

Quickest way of multi-labelling images?

I want to make a new dataset containg thousands of (different-sized) images. Now I need to assign multiple labels to each image. Of course I already looked at github etc. and there are good labelling ...
0
votes
0answers
8 views

How to get model predictions on all classes after applying Transfer Learning?

I have been following transfer learning with TFHub to implement transfer learning in my model for text classification. However, I do not understand how to get probabilities for all the classes (1000 ...
0
votes
1answer
23 views

CNN Architecture for Multiple Instance Learning

I have a binary classification problem where I have a bag of documents (image files) that I need to classify - the bag that is, not the individual document. However, a bag can have a different number ...
0
votes
0answers
4 views

Can the test set of non-image data be augmented?

I have learned the test set of image data can be augmented by a method called Test Time Augmentation and I am wondering after I researched on it if the test set of ...
0
votes
1answer
9 views

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 ...
0
votes
0answers
6 views

Unsupervised learning for image treatement

I'm searching for methods that I can use to detect objects in images using unsupervised Learning. I found that the CNN and AE can be used , but I'm not sure. Anyone can guide me please
2
votes
5answers
38 views

Binary classification as a 2-class classification problem

I want to create a dog-classifier, which outputs the probability of an image containing a dog. I have two approaches in mind - Binary classifier (1-class), which just outputs the probability of the ...
2
votes
2answers
19 views

Looking for animals dataset for deep learning classification

Do you know any datasets that contain animals and their accurate classifications? I am looking for any dataset that categorizes animals. For example: a dataset with insects, with an image of an ...
1
vote
1answer
41 views

Strange binary classification result with a model that indicate it has been well-trained

The problem : I am trying to build a model for binary classification for melanoma 'MEL' and nevus 'NV' the dataset is from ISIC archive ISIC 2019 but for 8 different type of skin lesion, I am using ...
0
votes
4answers
43 views

Keras model giving error when fields of unseen test data and train data are not same

I have created a simple Keras deep learning model in python. Total no of variables in training are 195 while in unseen test data are 181.All input fields are categorical(converted by one hot encoding)....
1
vote
1answer
25 views

Generating Synthetic Image to improve the performance of classifier

I need some suggestion from experts. For my project work, I have been learning about Generative Adversarial Network. I am trying to make a ...
0
votes
1answer
12 views

Tuning a classifier for high precision, with no regard for recall

I understand this falls under the decision making aspect, rather than the probabilistic, but for the purposes of some work I am doing, I need the classifier to have very high precision, as I can't ...
0
votes
0answers
6 views

Automatically assess training data quality for land cover classification system

I am working on a Land cover classification system, wherein, Sentinel-hub imagery is being used to categorize the land cover by using a time series of multispectral imagery. Training data is being ...
0
votes
0answers
27 views

How to choose our data set wisely?

I have a couple of questions and I was wondering if you could answer them. I have a bunch of images of the cars (side view only). I would like to train a model with those images. My objects of ...
0
votes
0answers
30 views

NotImplementedError: `fit_generator` is not yet enabled for unbuilt Model subclasses

I'm trying to build a model to classify images. The model runs perfectly fine locally. When I run using Google Cloud AI platform, I get the error: ...
0
votes
1answer
17 views

Why some papers writing false positive rate per case instead of percentage rate?

In some published works specially in medical image analysis, instead of writing FP rate as percentage, they write it per case, for example: FP: 128.52 [/case]. What is the meaning of this? Is it have ...
0
votes
0answers
27 views

Fast.ai Learner.validate result dependent on used sampler or num_workers in DataLoader

I am trying to understand why the result of Learner.validate function in fastai library depends heavily on the sampler used in <...
2
votes
1answer
33 views

Cat Dog classifier in tensorflow, fundamental problem!

I am trying to build an image classifier for a set of images containing cats and dogs. I am very new to the dark art of creating Neural Network models. I have had success building models with Keras in ...
0
votes
0answers
12 views

Image-Level Detection

I am not sure if this is the correct term to use, but I'm looking into Image-Level Detection models. By image-level, I mean models that get an image as an input and then determine whether it belongs ...
1
vote
2answers
35 views

Clustering on imbalanced data that has high correlation

I am clustering images of two categories, but for the purposes of the experiment, I do not know the labels i.e. this is an unsupervised problem. Via ...
3
votes
1answer
25 views

How to prevent model from recognizing false Classes

Let's say that I have a model that can recognize Cats and Dogs. However, when I use a picture of a Cup or Human it generates a random prediction at 0.70 confidence. Should I use sigmoid instead of ...
1
vote
0answers
17 views

Creating an Object Detection model with images and coordinates of bounding boxes

I am trying to build a custom Object Detection model which can detect guns from a given image. The dataset is from here. The dataset has a good number of images and each image has 4 coordinates of ...
2
votes
0answers
51 views

Why is my Siamese network always predicting 1?

There is no change to loss and the accuracy stays the same. ...
1
vote
0answers
9 views

Image and Video Formats with lossy-compression and fast subregion lookup?

I'm looking for image / video file formats that support lossy compression to reduce disk size and allow for fast subregion lookup. i.e. dont read the entire file when you only need to lookup a small ...
1
vote
0answers
26 views

matterport mask-r-cnn transfer learning on own dataset using VGG annotator ver.1

The code I used was taken from shapes.py, balloon.py, inspect_balloon_data.ipynb but mostly ...
7
votes
3answers
235 views

How to detect cardboard boxes using Neural Network

I'm trying to train a Neural Network how to detect cardboard boxes along with multiple classes of persons (people). Although it's easy to detect persons and correctly classifies them, it's incredibly ...
0
votes
0answers
18 views

best approach for CNN training with multiple subcategories and one category

I need to classify pictures into 2 categories: approved and rejected. Rejected category has different type of images which are not allowed (subcategories), for example nude or gore or anime etc. What ...
20
votes
7answers
3k views

Why do most published works in medical imaging try to reduce false positives?

In medical image processing most of the published works try to reduce false positive rate (FPR) while in reality false negatives are more dangerous than false positives. What is the rationale behind ...
6
votes
1answer
54 views

Finding outliers in Image dataset

I have been working on an image classification tasks for which I am extracting the image frames from the video stream collected for different classes. I have already trained an image classification ...
1
vote
1answer
26 views

Selection of base model for transfer learning

Is there a golden rule which gives intuition on which base model needs to be used for a give image classification problem. Most of the articles gives the below details which says how to train the ...
0
votes
0answers
72 views

Improve accuracy of Keras multiclass image classification with pretrained VGG16 conv_base

In the moment, I'm training my first "larger" image classification model with Keras (22 classes, 2000 train samples, 500 val samples each class). I use a pretrained model (VGG16). My current model is ...
0
votes
0answers
23 views

Difference between three equivalent ResNeXt blocks

https://arxiv.org/abs/1611.05431 I have been reading this article and have a question about the following three equivalent ResNeXt blocks. In the article, it says Under this simplified case, ...
0
votes
0answers
42 views

Image classification using surf feature in python

I have a fish image dataset and I would like to classify the fishes in them. The images have another object in them as well (this common object is in all of the images for all classes). I used a ...
5
votes
2answers
71 views

Procedure for Designing CNNs

Are there any standard procedure for designing a CNN? I wrote some Python code for classifying speech signals using the 1D convolutional model in the Keras environment, but I can't meet the accuracy ...
1
vote
1answer
108 views

Improving the results of CNN [closed]

Edit 2 I solved my problem. The issue was caused by the validation_generator. I used the method flow_from_directory with shuffle = true. By changing the value to false and calling the method ...
0
votes
0answers
18 views

tfrecord file size larger than the original data size and how to reduce this size?

tfrecord file size larger than the original data(video-frames) size. Is there any way to compress or reduce tfrecord file size. Do you have any suggestions or ideas?
1
vote
0answers
23 views

Pre trained neural networks to recognize certain things

How do you approach the problem or is not classification? For example, I would like to recognize if a face has makeup. But, in order to do this, it would first need to be able to recognize if it is a ...
6
votes
0answers
102 views

How to arrange the dataset/images for CNN+LSTM

I am working on an image classification problem using Transfer Learning with Resnet50 as base model (in Keras) (For example Class A and Class B). There is a time factor involved in this ...
2
votes
1answer
80 views

Having trouble understanding None in the summary of my Keras model

The above code is a sample of a CNN model built using Keras. The first layer is a convolutional layer which will receive images of input_shape = (64, 64, 3), thus ...