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
2
votes
0answers
18 views

How will my CNN results be affected by large discrepancies between the number of samples in some of the classes?

The number of samples in my dataset range between 3800 and 100,000 per class. Was wondering if my neural network will be more biased towards the classes with a higher number of images. I'm trying on ...
2
votes
0answers
162 views

TensorFlow - TFRecords load and transform images with bounding boxes

I'm trying to build a 'Car Classifier' using TensorFlow. I have 1000 labelled JPG images, 800x800, complete with bounding boxes and associated annotations.coco.json; split into train/validate/test ...
0
votes
1answer
57 views

high accuracy on non trained class in tensorflow model

I have trained a 4 multi-class (apple_nature, apple_disease, apple_blacrot, apple_healthy) image classification algorithm using TensorFlow. However, after training, we get a good accuracy model. The ...
0
votes
0answers
13 views

Will disparity in image format/quality between binary classifications affect training of Convolutional Neural Network?

I have an image dataset containing two classes. One of the classes has many images and they are all JPG images with the following format: ...
0
votes
0answers
820 views

Keras model has a good validation accuracy but makes bad predictions

I have this model which takes 9000 images in a dataset containing 96 categories of traffic signs, each category has more or less the same number of images (about 50). This is the model I made but ...
0
votes
1answer
33 views

How do I deal with the fact that I have images which are not consistent with the class they belong in an image classification problem with CNN?

I am really new to Neural Networks and to Machine Learning in general, and I have been given a dataset composed by images for performing multi-class image classification with a CNN. The images were ...
1
vote
0answers
29 views

Tensorboard reported accuracy does not match my own calculations

I'm using Google's AI Platform to train an image classifier with Tensorflow (resnet-50 model). I have only two classes. Training set is something like 4K images in size and validation set 1K images. ...
1
vote
1answer
39 views

How to deal with a binary classification problem, where the instances in the negative class are very similar? [duplicate]

Let's say, one wants to detect, whether a picture of a fixed size contains a cat or not. But as a dataset, you have 10000 pictures of cats, and 30000 pictures which don't contain a cat, but are very ...
0
votes
0answers
146 views

Difference in features generated by same filters for color and grayscale images?

Would there be ay difference between the features generated by CNNs if they are fed with same image in color and grayscale format. If I am performing classification with same network for let's say ...
0
votes
1answer
28 views

improving performance for a limited dataset with noisy images, pattern recognition

I am trying to recognize doodles in noisy images like in this one below. My dataset consists of only 10 000 images and 30 categories I've implemented a CNN but it is giving me a 6% accuracy. I am ...
1
vote
1answer
79 views

Is it possible to get an ROC curve using Relu activation?

Based on my understanding, given that Relu doesn't provide probabilities unlike Softmax, it's not possible to plot an ROC curve. However, is there some way to convert the output from a Relu to ...
3
votes
1answer
1k views

What exactly are the data augmentation experimental Keras' layers doing?

From what I gathered, data augmentation consists in increasing your number of instances in your dataset by applying some transfromations. Let's say I want to classify images. If I apply a random ...
0
votes
2answers
165 views

Is it possible the model be better on a few epochs rather than hundreds of epochs?

I have very interesting experience in my CNN binary image classification. Do you think the result is by chance or there is a logic behind it? I used InceptionV3 transfer with softmax (I know you will ...
1
vote
1answer
62 views

Accuracy graph of binary classification by CNN [closed]

Why in binary classification of images with CNN the loss and accuracy graph are so unstable? I mean accuracy of validation test does not increase smoothly, it goes to 80%, then comes to 60%, then ...
3
votes
1answer
108 views

Role of Image Resolution in Deep Learning

I have multiple image datasets about the same topic that I want to use for a classification task utilizing Deep Learning. The datasets differ in the resolution of images (i.e. some pictures are ...
1
vote
0answers
87 views

Understanding arcface, sphereface, and their differences

I'm a beginner in ml and I want to make a facial recognition system. While going through the research paper I realized that I'm losing the intuitive sense of the computations. I'm not from a ...
1
vote
0answers
45 views

*(CATEGORIES[int(prediction[0][0])])* giving me different result for single image prediction from saved model

From a saved model, I am trying to predict a single image. I followed this code - https://www.youtube.com/watch?v=A4K6D_gx2Iw I am getting different result for two different command- ...
2
votes
2answers
591 views

Merging Training and Validation Sets for better accuracy

I am training an Image Classification Model and my train-test set distribution is 80-20. After Training my train-test loss curve looks like this As the model is converged after around 20-30 epochs ...
-1
votes
1answer
72 views

Machine learning algorithms for identification and classification of Microorganisms

https://www.google.com/search?q=Viruses+images&tbm=isch&ved=2ahUKEwiB9-fsoL3sAhUJyHMBHWRZB-sQ2-cCegQIABAC&oq=Viruses+images&gs_lcp=...
2
votes
1answer
723 views

How can a CNN learn colours?

I've created spectrogramms of different classes of low-hertz signals. They all have a plain blue foreground with hardly other coloured pixels, even for me its not easy to distinguish the classes by ...
1
vote
0answers
23 views

Why does my model fail to predict on the whole dataset?

So I have about 3000 images with 6 classes and this is what I did: 1 - split into training set and test set prior to anything with 20% test size 2 - performed data augmentation on the under ...
0
votes
1answer
36 views

Creating a image classification model [closed]

I am working on a dataset to classify facial expressions. Dataset has 7 classes, training images 28000 and test images 7000. I created 2 models Model1: this model has 11 layers. Initially model was ...
0
votes
1answer
42 views

Machine learning algorithms for Geometrical objects shapes identification

Are there Machine learning algorithms which will take input dataset of all geometrical objects shapes as images in gif,jpg,tiff formats & output the geometrical shapes names? i.e. Geometrical ...
-1
votes
2answers
50 views

Machine learning algorithms for interpreting Companies brand/s logo/s

https://www.google.com/search?q=Company+brand+logos&client=ms-android-lava&prmd=isnv&sxsrf=ALeKk0218I-1fMd-hNXX_fAF8_fu6EOotA:1600348128111&source=lnms&tbm=isch&sa=X&ved=...
1
vote
1answer
471 views

How to build a database of image data for machine learning?

I want to build a database of image data for machine learning. But how should this be done? I'm assuming people don't just dump all of their image data into a folder? Do they use a relational database ...
1
vote
0answers
11 views

Preparing training data for crop species classification from drone images

I have high resolution multispectral (R,G,B,NIR,RE bands) images of a field taken from MicaSense RedEdge mounted on a drone. There are various species of crops planted. I want to classify the crops or ...
2
votes
1answer
129 views

Machine learning algorithms and Computer Vision technologies for detecting 52 playing cards deck

https://en.wikipedia.org/wiki/Standard_52-card_deck https://en.wikipedia.org/wiki/Playing_card https://www.google.com/search?q=playing+cards&client=ms-android-lava&prmd=sinv&sxsrf=...
0
votes
2answers
239 views

CNN: How do I handle Blurred images in the dataset?

I have 30% blurred images in each classes. I have a total of 10 classes. I'm not allowed to drop these blurred images. How do I train the model to get better accuracy for both blurred and nonblurred ...
3
votes
2answers
3k views

How to predict multiple images from folder in python

Here is the code for the Prediction of multiple images from the folder. But getting the same label(class) for all the images.I'm not able to find out why every image shows the same label. ...
0
votes
0answers
29 views

What are the best models developed for image classification

For inventory detection problem, when you cut single product images from the shelf, the next step you have to do is that you should label the product and identify which category this product belongs ...
0
votes
1answer
53 views

End-to-end ML project walkthrough [closed]

I am new to machine learning and have finished Andrew Ng's course on Coursera. I have just begun to tackle my first "real" ML problem - which is a binary classification problem. I was ...
0
votes
1answer
45 views

How to increase model's test accuracy?

I am using the InceptionV3 model for training. Here is the link for the code (https://github.com/maxmelnick/tensorflow/blob/no_random/tensorflow/examples/image_retraining/retrain.py) Initially I have ...
0
votes
1answer
470 views

how do the number of classes in an object detection model affect accuracy?

If I have, say, a Yolo or RetinaNet Object Detection Model... if I train it with 10 vs 50 classes, (assuming 3000 training data images per class), will the model with 10 classes perform similarly to ...
1
vote
1answer
107 views

How to increase model's prediction accuracy

I am using the InceptionV3 model for training. Here is the link for the code (https://github.com/maxmelnick/tensorflow/blob/no_random/tensorflow/examples/image_retraining/retrain.py) Initially I have ...
0
votes
1answer
24 views

[under/over]-sampling teaches model the wrong distribution?

TLDR: Will under/oversampling during the training phase teach the model the wrong distribution and adversely affect accuracy? Let us assume you want to train a classifier to differentiate between ...
0
votes
2answers
51 views

Image multi class classifier CNN

I have a problem, im designing a multiclass classifier to classify medic images, I have to classify in which grade of desease is it, this are 6 grades , each time the joint deforms a little, so, mi ...
1
vote
0answers
40 views

How to recognize plaid / tartan?

I have an idea for a side-project: I'd like to be able to start with an image of a Scottish kilt, and automatically determine what tartan is used. For example, this is my (MacGill) tartan. Ideally, I'...
0
votes
1answer
61 views

Tagged dataset with photos for race detection

Looking for the tagged dataset, because I would like to identify race by photo. I tried using the UTKFace dataset from Kaggle, but it outputs hispanic and Arab people on images as ...
0
votes
1answer
88 views

Creating an "unclassified" class in Random Forest

I am trying to classify satellite based images by creating a region of interest and then classifying according to it. I am using a Jupyter notebook using python to do that. I used a Random forest ...
1
vote
0answers
11 views

Generalise a CNN model for Question vs Spam . Techniques to generalise the model apart from more data

For my problem, every image which is not a picture of a question on a paper (either from text book or handwritten), is a spam. It means that each and every image in this world is a spam for my case ...
1
vote
0answers
17 views

Image classification tool for detection of small features

I have a dataset of images of damaged cars. Each image has an associated mask of overall damage and severity index of each type of damage. Unet successfully predicts the overall mask of damaged area ...
-1
votes
1answer
33 views

Suitable neural network type to classify text in images

I have images that contain text and I am not sure what is the type of NN that can do the job for me. Basically, it will have to read the images and understand the text in order to be able to classify ...
0
votes
1answer
49 views

Single image feature reduction at inference time : SVM

I am trying to train a SVM classifier using scikit-learn.. At training time I want to reduce the feature vector dimension. I have used PCA to reduce the dimension. ...
1
vote
0answers
108 views

Positive/negative training sample imbalance in multi-label image classifiers

I'm trying to train VGG-16 on the Pascal VOC 2012 dataset, which has images with 20 labels (and a given image can have multiple classes present). The examples are highly imbalanced, so I've "...
2
votes
1answer
39 views

Difference between convolution structures

I am having a hard time understanding the difference what is a multichannel CNN: In the paper titled, "A Multichannel 2D Convolutional Neural Network Model for Task-Evoked fMRI Data ...
2
votes
1answer
206 views

Training CNN on a huge data set

I am trying to train an AlexNet image model on the RVL-CDIP Dataset. The dataset consists of 320,000 training images, 40,000 validation images, and 40,000 test images. Since the dataset is huge I ...
1
vote
1answer
274 views

Understanding 'scale_boxes' in YOLO Algorithm of CNN

I'm studying Andrew NG's Convolutional Neural Networks and am in Week 3 of the course which deals with object detection using YOLO algorithm . I don't understand one section in the programming ...
1
vote
1answer
603 views

How do reshape an image to fit my Mnist Convolutional model?

I have done research but cannot seem to find what's wrong here I have created this model for Mnist digit clasification : ...

1 2 3
4
5
14