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
41
votes
2answers
37k views

How to prepare/augment images for neural network?

I would like to use a neural network for image classification. I'll start with pre-trained CaffeNet and train it for my application. How should I prepare the input images? In this case, all the ...
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 ...
18
votes
4answers
23k views

What is the difference between Inception v2 and Inception v3?

The paper Going deeper with convolutions describes GoogleNet which contains the original inception modules: The change to inception v2 was that they replaced the 5x5 convolutions by two successive ...
11
votes
3answers
12k views

Image resizing and padding for CNN

I want to train a CNN for image recognition. Images for training have not fixed size. I want the input size for the CNN to be 50x100 (height x width), for example. When I resize some small sized ...
11
votes
1answer
3k views

Reason for square images in deep learning

Most of the advanced deep learning models like VGG, ResNet, etc. require square images as input, usually with a pixel size of $224x224$. Is there a reason why the input has to be of equal shape, or ...
11
votes
2answers
16k views

How many images per class are sufficient for training a CNN

I'm starting a project where the task is to identify sneaker types from images. I'm currently reading into TensorFlow and Torch implementations. My question is: how many images per class are required ...
10
votes
3answers
5k views

Is there a person class in ImageNet? Are there any classes related to humans?

If I look at one of the many sources for the Imagenet classes on the Internet I cannot find a single class related to human beings (and no, harvestman is not someone who harvests, but it's what I knew ...
9
votes
3answers
2k views

Why use convolutional NNs for a visual inspection task over classic CV template matching?

I had an interesting discussion come up based on a project we were working on: why use a CNN visual inspection system over a template matching algorithm? Background: I had shown a demo of a simple ...
8
votes
3answers
5k views

Are there any image classification algorithms which are not neural networks?

Image classification is the task of assigning one of $n$ previously known labels to a given image. For example, you know that you will be given a couple of photos and each single image has exactly one ...
8
votes
1answer
159 views

Convolutional network for classification, extremely sensitive to lighting

I trained a convolutional network to classify images of a mechanical component as good or defective. Though the test accuracy was high, I realized that the model performed poorly on images which had ...
7
votes
1answer
18k views

How can I get the ImageNet ILSVRC 2012 data used for the classification challenge?

I would like to see if I can reproduce some of the image net results. However, I could not find the data (the list of URLs) used for training / testing in the ILSVRC 2012 (or later) classification ...
7
votes
2answers
8k views

Updating the weights of the filters in a CNN

I am currently trying to understand the architecture of a CNN. I understand the convolution, the ReLU layer, pooling layer, and fully connected layer. However, I am still confused about the weights. ...
7
votes
1answer
8k views

feature extraction for a pretrained model in keras

Keras has a way to extract the features of a pretrained model, described here https://keras.io/applications/ ...
7
votes
4answers
7k views

tool to label images for classification

Can anyone recommend a tool to quickly label several hundred images as an input for classification? I have ~500 microscopy images of cells. I want to assign categories such as 'healthy', 'dead', 'sick'...
7
votes
5answers
2k views

Covariate shift detection

Is there any standard approach for detecting the covariate shift between the training and test data ? This would be useful to validate the assumption that covariate shift exists in my database which ...
7
votes
2answers
617 views

Validation showing huge fluctuations. What could be the cause?

I'm training a CNN for a 3-class image classification problem. My training loss decreased smoothly, which is the expected behaviour. However, my validation loss shows a lot of fluctuation. Is this ...
7
votes
4answers
2k views

Build a tool for manually classifying training data images

I have a large number of images that I need to classify for training a clustering algorithm, and I would like to do so offline (the data is proprietary). Basically, I'd like to build a desktop survey ...
7
votes
3answers
311 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 ...
7
votes
3answers
3k views

ReLU vs sigmoid in mnist example

PLEASE NOTE: I am not trying to improve on the following example. I know you can get over 99% accuracy. The whole code is in the question. When I tried this simple code I get around 95% accuracy, if I ...
7
votes
1answer
1k views

Bag of Visual Words

What I am trying to do: I am trying to classify some images using local and global features. What I have done so far: I have extracted sift descriptors for each image and I am using this as my ...
7
votes
2answers
785 views

Difference between training and test data distributions

A basic assumption in machine learning is that training and test data are drawn from the same population, and thus follow the same distribution. But, in practice, this is highly unlikely. Covariate ...
7
votes
2answers
123 views

Neural Network Architecture for Identifying Image Copies

I have a large image collection and wish to identify the images within that collection that appear to copy other images from the collection. To give you a sense of the kinds of image pairs that I ...
6
votes
4answers
621 views

What are the possible ways to detect skin while classifying diseases?

I am working on a skin disease classification problem where I have successfully created a classifier ( TensorFlow + Keras ) which can classify images of two skin diseases. The sample image needs to ...
6
votes
2answers
79 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 ...
6
votes
1answer
4k views

Data preprocessing: Should we normalise images pixel-wise?

Let me present you with a toy example and a reasoning on image normalisation I had: Suppose we have a CNN architecture to classify NxN grayscale images in two categories. Pixel values range from 0 (...
6
votes
2answers
5k views

Where can I get labels for small ImageNet?

I have recently downloaded the small image net dataset: http://image-net.org/small/download.php The archives contain a lot of images, but no other files. How do I know which label the images have?
6
votes
1answer
4k views

Image Captioning in Keras

I am trying to implement demo of Image Captioning system from Keras documentation. From the documentation I could understand training part. ...
6
votes
2answers
152 views

Combining 2 Neural Networks

2 images as input, x1 and x2 and try to use convolution as a similarity measure. The idea is that the learned weights substitute more traditional measure of similarity (cross correlation, NN, ...). ...
6
votes
1answer
118 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 ...
6
votes
0answers
165 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 ...
5
votes
1answer
2k views

how to interpret predictions from model?

I'm working on a multi-classification problem - Recognizing flowers. I trained the mode and I achieved accuracy of 0.99. To predict, I did: ...
5
votes
1answer
5k views

How to implement global contrast normalization in python?

I try to implement global contrast normalization in python from Yoshua Bengio's deep learning book. From the book, to get normalized image using global contrast normalization we use this equation $$\...
5
votes
2answers
213 views

How is it possible to process an image with a few neurons?

An 1024*1024 pixel image has around one million pixels. If I would like to connect each pixel to an R,G,B input neuron, then more than 3 million neurons are needed. It would be really hard, to train ...
5
votes
1answer
2k views

What is the depth of an image in Convolutional Neural Network?

I am learning cs231n Convolutional Neural Networks for Visual Recognition. The lecture notes introduce the concepts of width, height, depth. For example, In CIFAR-10, images are only of size ...
5
votes
1answer
833 views

The most used loss function in tensorflow for a binary classification?

I am working on a binary classification problem using CNN model, the model designed using tensorflow framework, in most GitHub projects that I saw, they use "softmax cross entropy with logits" v1 and ...
5
votes
3answers
2k views

Binary classification of similar images with small region of interest

I have a dataset of microscope images and I want to train a ML/DL algorithm to perform binary classification. The positive class is when there is only one cell in the image, and the negative class is ...
5
votes
1answer
1k views

RELU vs Pooling

Does RELU means to change pixel value to 0 if it is negative anywhere , and later if we apply maximum pooling then what is the use of RELU because in this step we choose maximum value so no matter it ...
5
votes
3answers
5k views

Crop background from Image

I try to write a program to crop background from an image. This is a sample of my training data. I have images with and without a background. (manually cropped) The background is always similar (...
5
votes
4answers
9k views

Image classification in python

I have a set of images that are considered as good quality image and other set that are considered as bad quality image. I have to train a classification model so that any new image can be said good/...
5
votes
2answers
11k views

Where to find list of Tensorflow pretrained models available in download.tensorflow.org/models

I am trying the find the pretrained models (graph.pd and labels.txt) files for Tensorflow (for all of the Inception versions and MobileNet) After much searching I found some models in, https://...
5
votes
1answer
233 views

Should I prevent augmented data to leak to the test/cross validation sets

I have been working with the cats vs dogs dataset from kaggle which consist on 25000 images of cats and dogs labelled accordingly (btw, great dataset, totally recommended!) One of the things I did ...
5
votes
1answer
360 views

What is difference between intersection over union (IoU) and intersection over bounding box (IoBB)?

Can someone give a detailed explanation IoU and IoBB along with that the differences between them.
5
votes
2answers
222 views

How to predict on part of image after training on other part of image?

I have images of identity cards (manually taken so not of same size) and I need to extract the text in it. I used tesseract to predict bounding boxes for each letter and am successful to some extent ...
5
votes
1answer
372 views

Solving multi label image classification using TimeDistributed dense layer

I have a multi label image dataset having 5 labels. Each image can have more than one label at the same time. I am using a convolutional neural network to extract features and those extracted features ...
4
votes
2answers
6k views

How to maximize recall?

I'm a little bit new to machine learning. I am using a neural network to classify images. There are two possible classes. I am using Sigmoid activation at the last ...
4
votes
3answers
2k views

How to adapt the softmax layer for multiple labels?

Question: A image has multiple labels. Given a set of image with labels, how to adapt the softmax layers? My idea: Encode multiple labels to 0-1 variables. Use logistics regression as the output ...
4
votes
2answers
5k views

Training data set for food image recognition [closed]

There are many excellent posts and answers referencing data sources. However I can't seem to find many for food image/photograph recognition. I would have thought, with so many people taking and ...
4
votes
1answer
5k views

How to prepare colored images for neural networks?

I have seen many examples online regarding the MNIST dataset, but it's all in black and white. In that case, a 2D array can be constructed where the values at each array element represent the ...
4
votes
1answer
777 views

Has anyone tried to use the hierarchy of ImageNet?

The classes of ImagNet have a hierarchy. Did anybody try to build a hierarchy of classifiers to use this fact? Searching for "multistage classification" leads to different results.
4
votes
1answer
2k views

Deconvolutional Network in Semantic Segmentation

I recently came across a paper about doing semantic segmentation using deconvolutional network: Learning Deconvolution Network for Semantic Segmentation http://arxiv.org/abs/1505.04366. The basic ...