Stack Exchange Network

Stack Exchange network consists of 174 Q&A communities including Stack Overflow, the largest, most trusted online community for developers to learn, share their knowledge, and build their careers.

Visit Stack Exchange
Join us in building a kind, collaborative learning community via our updated Code of Conduct.

A form of signal processing where the input is an image. Usually treating the digital image as a two-dimensional signal (or multidimensional). This processing may include image restoration and enhancement (in particular, pattern recognition and projection).

2
votes
0answers
13 views

Better to crop or compress training data?

I've been trying to make an object recogniser in Tensorflow and have used labelImg to classify large electrical transmission towers at varying distances. In order to make 10-16MP (~2-7MB) images train ...
1
vote
0answers
26 views

Converting video into frames using openCV

I am converting video into video-frames using the given code converting video into frames ...
1
vote
1answer
27 views

Why is convolution filter used instead of correlation filter in CNN?

When I saw the two results of applying convolution filter and correlation filter, the results have the same distribution and are just flipped. Why is convolution filter used instead of correlation ...
0
votes
2answers
21 views

Should we keep all channels when doing image classification?

I am discovering the world of image recognition and now trying to build an image classifier. The set of images I have have the shape (101,101,3) which means that it has 3 channels. If I'm not ...
0
votes
0answers
49 views

OSError: cannot identify image file <_io.BytesIO object at 0x7f5b2d2d9e60>

I created a lmdb dataset of images and labels but on reading the images, it is giving me error which I can't understand. Code: ...
0
votes
1answer
16 views

Is it possible to make tensorflow print out everything it see in a given image and not just the top five results?

I'm working through the python API tutorials for Tensorflow and I'm seeing the results that are normally displayed, but it's always giving me the top five results. I'm trying to discern all ...
3
votes
2answers
56 views

What is the loss function defined by Mnih and Hinton in their paper “Learning to Label Aerial Images from Noisy Data”?

In section 3.3 of the paper, they state that they use the cross entropy. Then they define the probability for a label to be a false positive as $\theta_0$ and a false negative as $\theta_1$. They use ...
0
votes
0answers
9 views

Where can I find a dataset of images of faces and descriptions of them?

I'm doing an ML project that generates descriptions of pictures of faces. Is there a publicly-available dataset that has a set of face images along with a short description of what the face looks like?...
3
votes
0answers
62 views

Machine Learning & Image Recognition: How to start?

I've been a full stack web developer for 15 years now and would like to be involved in machine learning. There is already a specific scenario for this: We have a database with several million products ...
1
vote
2answers
53 views

How to reduce the resolution of a Image(276*276 --> 48*48) without affecting the features in it

I have an image with resolution of $276*276$. I've created a Convolution Neural Network which accepts $48*48$ images. So, I want to resize that $276*276$ image to $48*48$ without reducing any features ...
1
vote
0answers
18 views

advice on distance metric for knn w/image recognition

I'm getting my feet wet with machine learning and am implementing a knn algorithm on a dataset that i've created. I've created a set of images of circles and squares and want the knn algorithm to ...
1
vote
1answer
24 views

How can I split an image into rectangles?

I have a labelled form to which people will add their name and a series of numbers. They will then take a picture of the form. Like so: I can get decent results by simply sending this to AWS ...
2
votes
1answer
21 views

calculation of average ROC in IMageNet paper?

The IMageNEt paper Image Net. presents the Average ROC curve for the 16 classes in the imagenet data, visit image figure. 8 in the paper. what is the known function to compute this ROC plot. As ROC ...
2
votes
1answer
52 views

How Do Bayesian Methods in Machine Learning Help With the Problem of Limited Data? Can This Be Used for Image Classification/Recognition? [closed]

When reading about machine learning, I've often come across information stating that Bayesian methods in machine learning are effective when you only possess a limited amount of data. As someone who ...
1
vote
1answer
43 views

Division of numbers from contours in opencv in python for cnn

I want to separate numbers in suppose 7638 into different images which can be predicted individually using cnn. By finding contours how can I divide each contour into separate image in python. To be ...
4
votes
1answer
36 views

Searching for a 3D Dataset, segmented by 2 or more Experts

We are looking for data sets with 3D images, preferably from the medical field. It is important that they have been segmented by more than one person/expert. An example of this is the BraTS Challenge ...
2
votes
0answers
39 views

Identifying computer scanned digits

I have digit images as below which I would like to identify: Some are of slightly worse quality : The images are not of a fixed resolution but are mostly in the range (80*20 to 130 *40). Due to ...
3
votes
1answer
46 views

How can you build a model that reads out receipts and invoices?

The objective is to build a model that is capable of identifying information on receipts and invoices that can look completely different. I've had a discussion with my brother about the right ...
2
votes
1answer
38 views

How do we predict what is in an image using unsupervised deep neural networks?

From my understanding of unsupervised DNNs for image classification: The input layer is a 4,096 dimension vector (for 64 x 64 images) The hidden layers represent much lower "features" as identified ...
0
votes
1answer
108 views

Detecting text region from an image

So I'm working on a document processing AI and I already have a character recognition model which performs decently well. Now the problem is, how do I feed each character to the model in order to make ...
1
vote
1answer
16 views

i need a characters /letters dataset for matlab

My final project is number plate recognition.i need a data set of A-Z characters and 0-9 letters. i donot find it on any website give me a data set or send me a link. i have to make a neural network ...
4
votes
3answers
434 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 ...
0
votes
2answers
33 views

Why would 2 sets of similar training samples take significantly longer to train?

I've built a fully-connected feed-forward neural network to recognize handwritten digits. I used MNIST and another very similar dataset (containing Arabic digits - same training set and test set count ...
2
votes
1answer
507 views

How does the bounding box regressor work in Fast R-CNN?

In the fast R-CNN paper (https://arxiv.org/abs/1504.08083) by Ross Girshick, the bounding box parameters are continuous variables. These values are predicted using regression method. Unlike other ...
0
votes
1answer
45 views

Image Matching to solve captcha

I am building a bot with python and I need some system to solve captchas like these: I think I need a deep learning algorithm, but coding one is a pain in the ass. Is there any easy solution to this? ...
2
votes
1answer
52 views

Is color information only extracted in the first input layer of a convolutional neural network?

In a convolutional neural network (CNN), since the RGB values get multiplied in the first convolutional layer, does this mean that color is essentially only extracted in the very first layer? ...
1
vote
1answer
46 views

Is there an AI service that could be used to classify 30,000 different tools and parts?

I'm trying to build an image classifier where people can take a picture of a tool or part and have the image classified. Much like bixby or amazon's tool to do something similar, but with only 30,000 ...
1
vote
2answers
74 views

In a convolutional neural network (CNN), when convolving the image, is the operation used the dot product or the sum of element-wise multiplication?

The example below is taken from the lectures in deeplearning.ai shows that the result is the sum of the element-by-element product (or "element-wise multiplication". The red numbers represent the ...
0
votes
1answer
30 views

Could we use image hasing techniques for images classification tasks?

I have read some articles about image hashing, and I would like to know if we could apply this technique for general purpose images classification tasks. Especially I would like to know which could ...
3
votes
2answers
409 views

How can I find out what class each of the columns in the probabilities output correspond to using Keras for a multi-class classification problem?

I'm using transfer learning to build an image recognition model using a pre-trained VGG network in Keras and excluding the final fully-connected layer to get the output weights. I'm then using these ...
7
votes
2answers
136 views

Can I get numeric data from a color map?

In my class I often need to work with color map images. I would show the image and try to make inferences/observations about different subjects. Often times I need to actually quantify some aspects, ...
0
votes
1answer
26 views

Image similarity without perspective

I want to determine the similarity between images based on different features. The images show the same type of object (e.g. cars). I want to order images based on their similarity (e.g. through a ...
0
votes
0answers
39 views

Comparing two images

I have to find the same obj (for example the same t-shirt) in two different images and I want to build a neural network that performs this operation. I was thinking to use something like that: https://...
2
votes
1answer
689 views

How does YOLO algorithm detect objects if the grid size is way smaller than the object in the test image?

In YOLO algorithm how do these grids output a prediction if some grids only see a small black portion of the car if the model was trained on datasets with full images?
1
vote
0answers
107 views

Image similarity: Similarity of mixed vector

In order to identify the similarity between images (products) I want to use a neural network approach similar to TiefVision. This pre-trained neural network is basically translating the images into a ...
0
votes
0answers
126 views

How do you train a machine learning model to learn how to adjust images (contrast, brightness, saturation, crop etc.) from manually adjusted images?

Are there any examples of this kind of implementation? How would the model recognize which properties need to be adjusted?
1
vote
0answers
41 views

Automatically extract original dataset from a line plot image

Given a line plot image (bitmap, png, etc) form, I'm looking to extract the set of original datapoints without any user input, as shown in the below image: The outcome should be something like below:...
3
votes
2answers
110 views

What to do when facial recognition fails to find a face?

I am currently implementing a CNN to recognise the identity of people given a portrait picture of the person. The objective is to maximise the clf.score function in sklearn, the database is composed ...
3
votes
2answers
92 views

Contemporary alternatives to SIFT for image feature extraction?

I've been learning about SIFT and all the ways its descriptors can be used to do different tasks. I am particularly interested in the way SIFT can be used for image classification. (e.g. A 2006 paper ...
0
votes
1answer
229 views

Pre trained vehicle detection network

I'm looking for a pre-trained net recognizing vehicles, something like the Inception network for images. If that is impossible to find which vehicle detection algorithm would you suggest, possibly ...
1
vote
1answer
124 views

Match an image from a set of images : Combine traditional Computer vision + Deep Learning/CNN

In the application I am developing, I have about 5000 product label images.(One label per product). One functionality of my application is that user can take a picture using his camera and get a ...
0
votes
1answer
293 views

How do I represent SURF Features into Bag of Words to determine Nearest Neighbors?

I'm trying to use Speeded Up Robust Features (SURF) to get the $k$ most similar images from a set of images in my directory. I'm planning to use $k$-Nearest Neighbours ($k$-NN) for this. As far as I ...
1
vote
1answer
109 views

Unsupervised learning if existing image captions match the images

I need to train a system on a large set of images and associated captions to determine which (image, caption) pairs are correct and which are not. I don't have any labeled pairs, but I can assume that ...
-1
votes
1answer
121 views

Should I gray scale the image?

I'm categorizing 30 types of clothes from the image using R-CNN Object Detection Library from tensorflow : https://github.com/tensorflow/models/tree/master/research/object_detection Does color matter ...
7
votes
2answers
72 views

Ways to reconstruct shuffled pixels of a video file?

Suppose that you have a video file which pixel order has been shuffled once. That is, a random order have been defined once and applied to all frames. Does it exist some known approach for ...
1
vote
0answers
230 views

RGB + Depth Encoding for CNNs

I need to train a CNN (YOLO to be precise) on RGB + depth information. I have the RGB input as a separate PNG file and the depth map as a separate PNG file. These PNG files are 8 bit depth, 3 channel ...
13
votes
4answers
3k views

Convolutional neural network overfitting. Dropout not helping

I am playing a bit with convnets, specifically I am using the kaggle cats-vs-dogs dataset which consists on 25000 images labeled as either cats or dogs (12500 each). I have managed to achieve around ...
1
vote
0answers
35 views

Faster R-CNN: Labels regarding the positive anchors when there are many classes

The authors of the original paper of Faster R-CNN when they refer to the positive anchors, they are labeled as 1. I guess they refer in binary classification. What happens in the case in a task we ...
4
votes
1answer
4k views

How to train an image dataset in TensorFlow? [closed]

As I am new to TensorFlow, I would like to do image recognition in TensorFlow using Python. For this Image Recognition I would like to train my own image dataset and test that dataset. Please answer ...
0
votes
1answer
508 views

Image Feature Vectors

I have downloaded a dataset from Amazon. http://jmcauley.ucsd.edu/data/amazon/ Dataset involves feature vectors of images. There are around 1.5 M feature vectors. Dataset consists of 10 characters (...