The Stack Overflow podcast is back! Listen to an interview with our new CEO.

Questions tagged [image-recognition]

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).

Filter by
Sorted by
Tagged with
1
vote
1answer
14 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
0answers
7 views

Tesseract training- JTessBoxEditor issue

I am trying to train my tesseract by making box characters in the images but the JTessBoxEditor is not recognising any characters. When running the command --> tesseract eng.arial.exp1.tiff eng.arial....
0
votes
1answer
13 views

How to perform preprocessing for hyperspectral images

Here I would like to apply the CNN and DNN for face recognition computing and later will compare that both of them which one is better or faster My idea is - In the UWA hyperspectral face database, ...
0
votes
0answers
10 views

Why is Dice loss neglecting random classes?

I implemented Dice loss for a semantic segmentation problem (with a severe class imbalance in my dataset) as follows: ...
0
votes
1answer
19 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
1answer
12 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 ...
0
votes
1answer
22 views

A Question: is it possible for me to create an AI that learns to play games which I did not create?

Mainly, I have a question which I could not find an answer for anywhere, about an AI machine learning game. Is it possible for me to create an AI which can learn a game that I did not myself create, ...
1
vote
0answers
13 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
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
22 views

Image Recognition Model with Adaptive Learning

Problem Statement: To be able to detect faces of specific people with good accuracy and tag those images with the names of the people it contains. To do this we have about 40 images person, and 10 ...
0
votes
0answers
19 views

Deep learning, signal processing and feature engineering

I have a signals represented in python in dense matrices (the values are y-coordinates from a chart - eg. weather temp etc. in different locations around the world). I'm currently trying to process/...
0
votes
0answers
8 views

How to use skimage.feature.hog to calculate hog of training data where examples are stacked vertically

I have a $n*1024$ dimensional $2D$ array where n is number of examples which contain n images($32*32$) stacked vertically. I would like to calculate the hog of these images ...
0
votes
0answers
25 views

FAISS for similar image search

I have looked at FAISS examples for feature storage and querying. I have not seen any example specific to store / retrieve image vectors ? Please share if there are such real life examples. https://...
1
vote
0answers
35 views

Intersection Over Union / Bounding Box for multiple bounding boxes in an image

My image has 4 ground truth bounding boxes and the prediction just has 3 bounding boxes I need to calculate the quality of bounding boxes predicted. I know how to calculate IoU / IoBB for 2 ...
0
votes
1answer
53 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
0answers
25 views

image classification vs image Segmentation

i'm aware of difference between image classification and image segmentation (or detection) I can't find any article comparing performance between 2 approch. I would like to know if doing image ...
0
votes
0answers
127 views

TensorFlow: What is wrong with my (generalized) dice loss implementation?

I use TensorFlow 1.12 for semantic (image) segmentation based on materials. With a multinomial cross-entropy loss function, this yields okay-ish results, especially considering the sparse amount of ...
1
vote
0answers
15 views

How do I identify specific parts of a PDF document?

I have a bunch of medical records that I have to input manually. I would like to automate this but all of the records are in different formats. What is the best strategy to build a deep learning model ...
2
votes
0answers
28 views

Why is a general/original softmax loss not preferred in FR (face recognition)?

In some papers I've read that softmax loss is not preferred in FR since it does not give a good inter-class and intra-class margins, but could not understand 'why?'. So can someone explain, why ...
0
votes
0answers
11 views

Selfie image embeddings

https://arxiv.org/pdf/1906.02940.pdf I have read an article and want to implement an embedding algorithm. My problem is that I do not fully understand how the classifier is built in the decoder. More ...
0
votes
0answers
37 views

Can Microsoft's cognitive service find similar person in a set of images without using the face service?

I need to create an application that can detect if a person X entered as an input exists in an image set and return as output all the images in which the person X exists. The problem is that the ...
3
votes
1answer
37 views

How and Why to rescale image range between [0,1] and [-1,1]

I am trying to implement model described in Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network in which author says in section 3.2 that We scaled the range of the ...
3
votes
1answer
40 views

Super Resolution CNN vs Regular CNN

I am digging into finding a solution for background subtraction and one of the requirements is to not loose in quality of input image. Found that there is a specific type of CNN like Super Resolution ...
4
votes
1answer
50 views

Triplet loss function for face recognition?

In the Andrew-NG coursera course on Convnets he talked about triplet loss function for one shot face recognition. The formula given in the video is, $$\to \small \small \small ||f(A)-f(P)||^2 \;+\;\...
1
vote
2answers
31 views

Training a CNN to convert ellipses into circles

My current project has to do with modeling the effects of blurring/convolution of objects in various imaging processes. Right now, I am starting off with a preliminary, artificial model. I am using ...
0
votes
2answers
29 views

How to train or approach the image datasets with different resolution in Deep Learning

Image classification: I am having a data set of image collection more than 10k but even though all are the same image but taken in different sizes (pixels into pixels) some are in square and some are ...
0
votes
1answer
10 views

Storing masks in jpg format

I've created masks(numpy array with 0,1 as values) and tried exporting this array to jpg using matplolib but it's not exporting the values as it is. I'm getting a range of pixel values in resulting ...
0
votes
0answers
7 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
1
vote
1answer
32 views

conv net data retrieval on unseen class

I have build a conv net for image classification which work "well" Now I extract features from last fully connected layer and use it for image retrieval (find image most similar to my target image) ...
0
votes
0answers
20 views

Have you come across a dummy passport or drivers license dataset for training models?

We've built a new public benefits screening application that can recognize passports, drivers licenses etc from scanned images, used for people to prove identity when applying for government benefits, ...
1
vote
0answers
23 views

Best OCR approach on documents with different formats to find one specific information

Unfortunately, because of confidential data, I can't give a more specific explanation. The Problem So I've got a few documents that in general contain the same information but have different formats....
0
votes
1answer
22 views

Is text recognition by definition a part of image recognition?

I'm referring to more advanced text recognition systems that are using neural networks to find and extract text from images like the ones Google and Microsoft are offering on their ML platforms. If ...
1
vote
0answers
24 views

Semantic Segmentation using Scipy or Scikit-image

Many days ago I saw a user using scipy function to get region of interest (RoI) in an image using different colors. I believe it was some sort of filter. Now I'm trying to do the same but I'm not able ...
0
votes
0answers
11 views

Feedback on duplicate and near-duplicate image detection

Good morning all, I recently completed building a script that does the following: Stores a list of all .jpg images existing in specified drive. Cleans/ids duplicates through md5sum Iterates ...
1
vote
2answers
85 views

Why do we use a softmax activation function in Convolutional Autoencoders?

I have been working on an image segmentation project where I have created a convolutional autoencoder. I saw this image and implemented it using Keras. At the output layer, the author has used the ...
0
votes
1answer
18 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 ...
1
vote
1answer
152 views

Extract text from a image - OCR

This is the first time I am working with OCR. I have an image and want to extract data from the image. My image looks like this: I want to extract the parameters and the values against them. Can ...
0
votes
0answers
10 views

In which publication was the term “Dimension-Hopping” coined?

Apparently Geoff Hinton coined the term but was it through literature or lecture? I just want to add a reference for using the term in my report. Dimension-Hopping in Machine Learning
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 ...
0
votes
0answers
5 views

Analyzing multispectral images data from a drone

We are planning to develop an application/software for monitoring of rice field. After researching, I was curious on how to analyze the data from drone camera. Reading the data and then showing the ...
0
votes
0answers
66 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 ...
1
vote
0answers
13 views

How to locate the invoice within a camera captured image?

The demand is to locate the invoice within a camera captured image about that invoice. The invoice is always a white paper with printed black or blue characters, tables and red stamps. Sometimes the ...
0
votes
1answer
42 views

Data set of vectors of SVG paths for digits

I have used the MNIST data set many times to train models for digit recognition based on object character recognition (OCR). I am now trying to do the same but with a data set of svg paths.. I am ...
0
votes
0answers
15 views

State of the art in accurate object tracking & detection

Im working with an offline video file which has vehicles in it. I tried using YOLOv3, but it is not very accurate. Moreover, it kind of fails in occlusion. I am concerned more about accuracy than ...
0
votes
0answers
59 views

Facial Recognition Using One shot Learning Research Paper

1) I am looking for a latest Research Paper for "Facial Recognition Using One shot Learning" for my semester Project. I want to implement that paper and want to improve that. i have searched on ...
4
votes
1answer
78 views

How can one quickly look up people from a large database?

Vocabulary Face detection: Finding all faces in an image. Face representation: The simplest way to represent a face is as an image (pixels / color values). This is not very space efficient and likely ...
1
vote
1answer
296 views

How to encode a time series as an image to feed it into CNN?

I want to try CNN in the task of stock chart pattern recognition. I suspect that feeding a line chart won't work because the image will have a lot of empty pixels. What time series encoding options ...
0
votes
0answers
38 views

Is it possible to make a 'forked path' neural network?

I want to make a network, specifically a CNN for image recognition, that takes an input, processes it the same way for several layers, and then at some point splits before coming to two different ...