Questions tagged [image-recognition]

For questions related to image recognition in the context of AI.

Filter by
Sorted by
Tagged with
0
votes
0answers
19 views

Does adding new keypoints increase accuracy for foot keypoint detection?

I am trying to have better results for foot keypoint detection(or foot pose estimation). In foot keypoints dataset the images labeleld for 6 different keypoints(big,small toes and heel for each foot). ...
1
vote
1answer
23 views

Validity of ImageNet for measurement of the model performance

ImageNet dataset is an established benchmark for the measurement of the performance of CV models. ImageNet involves 1000 categories and the goal of the classification model is to output the correct ...
0
votes
0answers
33 views

How to improve accuracy of CNN used for facial micro-expression analysis

From the paper (1) Facial expression analysis using CNN, the results using CNN show a 65% and 62% accuracy respectively, for emotion classification and state of mind identification. Proposed Method: ...
1
vote
0answers
48 views

What exactly do gradient-based saliency map tell us?

As far as I understand, gradients are supposed to tell us 1) the magnitude and 2) direction, to update a parameter such as to minimize the loss function. Regarding saliency maps, which use gradients ...
0
votes
0answers
16 views

Comparing large numbers of images to find outliers

There are many methods you can use to compare two images in ML (Siamese NN, CNNs, Ect.) What I cannot figure out is comparing a large number of images (Without Retraining) to find images of a ...
0
votes
0answers
24 views

Encoding Image Priors into CNN

There's a core problem with all of ML which I haven't really seen made explicit: the issue is every model needs to have an assumption on the structure of the data you learn and this assumption needs ...
0
votes
0answers
30 views

Why am I getting a very small number as CNN prediction?

I created a CNN using Tensorflow to identify pneumonia and sometimes it returns a very small number as a prediction. why is this happening? I have attached the link for the dataset Here I how I ...
0
votes
1answer
40 views

For a task that searches for an image artifact within a picture, can existing tools can be used or do I need to design the process myself?

I am familiar only with basic AI/NN concepts but never worked with any libraries/tools as tensor flow. Currently, I have a task for which AI might be ideal: detection of a certain image artifact in a ...
0
votes
1answer
27 views

Multiple labels for the same rectbox?

My goal is to identify the horse in a photo. I'm dealing with about 500 unique horses. My feeling is that the best way to distinguish one horse from another is by its face. So I trained Yolov5 ...
0
votes
1answer
38 views

Can I flip a video to generate more data for action recognition?

There are 8 distinct action classes and around 50+ videos per class. I was wondering if flipping videos from the training set can be a good option to generate additional data. Is it?
2
votes
1answer
48 views

How do automatic high-beam headlights work on cars?

Modern cars can operate high-beam headlights automatically: They automatically switch from high-beam headlights to low-beam ones (less intense) when you enter a town or there is a car in front of you ...
1
vote
1answer
32 views

What sort of out-of-the-box technology could be used to create work similar to artist Refik Anadol?

Refik Anadol has machines view actual pictures and then has the machine create its own images. This video shows some of the stuff he does. What kind of out-of-the-box tools (e.g. a Python package) or ...
1
vote
0answers
30 views

What is the purpose of hard distillation?

In order to get a smaller model, one often uses larger model, that performs reasonably well on the data as a teacher, and uses the information from large model to train the smaller one. There are ...
0
votes
0answers
24 views

Without using data augmentation gives results better than using data augmentation

I am a beginner to deep learning, I'm doing the image classification problem on a small self plant disease imaging dataset (400 images). I am doing transfer learning (pre-trained ...
0
votes
0answers
37 views

How to increase accuracy of image orientation classification (Left, Right, Center)?

I am working on classifying images in "Left", "Right", "Center", "Back". Training and Validation images look like this: The images are "Left", "...
1
vote
0answers
41 views

Is having near-duplicates in a training dataset a bad thing?

I am making a labeled dataset of images from web streams for a CNN classification. Pictures from the same stream are quite similar as far as background, but slightly different as far as the main ...
1
vote
0answers
37 views

Image recognition neural network: scaling and rotation

Are there some effective and robust solutions for scaling and rotation for image recognition with the neural networks (NN)? I see tons of sources on the Web with explanation how neural network is used ...
0
votes
0answers
29 views

Machine Learning Algorithm for OCR on full pages of text

I would like to build an OCR application. In. particular, I want my algorithm to scan entire pages of text in a specific niche language. I was therefore wondering if there are some algorithms that ...
2
votes
0answers
26 views

Is soft labeling the same thing as label smoothing?

I have some data with soft labels and I am trying to figure out the best approach to solve the problem with Machine Learning (since regular classification is of the table, i.e. hard labels). However, ...
1
vote
0answers
11 views

How to localize and classify objects in video

What methods are used to localize an object in an video and classify that object? Example: I have a camera which detects an pickup truck driving into a garage of three (1,2,3). In need to know if the ...
2
votes
2answers
70 views

How to classify two very similar images using Deep Learning?

I am a newbie in Computer Vision. I have a scenario in which I have a stationary camera in a factory. I want to detect whether the technician is working on the machine or not. Images are like the ...
0
votes
1answer
30 views

Should I label static objects on video dataset?

I'm using nvidia Transfer Learning Toolkit to detect cars in some video frames. I found some dataset (for example https://www.jpjodoin.com/urbantracker/dataset.html and https://www.kaggle.com/...
1
vote
0answers
15 views

What does the lambda parameter in the paper "Interpretable Explanations of Black Boxes by Meaningful Perturbation" do?

I do not understand the purpose of the $\lambda$ parameter in equation 3 of the paper Interpretable Explanations of Black Boxes by Meaningful Perturbation. $$m^{*}=\underset{m \in[0,1]^{\Lambda}}{\...
0
votes
0answers
18 views

when updating the bias matrix, do we get the total sum of dZ or the sum of the axis of dZ?

I'm currently studying how to implement a neural network from scratch to know how it works, I came across this article: https://www.samsonzhang.com/2020/11/24/understanding-the-math-behind-neural-...
1
vote
0answers
20 views

Is it possible to create a simple face-tracking app that can monitor how much time one spends at their desk?

Context: I'm an experienced programmer with a graduate education in AI and previous CUDA programming experience. I'm versed in Machine Learning but am out of the loop -- I've not used any of the ...
1
vote
0answers
28 views

How to deal with images that do not contain any object of interest?

I'm currently working on an iOS App where I want to detect if there is a table, chair or bench in the current camera input. My idea was to take the MobileNetV2 model and get it to classify these three ...
1
vote
0answers
25 views

DeepLabV3: Why use global average pooling in the ASPP module?

I'm trying to understand the rationale of the various modifications the authors of the DeepLab models have made to their third version, DeepLabV3. In the paper, the following is written: ASPP with ...
0
votes
0answers
27 views

What is "fill" algorithm used for image resizing and cropping?

I was going through this documentation directed by Codelab-Developer-Google. In order to resize an image, the notebook is using the "fill" algorithm. See the below code ...
0
votes
0answers
11 views

Inconsistent Classification Accuracy between Classification Network & Object Detection

I have been working on an object detection and classification problem, and I am having understanding a discrepancy in my results. I am try to detect and classify 2 classes. These objects are ...
1
vote
0answers
27 views

Is it possible to train a perceptron to tell if a picture is a dog or cat?

I know perceptron is a linear classifier that tells linearly separable binary class data, such as iris setosa vs. iris versicolor via their sepal's length and width. I'd just like to know if I have 2 ...
0
votes
0answers
24 views

Document clustering from ordered pages list

I have a series of ordered pdf pages which own to different documents. Let me give you an example: Pages: 1 2 3 4 5 6 True Pages: 1 2 | 1 2 3 4 So I have like six ordered pages, two of which from ...
0
votes
0answers
19 views

New image-to-image translation algorithm for other type of tasks

I found this amazing new research paper "High-Resolution Photorealistic Image Translation in Real-Time: A Laplacian Pyramid Translation Network" and an associated video. It's about a new ...
0
votes
1answer
61 views

Number of classes vs number of parameters/layers?

How to estimate the number of parameters in CNN for object detection? I know that there are some well-known architectures that was trained on a lot of data (AlexNet, ResNet, VGG, GoogleLeNet). But ...
0
votes
0answers
35 views

How can my CNN produce an "unknown" label?

I have a dataset of 20k images of infected mango. I have built a web-based app using Flask, where a user can upload a picture, and my CNN model detects the disease. I have 6 classes in the model, ...
0
votes
0answers
24 views

Finding an object in a large image

I am looking for an algorithm to solve the following problem. There is a very large image (road map). A small distorted part of big image is fed into the input. I want to find the location of a small ...
0
votes
1answer
38 views

Cnn for Combination of both digits and letters(small and capital) [closed]

Hi I am new to machine learning can anyone suggest open dataset consists of both digits and letters(small,capital) I want images consisisting of both digits and letters to train my cnn model and make ...
0
votes
0answers
22 views

Is it possible to do object detection on an object classification dataset?

I'm new to computer vision, which I find fascinating. I wonder whether it is possible or if there has been any research into going from object recognition data to object detection. In other words, ...
0
votes
0answers
11 views

Can I get some advices on inferencing people from upwards using Yolov5?

I'm trying to inference people from upwards and count them using Yolov5. I know the controversy between yolov5 and yolov4, but for me, Yolov5 is more easier and reliable to use, also the setup. I have ...
0
votes
0answers
33 views

How to train feedforward network to recognize images?

Context I'm trying to create network for digits recognition. All digits are the same font and size of 40x40. I know that I can use feedforward network or CNN. I'd like to use the first one. Issue I ...
2
votes
1answer
50 views

How to properly use Flatten layer?

Context I'm trying to create net that will be able to recognize printed-like digits. Something like MNIST, but only for standard printing font. Images are of the size 40x40 and I'd like to put them ...
0
votes
1answer
31 views

What algorithm to use to classify data by spatial relations?

Let's assume I have dataset of image-like 2D samples where values can be divided into few discrete levels (for example 1, 2, 3 and 4) like in the image below, where each color maps different value, ...
0
votes
0answers
15 views

How to make CNN to recognize whole picture, not just the details?

In my current project I use CNNs to analize plots (CNN autoencoders for feature extraction and KMeans for clusterization) and I get the feeling that these networks, can extract only features that are ...
1
vote
0answers
19 views

How can I train a model to recognize object with zoomed-in image?

Humans are good at guessing animals with zoomed-in images from patterns of fur/skin. (For example, if we saw a black-white pattern fur, it must be a zebra) I have some experience guessing a car model ...
0
votes
2answers
69 views

Accuracy Not Going Above 30%

I am trying to make a big classification model using the coco2017 dataset. Here is my code: ...
1
vote
1answer
85 views

Should one use an "other" category in image classification?

In image classification, there are sometimes images that do not fit in any category. For example, if I build a CNN in Keras to classify Dogs and Cats, does it help (in terms of training time and ...
0
votes
1answer
25 views

Why do popular object detecting models output heatmaps instead of coordinators of object directly?

I think heatmap outputs of architectures like CenterNet, OpenPose, etc. can be changed to coordinator outputs, and loss functions like focal loss can be modified so they can deal with coordinators ...
1
vote
1answer
62 views

Is there a full and precise formulation of Theorem 1 in the Integrated Gradients paper?

Theorem 1 (page 5) in the paper about Integrated Gradients states that Integrated gradients is the unique path method that is symmetry-preserving. What I miss is A precise formulation of the ...
0
votes
1answer
49 views

Denoising Images When Training a Classification Model

Suppose you have a binary outcome variable and have some training data (10,000 images in jpg format). Also you have a test set of say 11,000 images. If we want to train a classification model and want ...
2
votes
2answers
94 views

How to recognize sequence of digits in an image

I am learning to program neural networks and others, and I would like to know how I can get the numbers that are in an image, for example, if I pass an image that has 123 written, get with my model ...
1
vote
1answer
77 views

Predicting continous value with CNN (prediction of fruit maturity)

I want to train some IA algorithm to be able to evaluate the maturity of a fruit (say, measured in numbers of days before rotten) based on an image of the fruit. My first instinct is to go with ...

1
2 3 4 5 6