Questions tagged [computer-vision]

Computer Vision is a subfield of computer science which deals with analyzing and understanding images. This includes detection of objects like faces in images or segmenting images.

Filter by
Sorted by
Tagged with
1
vote
1answer
30 views

Feature extraction from sequence of images with Siamese Neural Network

I am trying to train a neural network to recognize certain actions in short movies. Each such movie consists of a fixed number of frames, each frame - the image is of course the same size, after ...
0
votes
1answer
23 views

Training CNN: Understanding number data generated while training the model

I am training CNN on kaggle and my training and test datasets shapes are as follows: ...
2
votes
0answers
28 views

What is the difference in computational cost at inference time between object detection and semantic segmentation?

I am aware that YOLO (v1-5) is a real-time object detection model with moderately good overall prediction performance. I know that UNet and variants are efficient semantic segmentation models that are ...
1
vote
1answer
46 views

Transfer Learning on Resnets/VGGs — Validation accuracy can never be over 75%

I am trying to classify skin cancer images into two categories -- malignant and benign. Literatures suggest that using pre-trained resnet/vgg network achieves more than 90% accuracy. However, with my ...
1
vote
0answers
19 views

Machine learning model (neural network or SVM) for unequal feature matrices size

I have feature matrices obtained from visual bags of words model for various dictionary sizes. Example, Nx5, Nx10, …., Nx15000. Where N is the number of samples and 5, 10, …15000 are the visual ...
1
vote
0answers
25 views

Why are axes-aligned bounding boxes used in object detection

I understand (I think) why in object detection, the result is a rectangle: it is a simple shape that can be defined by 4 variables (2 pairs coords of opposite corners or 1 pair of coords + width and ...
0
votes
1answer
24 views

Which F1-score is used for the semantic segmentation tasks?

I read some papers about state-of-the-art semantic segmentation models and in all of them, authors use for comparison F1-score metric, but they did not write whether they use the "micro" or &...
1
vote
0answers
89 views

Yolo issue with detecting positives

I've recently tried to implement a Yolo detector for traffic light detection based on yolo v1 implementation in Tensorflow/Keras. My model really struggles with detecting small objects. Loss function ...
0
votes
0answers
6 views

How do you compare outputs from different augmentations for consistency training?

I'm trying to figure out how papers using consistency train on unsupervised data, and I'm stuck on how outputs from different augmentations are compared. Since the augmentations are transformations, I ...
0
votes
0answers
188 views

How to convert VGG VIA Instance segmentation annotation to COCO/PASCAL for Tensorflow Object Detection?

I have VGG VIA JSON annotations for instance segmentation for counting diamonds from a given image. The annotations are mixture of Circle, Polygons, Polylines. However, I am planning to use the ...
-1
votes
1answer
49 views

LED status detector [closed]

I have a piece of custom device that displays its working status by blinking LEDs fitted on the device. for example, the led is ON means the board is on led is OFF means the board is off. red led ...
0
votes
0answers
20 views

Refactoring Tensorflow 2 to Distributed Tensorflow for CNN

I have been trying to reproduced this paper that is training a CNN with Tensorflow. Unfortunately, I only have access to limited computing resources. I have a few raspberry pi that I was thinking of ...
0
votes
0answers
7 views

How to predict multiple set of coordinates for signboards text localisation through neural network

I am creating a signboard translation model from scratch. I have images of signboards where there are multiple texts and I have the corresponding set of coordinates for multiple texts. I want to ...
0
votes
1answer
48 views

What I need to write in the line level of torch.vison for 21 classes?

In this code I found , line labels = torch.ones((records.shape[0],), dtype=torch.int64) ,that there is only one class and 0 in the case of Faster RCNN is reserved for the Background. What would be ...
1
vote
1answer
72 views

How can I save my learning rate on each finished epoch using Callbacks?

I used LearningRateScheduler for my model training. I want to save learning rates on each epoch in CSV file (or other document files). Is there any way to save those learning rates using callbacks?
1
vote
0answers
14 views

Liveness Detection System - Suggestions

I am trying to build a liveness detection system but till now I haven't been able to generate any significant results. I read the article by pyimagesearch this on the same topic but no luck. Tried ...
1
vote
1answer
81 views

How to plot multiple models val and traing acc/loss curve from csv files?

I trained multiple CNN models, after that, I saved models details (Like , training/Validation Acc/Loss ) by callbacks by using this codes : ...
0
votes
0answers
14 views

Saving the Autoencoder predicted image to a new directory

I trained an autoencoder model in Keras to generate denoised images given noisy images. The predicted images are stored in the "result" directory, with the individual filenames appended with ...
0
votes
0answers
13 views

Denoising Prior to Image Classification

From what I have read, Denoising during preprocessing for image classification tasks seems to be a bit controversial. While on one hand it might improve classification accuracy, the computational ...
0
votes
0answers
33 views

Mask RCNN 1 class only

I am looking to use only one class, person (along with BG, background), for the Mask RCNN object detection. I am using this link: https://github.com/matterport/Mask_RCNN to run the mask rcnn. Is ...
1
vote
0answers
15 views

Comparison of different ways of Upsampling in detection models

There are various ways to increase the resolution of tensor in (width, height) dimensions, frequently used in detection models like ...
0
votes
0answers
7 views

What should be the MINIMUM value of 'k' in LSH (Locality Sensitive Hashing) for 20M + data points?

For 20M + images, I'm thinking about using LSH for similarity of Vectors or data points or more precisely image Embeddings ...
0
votes
0answers
28 views

Unidentified Image error while loading images on Google Colab

I'm writing a code to make movie genre classification with movie posters. I opened a github repository where I put all the posters and cloned it on Colab. Until here, eveything works fine. When I'm ...
2
votes
0answers
28 views

Energy-Based modelling vs Deep Learning

I am doing some research on machine learning algorithms in the context of a seminar, which focuses on Energy-Based Modeling vs Deep Learning Modeling specifically in working with images. Now I know ...
0
votes
0answers
24 views

Darknet and Data Augmentation

In the darknet deep learning framework .cfg files we see parameters like angle, saturation, exposure These parameters are used ...
0
votes
0answers
19 views

Object detection in RGB-D images

Can you please recommend papers/github or smth about object detection on RGB-D images (NOT 3d cloud points).The result should still be objects in rectangles in the 2d image, as in the usual methods ...
2
votes
0answers
19 views

Statistical method to find the value which preserves the most information inside “most” of data points. (resize images to a common height)

So I have this data of around 88K images and I found out some interesting properties for my images. ...
0
votes
2answers
43 views

What is the best approach for detecting the defect?

Assuming that we have 10 same objects, they are lined up and equidistant. If any of them is rotated a very small angle(5 - 10deg), what is best method to detect them? I am using a camera to capture ...
0
votes
0answers
10 views

Evaluating the performance of tracking multiple objects detected with object detection

I have a ground truth dataset where the objects have been manually annotated and each object have been provided an ID that is consistent through time. There are no false positives or false negatives ...
0
votes
0answers
11 views

which image filter to use here

I have an image which is generated from noise using deep learning. When I zoom in on the image it looks like the image provided below. As you can see image is not sharp enough. I want to sharpen the ...
0
votes
0answers
9 views

Differential Learning Rates To Train Parts of A Network Faster

So I've had a rather "out there" idea. I want to train a dense network on a regression problem based on tabular data but I'd also like it to incorporate image data. My idea was to use a CNN ...
2
votes
0answers
17 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 ...
1
vote
0answers
17 views

What should be the best CNN model for Feature extraction of images for Image-Image search engine using LSH?

I have images something like the below: And like this: I have a huge data around 20M or so am I want to apply de-duplication and improve the search for this ...
1
vote
0answers
38 views

How to fit pretrained yolov4 model to other class?

I have already trained model for one class, so I have weights and how can i train it for second class? This model detects cars 100% and I need it to detect vehicle plate number, I used yolov4, darknet ...
0
votes
1answer
16 views

How to manage memory constraint and increase speed for 1 vs rest image similarity comparison for over 100k images for computer vision?

I'm looking for ideas on how to do things in a better way, efficiently when using Machine/Deep Learning. I am working on a search improvement problem using Computer vision where I am thinking about ...
1
vote
1answer
29 views

Creating new images [closed]

I would like to create new images of landscapes with deep neural network. If my input is a large dataset of pictures of landscapes, how can I do to output new pictures of landscapes ? Which techniques ...
3
votes
0answers
125 views

What are the 'protos' in TF Object Detection?

I am struggling to understand what are the 'protos' in TF Object Detection? Why do we need them here? Also, while setting up the TF API we need to download and compile protocol buffers. There is also ...
0
votes
0answers
34 views

Reading data from Twilio video streams

Tl;dr: I would like to read video streams coming from all the participants from this https://tfvideo-5708-dev.twil.io/video.html in python Details: I have a live tutoring website that uses Twilio ...
0
votes
0answers
37 views

Is there a pre-trained network trained on RGB-D (4) channels?

The most used pre-trained networks for computer vision (e.g. ResNet50) are trained on 3 channels (RGB). At the same time, many cameras used in robotics return RGB-D outputs, that is including depth ...
0
votes
0answers
31 views

Agglomerative Hierarchical Clustering on Images

My goal is to implement the agglomerative hierarchical clustering algorithm on an RGB image to cluster every pixel until some stopping criteria is reached. In order to do so, I assumed that each pixel ...
1
vote
1answer
826 views

Is ImageNet 1k a subset of ImageNet 22k

There are 2 different ImageNet datasets: ImageNet 1k usually referred to in papers as just ImageNet and the full ImageNet dataset also called ImageNet 22k. Is the ImageNet 1k a subset of the 22k? And ...
1
vote
1answer
30 views

what are the main differences between parametric and non-parametric machine learning algorithms?

I am interested in parametric and non-parametric machine learning algorithms, their advantages and disadvantages and also their main differences regarding computational complexities. In particular I ...
0
votes
1answer
35 views
1
vote
1answer
25 views

What do the parameters used in crop mean?

When we have an image to be used as an input to a CNN and we want to classify only part of the image, we usually feed the classifier with a crop of the image. Lets say my image is called frame and <...
2
votes
1answer
88 views

How to get pixel location in after rotating the image?

I'm trying to rotate some images with some boundary boxes, but I couldn't get the new bb. So if I have an image of 100x70 and I have a pixel at (19,39) and then I rotate the image with angle = 45, how ...
1
vote
0answers
31 views

There are 2 figures explaining transposed convolution. Which one is correct?

I have been struggling to understand transposed convolution. When I search for "transposed convolution", there are 2 figures explaining transposed convolution in which I think are not ...
0
votes
0answers
15 views

What are the different ways to feature engineer webpage data for input into a webpage classification model?

Looking for resources on the different ways that one can manipulate webpage data to input as features into a neural net. I'm aware of a service called diffbot that claims to use a CV based method to &...
0
votes
0answers
17 views

how to make the object detection detect only full object not part of it?

I have trained an object detection model to detect different kinds of cards and crop them and save them, the model detect the object very well and I got a good accuracy, now I want to add some post-...
0
votes
0answers
124 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
0answers
18 views

Kaggle API does not download the entire dataset

I am trying to download the statefarm distracted driver detection dataset using the API key on Colab: ...

1
2
3 4 5
10