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
0
votes
0answers
5 views

Small object detection preprocessing

I am currently working on an object detection project in which I amtrying to detect very small objects 50x50 object in a 2k image. EfficientDet produced a very low result if I just put the raw ...
0
votes
1answer
41 views

the size of training data set in the context of computer vision

Generally speaking, for training a machine learning model, the size of training data set should be bigger than the number of predictors. For a neural network, or even a deep learning model, the number ...
0
votes
0answers
12 views

How to annotate the object more efficiently

I want to perform object detection and object counting on the given below image using neural networks. My first step will be to annotate and label each object present in the training set of images. In ...
0
votes
0answers
11 views

Value of AP and AR are -1.000 in evaluation

As I understand, the AP amd AR calculation are as of follow: ...
1
vote
2answers
105 views

What is Image Annotation?

Why do we need to use Labelimg tool for object detection? After labeling the bunch of training images using labelimg tool which will give CSV file How that CSV file works with TensorFlow object ...
0
votes
0answers
18 views

Testing trained model on the image from the test set

I trained my EfficientNet (CNN) and got accuracy=0.73. The question is how to check it on one concrete image from the testing set? How to write a code in python for it? I described the testing set ...
0
votes
1answer
18 views

What is better opensource alternative for identifying small face other than yolo?

I was trying to identify small face meaning that I want to know who that face belong to according to training dataset. I have previously use yolov4 to detect small object before and I know the ...
0
votes
0answers
5 views

Does PIFUHD 3D reconstruction model preserve sizes?

This is little conceptual question. I am working on 3D reconstruction using deep learning from 2D images. I came across PIFUHD model which is developed by Facebook and I have a question regarding that ...
0
votes
1answer
217 views

Class token in ViT and BERT

I'm trying to understand the architecture of the ViT Paper, and noticed they use a CLASS token like in BERT. To the best of my understanding this token is used to gather knowledge of the entire class, ...
1
vote
1answer
307 views

How to prepare masks for multiclass semantic segmentation?

It's very straightforward for binary semantic segmentation: black color (0s) is responsible for background, whereas white color (1s) is responsible for objects of interest. But what about multiclass ...
0
votes
0answers
3 views

Train only Region Proposal Network in faster RCNN architecture

I am looking for a way to used my pretrained EfficientNetv2 model and turn it into an object detection. Is there anyway, I can put my pretrained model as a backbone and only train the region proposal ...
0
votes
0answers
12 views

Vgg16 model validation accuracy is stuck

I am working on a CNN model for MRI brain images classification (Alzheimer disease), I use transfer learning method for image classification - vgg16 model trained on ImageNet (1000 classes). I’ve ...
0
votes
1answer
26 views

CNN can't predict images outside the dataset

I am using celeba dataset to train my CNN face landmark detection model. Here is my model ...
3
votes
1answer
44 views

Can reducing the number of classes in multi-label classification increase performance?

This is more of an open question with people which have experience in this. I'm working on a multi-class multi-label classification for chest x-rays. I would like to know how much can reducing the ...
1
vote
1answer
18 views

face landmark detection cnn loss not converging in tensorflow

I am trying to build face landmark detection model using simple regression.I used celeba dataset which has 5 points hence 10 output units.I used grayscale and normalized image as input. Here is my ...
0
votes
0answers
7 views

How can I use COCOAPI/PyCOCOTools to evaluate the performance of Tensorflow Lite models

I have used the Tensorflow Object Detection API to train models on a custom dataset. The tensorflow object detection API also allows evaluating the trained models on a test set and gives results in ...
4
votes
1answer
324 views

How can I detect partially obscured objects using Python?

I'm building a computer vision application using Python (OpenCV, keras-retinanet, tensorflow) which requires detecting an object and then counting how many objects are behind that front object. So, ...
0
votes
1answer
29 views

How to interpret fast-rcnn metrics?

I'm following this tutorial to fine tune Faster RCNN model, during training process a lot of statistics are produced however I don't know how to interpret them. what are major characteristics to look ...
0
votes
0answers
27 views

Correct way of computing dice score for image segmentation?

In binary image segmentation, for given a set of images, it's true mask and predicted mask. How do you compute dice score? Should I compute the dice score for each image separately and then find mean ...
1
vote
1answer
45 views

How to estimate real distance between two detected objects in an image?

You may think this is a duplicate, but my situation is different than previously asked questions. The only information I have is the width and height of the bounding boxes of detected people. The ...
0
votes
1answer
27 views

best similarity measure for images with different angles

I want to compare different images (where the images are of the same setup but the angles with which the images are taken are different). I want to obtain some sort of similarity score. I tried using ...
0
votes
0answers
18 views

How metric learning works for content based item retrieval

I was doing some computer vision experiments and recently I have started learning about metric learning and the image retrieval problem. I was experimenting with the inshop image retrieval dataset to ...
1
vote
1answer
47 views

White circles extraction from a little darker background

I'm trying to extract three white circles on the top left corner from the image below: I've tried to use: ...
0
votes
0answers
15 views

Labelling Images - Image Recognition

I'm new to image recognition and I've been tasked with implementing a YOLO classifier. Images I have relate to the installation of a product. So to train this custom dataset, I've been labelling the ...
0
votes
0answers
7 views

What is the difference between a bounding box and ROI (Region of Interest)

I was reading about the Fast RCNN for object detection. From what I understand, it uses pre-computed ROI's (using selective search) and uses these to predict the bounding box offsets and uses smooth ...
0
votes
1answer
306 views

How to calculate LFW accuracy of face recognition model?

In my research I have observed many of the face recognition algorithms propose their model accuracy interms of LFW dataset accuracy. I understood that LFW is a open source database and I did download ...
0
votes
1answer
28 views

How to model the probability of detecting an image, given it is seen multiple times

Are there any existing methods/models describing the probability of an object being detected by a computer vision algorithm given it is seen $n$ times at similar angles and orientations? I know that ...
0
votes
0answers
18 views

How to evaluate pix2pix?

As far as I know, to evaluate synthesized images it is proposed to use: human scoring, "Inception score", where in the second case the quality is rated based on a pre-trained Inception ...
0
votes
0answers
11 views

Faster RCNN is not able to recognize composed elements

I tried to fine tune Faster RCNN to realize object detection task with bounding boxes where I shall recognize face, eyes and mouth on image. However Faster RCNN seems to fail to recognize objects when ...
1
vote
1answer
32 views

Approach fpr extracting/cropping features images using deeplearning and no annotations

Let's say I want to have a bunch of images of hats from videos. How would I priniciple build something that would learn to recognize, and crop or bound box hats? I heard you need a dataset with ...
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: ...
1
vote
1answer
21 views

What is the upscaling factor in super resolution with deep learning? [closed]

I have been reading papers on single image super resolution (SISR) and I frequently encounter X3 upscaling factor, X4 upscaling factors. Example: SRGAN mentioning x4 upscaling factor It would be ...
2
votes
2answers
4k views

How to properly save and load an intermediate model in Keras?

I'm working with a model that involves 3 stages of 'nesting' of models in Keras. Conceptually the first is a transfer learning CNN model, for example MobileNetV2. (Model 1) This is then wrapped by a ...
1
vote
1answer
194 views

How to determine key frames in a video for video classification?

How to detect changes between when the changes between 2 frames of videos that are significant enough to be counted for video classification? Thinking of the problem as analogous to edge detection in ...
0
votes
0answers
33 views

How to convert RGB to One Hot encoding of Pixel in Pascal VOC Dataset?

I am trying to implement Semantic Segmentation on PASCAL VOC 2007 Dataset using Fully Convolutional Network. My Network outputs images of (Height, Width, Classes); but the training label masks are of ...
4
votes
1answer
2k views

Gradient flow through concatenation operation

I need help in understanding the gradient flow through a concatenation operation. I'm implementing a network (mostly a CNN) which has a concatenation operation (in pytorch). The network is defined ...
2
votes
1answer
145 views

Doing a fine tuning after a transfer learning

I read about fine tuning and transfer learning for CNNs and was wondering if we can do fine tuning after using transfer learning on the same CNN? If so, will this increase the performance of the model ...
4
votes
2answers
516 views

How to determine the number of the training images in Keras after data augmentaion?

I want to create a CNN model and I am using data augmentation. I want know the number of augmented images in Keras. How to determine the number of the training images in Keras after data augmentation?...
1
vote
2answers
146 views

Facial recognition on offline images

I want to do facial recognition on wide varieties of images captured at various ages of my family members. Below are some of the questions I have. If a person uses glasses of different types, do I ...
2
votes
1answer
52 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 ...
2
votes
2answers
468 views

Pre-processing on MRI images

I have MRI images of brain tumors collected from a hospital (not a benchmark dataset). And I am planning to use them to predict/classify tumour types using a typical machine learning approach: texture ...
1
vote
0answers
9 views

A good way to use facial landmark as model input

We are planning to use facial landmark information as input to the model. Since there are more than 60 points, it doesn't look good to use 60 channels as inputs after one-hot encoding. I found a few ...
0
votes
1answer
17 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 &...
6
votes
0answers
2k views

Python : Feature Matching + Homography to find Multiple Objects

I'm trying to use OpenCV via Python to find multiple objects in a train image and match it with the key points detected from a query image. For my case, I'm trying to detect the tennis courts in the ...
1
vote
0answers
18 views

How Does EAST detector implementation with VGG16 look? How many outputs does it have?

I was reading the Efficient and Accurate Scene Text Detector paper and saw the author reference VGG-16 as a possible stem "feature extractor" network. In the paper they say: In our ...
1
vote
1answer
58 views

Synchronizing Multiple Cameras in Autonomous Driving

Please forgive the naivity of this question, it's just due to lack of experience. It goes without saying that self-driving cars have up to 8 cameras and more that do various vision related tasks: ...
0
votes
1answer
156 views

Can somebody explain me the meaning of this sentence? (Color Similarity - Selective Search Algorithm)

This is a sentence from this article : Color similarity: Computing a 25-bin histogram for each channel of an image, concatenating them together, and obtaining a final descriptor that is 25×3=75-d. ...
2
votes
1answer
40 views

Can I train a CNN to detect the number of objects without localizing them first?

So I was trying to search but couldn't find any answers. I was wondering if it possible to train a model to detect the number of items of interest in a photo without having bounding boxes or dots to ...
0
votes
1answer
35 views

Comparing two images and showing the difference in a new image?

I would like to compare two web pages images using computer vision techniques. Show what are non-unique portions comparing both images. Which part image1 not exist in image2 vice versa.
0
votes
0answers
19 views

Predictions receiving in Unknown (8)[e,e,e,e,e,e,e,e] format from TensorflowJS Mobilenet

I have trained a mobilenet on diamond images to count diamonds in broswer. I then converted the SavedModel format to TFJS format. I have the following code in my JS file. ...

1
2 3 4 5
10