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
4 votes
3 answers
921 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?...
0 votes
0 answers
12 views

Best cloud provider for Computer Vision in 2024. (Market relevant)

So I am currently unemployed, I am an ML engineer, Computer Vision focused. I have experience with many cloud providers but no certifications. Generally job postings will ask for experience/...
0 votes
0 answers
7 views

Target bounding box coordinates for classic YOLOv2

Let's say I build training data for classic YOLOv2 from paper: https://arxiv.org/pdf/1612.08242.pdf let me know if I understand output format correctly. Example Bounding box from picture: bounding ...
2 votes
2 answers
1k views

How to remove background (watermark) logo from image

I have been scratching my head for a while. What I have is a scanned PDF document with text and water marked logo at the back as in the below image. I want to do OCR over this, which becomes very ...
0 votes
1 answer
97 views

Why a CNN with decreasing filter layers sizes could perform better than a "regular one" with increasing sizes?

I did dozens (or probably hundreds) of tests and the best result with less total parameters(4 times or less) was a decreasing filter layers size architecture. This is a CNN for multiclass image ...
41 votes
2 answers
52k views

How to calculate mAP for detection task for the PASCAL VOC Challenge?

How to calculate the mAP (mean Average Precision) for the detection task for the Pascal VOC leaderboards? There said - at page 11: Average Precision (AP). For the VOC2007 challenge, the interpolated ...
1 vote
1 answer
41 views

Is vision transformer (ViT) always better than CNN?

The paper - AN IMAGE IS WORTH 16X16 WORDS: TRANSFORMERS FOR IMAGE RECOGNITION AT SCALE proposed vision transformer and outperformed CNN-based models in many cases. When it comes to sequential data, we ...
3 votes
1 answer
318 views

Why does joint embedding of word and images work?

I often see some papers where the authors do point-wise multiplication of word and image embedding (e.g the image below). Why does this implementation works? I do not understand.
0 votes
1 answer
205 views

How many bounding boxes does the YOLOv6 model predict in total before thresholding?

I understand that the YOLOv5 model predicts 25200 bounding boxes between all 3 levels of output. How many does the YOLOv6 model predict, if the input resolution is 640x640?
1 vote
1 answer
4k views

Training Inception V3 based model using Keras with Tensorflow Backend

I am currently training a few custom models that require about 12Gb GPU memory at the most. My setup has about 96Gb of GPU memory and python/Jupyter still manages to hog up all the gpu memory to the ...
3 votes
2 answers
2k views

Cross validation for convolutional neural network

I am using Keras to create a CNN model, and I would to use K-fold cross-validation to train the dataset. The dataset contains images and I am using ...
1 vote
1 answer
439 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 ...
0 votes
0 answers
14 views

Should I remove the watermarks of my images before training Yolov8?

I would like to train a Yolov8 network in an animal detection task using camera trap images. Some camera trap images have information added to them such as date, time, day of the week, camera brand, ...
4 votes
1 answer
82 views

How to collect a computer vision dataset?

Context: my team is researching some plant-growth patterns using object detection models. We have collected a small set of images (a few thousand) and ran some simple experiments. The results were ...
0 votes
1 answer
222 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
1 answer
154 views

Cable angle measurement (rotation)

I need to detect the rotation of a cable (degree) in the x-axis with high precision [0.2 (or more) degree detection] from its original state. Detailed description: I have a cable that is set in its ...
0 votes
0 answers
12 views

Using two different dataset file formats to train model

I am looking to train a model on computer vision for imsge prediction but I have an images dataset and a .csv dataset. Note: both datasets have 6 classes A, B, C, D, E, F, only different is the file ...
0 votes
1 answer
175 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 &...
0 votes
0 answers
7 views

How to calibrate IMU for large scale deployments possibly using deep neural network

We were testing our visual SLAM algorithm on robots. We were getting poor performance. Then we calculated wite noise and random walk parameters (using kalibr) for the IMU and used it in our algorithm ...
3 votes
1 answer
248 views

VQ-GAN understanding

I tried to understand how VQ-GAN works, but unfortunately I have not understood it. I tried to read some articles about it and watch a video. I believe a good and simple article will help me. You ...
0 votes
1 answer
25 views

Object localization and text extraction using VGG

I'm new to Computer Vision and training a TensorFlow neural network using VGG16. The problem is quite simple: I'm training in a custom dataset to detect and localize numbers in a 100x100 image. The ...
0 votes
0 answers
9 views

Suggestions for a computer vision teaching module in R

I'm teaching an undergrad seminar in machine learning. It's quite basic: kNN, tree-based models, neural nets, etc. For the last module I ask the students what they'd like to cover and they voted for a ...
1 vote
0 answers
229 views

Meta's SAM model: can extract semantic embedding vector?

I'm interested in finding an embedding vector for each segment found by the Facebook/Meta Segment Anything model (for classification and tracking of segments). Can ...
0 votes
1 answer
128 views

About the Evaluation method of the Market 1501 ReID dataset

The market 1501 dataset has train, query and gallery folders, each containing multiple views of people from multiple cameras. I would like to understand how to evaluate a model (trained with triplet ...
0 votes
0 answers
50 views

Need help in Image Similarity search engine

I need to build a Jewellery Image Similarity engine. As in if the user shows an image of a Golden earring with blue stones, the similar jewellery images should be fetched from our DB. I have a dataset ...
0 votes
0 answers
14 views

How to treat "ignore" boxes during object detector evaluation?

I want to evaluate the performance of multiple object detectors for comparison, each of them has been trained on this data. This dataset has images labeled, where each image can have multiple labels. ...
0 votes
1 answer
112 views

Convert from gray to BGR

I want to convert my grey mnist to color. I have came up with the following code, but the output is still gray. ...
1 vote
1 answer
270 views

Bounding box regression without a classification task

I am using PyTorch to create a model that detects certain objects in an image. I framed my problem as a regression on bounding boxes, without any classification task whatsoever. The reasoning behind ...
1 vote
1 answer
108 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
1 answer
66 views

Training Loss for Classification Model Isn't Decreasing

I'm currently building a video classification model for engagement detection but I'm having some trouble training it. The model takes in two tensors as inputs: a 10x48x48x1 tensor which holds a stack ...
1 vote
1 answer
284 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 ...
3 votes
1 answer
467 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 ...
1 vote
1 answer
75 views

Drawing transparent bounding boxes with Torchvision

I am using Torchvision in a Python script to draw bounding boxes and then crop images based on the bounding boxes drawn. The script works well, except that the bounding boxes obscure the subjects in ...
1 vote
1 answer
500 views

Is it possible to modify YOLOv8 to use it as a feature extractor for other tasks?

I'm reading through the documentation of YOLOv8 here, but I fail to see an easy way to do what I suggest in the title. What I want to do is to load a pretrained YOLOv8 model, create a bigger model ...
1 vote
1 answer
120 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
0 answers
6 views

Estimating the Cost of Creating an Image Dataset like GQA and Relevant Sources

I am currently working on a project that requires an extensive image dataset, similar to the GQA dataset. I am in the early stages of planning and would like to get an estimate of the cost involved in ...
1 vote
2 answers
452 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 ...
1 vote
1 answer
1k 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
1 answer
690 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 ...
2 votes
1 answer
577 views

What is the difference between proposal-based approach and proposal-free approach?

From here it says that Techniques to solve instance segmentation can be roughly grouped into two categories: proposal-based methods and proposal-free methods. In proposal-based methods, a set of ...
0 votes
1 answer
353 views

What is Typical Variation Normalization?

I was reading this paper and came across a term "Typical Variation Normalization". What does that mean intuitively and formally? Any resources I can refer to know more about it?
0 votes
1 answer
225 views

OCR with grouped text based on solid rectangles

I can read text from an image using OCR. However, it works line by line. I want to now group text based on solid lines surrounding the text. For example, consider I have below rectangle banners. I can ...
0 votes
1 answer
1k 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
1 answer
838 views

What is `Multi-scale` in Multiscale Convolutional Network?

I was reading an article on Deep Learning and came across this term called Multi-scale Neural Network. I fully understand the concepts of convolutional neural network but it is a bit difficult to ...
1 vote
2 answers
155 views

Class Imbalance in Dataset of Images

When dealing with an imbalanced dataset, I have been taught to oversample on only the train samples and not the entire dataset to avoid overfitting, however this was for structured text based data in ...
0 votes
0 answers
28 views

How can I identify coverage types in NFL games using Computer vision

I am currently working on a project that classifies coverage types from sports highlights using advanced computer vision techniques. Next Gen Stats effectively utilizes tracking data to identify ...
0 votes
0 answers
11 views

Using AWS Sagemaker (Ground Truth) for Labeling Jobs + Rekognition. How best to approach my project?

I'm new to ML so bear with me. I want to create an object detection model that can detect anything from flags (e.g. Israel flag) to symbols (e.g. yin-yang sign) to a giving setting (e.g. war). I am ...
0 votes
1 answer
476 views

Detection of a specific shape in an image

I want to create an algorithm in order to detect the following shape (in the blue region) in videos or images: I have no dataset from the corresponding object so I thought that if I define it ...
1 vote
2 answers
345 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 ...
1 vote
1 answer
170 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 ...

1
2 3 4 5
13