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.

224 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
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 ...
5
votes
2answers
607 views

Image recognition of selfie images

I developed an Android app that lets anyone upload pictures of encyclopedic things (bridges, museums, dishes, landscapes, paintings, etc) to Wikimedia Commons. Unfortunately, 5% of the users find it ...
4
votes
1answer
330 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, ...
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 ...
4
votes
2answers
539 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?...
3
votes
0answers
99 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 ...
3
votes
4answers
52 views

Pre-trained models

I am starting off with machine learning so could someone tell if there is some site where one can find the current best performing trained models for any specific problem like sentiment analysis or ...
3
votes
0answers
1k 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 ...
3
votes
1answer
132 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.
3
votes
0answers
44 views

Formula to calculate size of Capsule output similar to the formula for CNN?

Is there any formula to find the output dimensions of a capsule network similar to that of a Convolutional Neural Network? For Example: In CNN, we know that ...
3
votes
0answers
352 views

Where can I find a >1K dataset of annotated store receipt pictures/scans?

I’m looking for a large dataset of store receipt pictures or scans. The image quality is not of the highest priority. However, some annotations would be nice: vendor date of purchase total amount (...
3
votes
1answer
80 views

Classifying Car Data By Year

I have huge car photos. I want to predict car's "brand-model-body type and production year" First, I splitted data into train and validation, and I categorized them like this. Every category has ...
2
votes
0answers
25 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 ...
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 ...
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. ...
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 ...
2
votes
0answers
29 views

What is the difference between HLC (Histogram of local features) , CSS ( color self-similarity) ans MDST (Max DisSimilarity of Different Templates)

I'm new to computer vision and have been researching for Master thesis purposes in Detection algorithms and the techniques used in each. As I arrived to the point where alot of papers showed the ...
2
votes
0answers
9 views

Dataset suggestion: video dataset with accurate depth and pose info

Please suggest some datasets (can be synthetic, like rendered in blender or so) which have video frames (30fps preferred) with accurate ground truth depth maps and pose (rotation and translation for ...
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 ...
2
votes
2answers
568 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 ...
2
votes
0answers
44 views

Real-life applications/examples of transfer learning approaches

I recently read a nice, informative paper titled 'A Survey on Transfer Learning'. It mentions 3 settings of transfer learning - inductive, transductive, and unsupervised. At the same time, it states ...
2
votes
0answers
22 views

Information Extraction from image / text - approach?

I need assistance with a ML project I am currently trying to create. I receive a lot of invoices from a lot of different suppliers - all in their own unique layout. I need to extract 3 key elements ...
2
votes
0answers
252 views

Difference detection between two images

I am trying to compare two images and detect the difference between them whether in shape or color. -The change in shape: the number of parts has changed ( increased or decreased). -The change in ...
2
votes
0answers
19 views

orientation detection - images of govt. issued documents

Trying to figure out a macro approach to detecting orientation of documents that works across document types (maybe a pipe dream). We successfully used SIFT to detect orientation in documents where we ...
2
votes
2answers
39 views

shapes recognition for shapes formed by dotted points

In the image, below right corner there is circle shape and triangle shape made with set of co-ordninates.I have searched extensively in the net for algorithm or approach to classify shape correctly ....
2
votes
0answers
300 views

Curve of MAPs to evaluate training progress of Mask RCNN on synthetic data

Is MAP (Mean Average Precision) a good substitute for measuring training and validation accuracy at different stages of training a machine learning model for object detection? I am retraining a Mask ...
2
votes
0answers
25 views

Image reconstruction using low-light components

Let's say we have a regular photo and three low-light photos illuminated in different colors. Each pixel is a three-component vector $q=(R,G,B)$. Then $q_k^{A}$ is the $k$-th pixel of the regular ...
2
votes
3answers
139 views

Can the same CNN architecture be used for different data sets?

I have a CNN architecture that works well on 32x32x3 images. Can I use that same architecture for a data set made up of 28x28x1 images? (Both data sets have 10 classes). If this is possible, what ...
2
votes
0answers
305 views

How to calculate size and offset of YOLO grid in a fully convolutional network with zero padding?

Fully convolutional network with zero padding: I have a fully convolutional network which does not have any padding in convolutional layers. This implies that, after each convolution operation, the ...
2
votes
0answers
42 views

Is it possible to modify the layers of the models present in the Tensorflow Object Detection API

I would like to know if there is any way in which we can change the base layers of the models offered by the Tensorflow Object Detection API and if so, is it possible to change things like pooling/...
2
votes
1answer
47 views

Detecting unique icon on video in real time

For a project I am working on I'd like to be able to detect unique icons/barcodes in video footage. Suppose you have 10 people in the frame where each person is wearing a t-shirt with a similar but ...
2
votes
0answers
690 views

How to calculate Average Precision for Image Segmentation?

If I've understood things correctly, when calculating AP for Object Detection (e.g. VOC, COCO etc) the procedure is: collect up all the detected objects in your dataset sort the detections by their ...
2
votes
1answer
2k views

How to generate Anchor boxes for SSD?

I am currently trying to understand the method of generating anchor boxes for object detection. I am looking at a code where the author has done this task in a very flexible way. But I am having ...
2
votes
2answers
475 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 ...
2
votes
0answers
40 views

How can I get the original pixels that lead to the decision in CNN?

I work on medical images and I want to locate the most relevant regions of the image based on deep learning spatially CNN. So I feed my data into VGG16 architecture and get the features maps. Now I ...
2
votes
0answers
391 views

Training detector without bounding box data

From what I can see most object detection NNs (Fast(er) R-CNN, YOLO etc) are trained on data including bounding boxes indicating where in the picture the objects are localized. Is there any model ...
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 ...
2
votes
0answers
105 views

it is possible to use features maps of CNN to localised important areas in image?

I'm new in deep learning and CNN, I understand how convolutional and pooling layers work, I understand how and why feature maps are created. How I can localize from the feature maps important area in ...
2
votes
1answer
106 views

How to fetch text from pdf to further proceed with question answer based model from the same document?

To illustrate the above title. Suppose you have a pdf document, which is basically scanned from hardcopy, now there are set of fixed questions to answer from the document itself. For an example a ...
2
votes
0answers
170 views

Maximum number of classes YOLO net can recognize

I'm trying to make a mobile app on image recognition(Computer Vision Application) . Does anyone know whether modern day smartphones have enough processing power/memory to recognize, say about 1 ...
2
votes
0answers
282 views

Spatial Transformer Networks and Data Augmentation

We are all familiar with the famous Deep Mind paper STN. Upon implementation, such as here, did anyone still use input data augementation such as affine transformations? There are used to make CNN ...
2
votes
0answers
219 views

GTX 1080t ti rans out of memory

I have 60000 images divided into two classes. I have tried to build transfer learning with pretrained ResNet50 but my new GTX 1080 ti returns -1 after couples of epochs. My guess is that it runs out ...
2
votes
0answers
24 views

Given a query image Q and two other images X and Y, how to determine which one is most similar to Q?

Given a query image Q and two other images X and Y (you can assume they have more or less the same resolutions if that simplifies the problem), which algorithm would perform extremely well at ...
2
votes
0answers
93 views

How to combine heterogeneous image features extracted with different algorithms for similar image retrieval?

Say I have access to several pre-trained CNNs (e.g. AlexNet, VGG, GoogleLeNet, ResNet, DenseNet, etc.) which I can use to extract features from an image by saving the activations of some hidden layer ...
2
votes
0answers
31 views

which algorithm will be good for detecting and recognition of faces from variety of angles

i am building a face recognition app for my class attendance system , i collect training data from social website like facebook, instagram and other, as you can see the images i got from there is not ...
2
votes
1answer
534 views

Two parallel models for semantic segmentation in Keras

I want to build two parallel models for image semantic segmentation in Keras. ...
2
votes
0answers
77 views

Piecing together an equivalent of Google's Data Science / Engineering AIY Computer Viz kit

Google has a DS / AI / ML / engineering themed DIY kit for voice recognition and computer vision. The big manufacturers (Micro Center, Mouser, Seeed, etc) who partnered with Google are sold out and ...
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 ...
2
votes
0answers
192 views

Recognition of Geometric shapes for ridges

I want to recognize these geometric shapes which are related to each other. For instance, looking at the image of the roof below, just by knowing the existence of the ridges in RED, I know that the ...
2
votes
0answers
225 views

How to improve the neural art algorithm?

I have been playing around the algorithm with tensorflow in this paper. I tried to convert a photo to a Chinese ink and wash painring, but I got some strange patterns in the output picture(those in ...

1
2 3 4 5