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
31
votes
2answers
42k 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 ...
21
votes
3answers
28k views

What does the notation mAP@[.5:.95] mean?

For detection, a common way to determine if one object proposal was right is Intersection over Union (IoU, IU). This takes the set $A$ of proposed object pixels and the set of true object pixels $B$ ...
20
votes
4answers
28k views

What is the difference between Inception v2 and Inception v3?

The paper Going deeper with convolutions describes GoogleNet which contains the original inception modules: The change to inception v2 was that they replaced the 5x5 convolutions by two successive ...
20
votes
3answers
20k views

Why convolutions always use odd-numbers as filter_size

If we have a look to 90-99% of the papers published using a CNN (ConvNet). The vast majority of them use filter size of odd numbers:{1, 3, 5, 7} for the most used. This situation can lead to some ...
18
votes
1answer
11k views

What is the difference between semantic segmentation, object detection and instance segmentation?

I'm fairly new at computer vision and I've read an explanation at a medium post, however it still isn't clear for me how they truly differ.
13
votes
3answers
15k views

What is the difference between Dilated Convolution and Deconvolution?

These two convolution operations are very common in deep learning right now. I read about dilated convolutional layer in this paper : WAVENET: A GENERATIVE MODEL FOR RAW AUDIO and De-convolution is ...
12
votes
5answers
6k views

Unsupervised image segmentation

I am trying to implement an algorithm where given an image with several objects on a plane table, desired is the output of segmentation masks for each object. Unlike in CNN's, the objective here is to ...
11
votes
1answer
14k views

Optimizer for Convolutional neural network

What is the best optimizer for Convolutional neural network (CNN)? Can I use RMSProp for CNN or only for RNN?
11
votes
1answer
4k views

What is difference between Fully Connected layer and Bilinear layer in CNN?

What is the difference between Fully Connected layers and Bilinear layers in deep learning?
10
votes
2answers
1k views

How can I detect if an image was photoshopped?

I would like to check JPG files if they were manipulated to change the content. What I consider NOT photoshopped: Cropping Rotating (Scaling) Image resolution Automatic changes smartphones might ...
9
votes
1answer
16k views

number of parameters for convolution layers

In this highly cited paper, authors give the following discussion on the number of weight parameters. I am not very clear why it has $49C^2$ parameters. I think it should be $49C$ since each of $C$ ...
9
votes
1answer
1k views

How can you build a model that extracts data out from receipts?

I'm trying to build a model that is capable of identifying information on receipts and invoices. I have used google cloud vision api for text extraction from the receipt but the problem is it just ...
9
votes
1answer
7k views

Data preprocessing: Should we normalise images pixel-wise?

Let me present you with a toy example and a reasoning on image normalisation I had: Suppose we have a CNN architecture to classify NxN grayscale images in two categories. Pixel values range from 0 (...
9
votes
1answer
392 views

Train a GAN on “before and after” images of dental surgeries [closed]

I want a GAN to train on "before and after" images of dental surgeries; so that it can generate "after" pictures for fresh patients. Input images are like these: https://img.webmd.com/dtmcms/live/...
9
votes
2answers
192 views

Are there studies which examine dropout vs other regularizations?

Are there any papers published which show differences of the regularization methods for neural networks, preferably on different domains (or at least different datasets)? I am asking because I ...
8
votes
1answer
1k views

Using Neural Networks to extract multiple parameters from images

I want to extract parameters from an image using a neural network. Example: Given an image of a brick wall the NN should extract the width and height of the bricks, the color and the roughness. I ...
8
votes
1answer
7k views

Recognition human in images through HOG descriptor and SVM classifier performs poorly

I'm using a HOG descriptor, coupled with a SVM classifier, to recognise humans in pictures. I'm using the Python wrappers for OpenCV. I've used the excellent tutorial at pymagesearch, which explains ...
8
votes
4answers
4k views

Faster-RCNN how anchor work with slider in RPN layer?

I am trying to understand the whole Faster-RCNN, From https://www.quora.com/How-does-the-region-proposal-network-RPN-in-Faster-R-CNN-work Then a sliding window is run spatially on these feature ...
7
votes
2answers
9k views

How to deal with large training data?

Currently, I use image files and transform them into a *.npy file(saved as a numpy array) as training data. At present this training data set is nearly 3GB. Now I have more image files, so the ...
7
votes
1answer
7k views

How to implement global contrast normalization in python?

I am trying to implement global contrast normalization in python from Yoshua Bengio's Deep Learning book (section 12.2.1.1 pg. 442). From the book, to get a normalized image using global contrast ...
7
votes
1answer
18k views

What is the meaning of hand crafted features in computer vision problems?

Are these the features which are manually labelled by humans? or Is there any technique for obtaining these features. Is this related to learned features?
7
votes
4answers
7k views

Exploratory Data Analysis with Image Datset

In Machine Learning Kernels on Kaggle I often see EDAs with structured data. So, I was wondering, if there are any recommended/standard procedures for EDA with image datasets. What kind of statistical ...
7
votes
2answers
11k views

How can I detect blocks of text from scanned document images

ORIGINAL IMAGE: GOAL: I want to separate texts into individual paragraphs by placing bounding boxes over them (as shown above). I tried it do this via traditional computer vision approach using ...
7
votes
2answers
145 views

Neural Network Architecture for Identifying Image Copies

I have a large image collection and wish to identify the images within that collection that appear to copy other images from the collection. To give you a sense of the kinds of image pairs that I ...
6
votes
4answers
2k views

Why choose TensorFlow?

I have noticed that most of the deep learning developers use TensorFlow. So why choose TensorFlow? What is the advantage of TensorFlow over Theano and CNTK?
6
votes
1answer
2k views

Convnet training error does not decrease

I'm training a convoluted neural net to drive a toy car, and no matter what I do the training accuracy does not increase beyond 30-35%, which is where it starts when the convnet is randomly ...
6
votes
1answer
45 views

Unable to understand the meaning of following lines of the research paper for image segmentation

I am implementing a paper on image segmentation. It is based on the slight modification of the u-net architecture. The paper is based on encoder and decoder steps Following are the lines of the paper ...
6
votes
1answer
8k views

How to make two parallel convolutional neural networks in Keras?

I created two convolutional neural networks (CNN), and I want to make these networks work in parallel. Each network takes different type of images and they join in the last fully connected layer. ...
6
votes
2answers
8k views

What is the different between Fine-tuning and Transfer-learning?

Usually the neural network training has at least 2 steps: first trained on a large set of some standard data (ImageNet, ...) and then the resulting weights are trained on a small set of my data (in ...
6
votes
2answers
574 views

Image segmentation - handcrafted features vs DNN?

Currently working on a project that requires multi-class image segmentation to identify distinct anomaly types in various sheet metals. Have had moderate success with various NN segmentation ...
6
votes
1answer
1k views

Implementing spatio-temporal convolutions in pytorch

I am trying to implement a layer to perform the (2+1)D convolutions described in this paper: https://arxiv.org/pdf/1711.11248.pdf The basic idea is as follows: Let's say I have a 3D convolutional ...
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
1answer
1k views

Does image's background matter for detector training (CNN)?

Does an image's background matter for detector/localisation in the training part (using CNN)? For example, if I want to make a face detector, which one is better as training dataset? Faces cropped ...
5
votes
1answer
5k views

What is fractionally-strided convolution layer?

In paper Generating High-Quality Crowd Density Maps using Contextual Pyramid CNNs, in Section 3.4, it said Since, the aim of this work is to estimate high-resolution and high-quality density maps,...
5
votes
4answers
906 views

Classification problem with many images per instance

I am working in the following kind of classification problem: I have to classify every instance as class A or class B using many images of the instance. That is, every training example has not one ...
5
votes
1answer
3k views

What is the depth of an image in Convolutional Neural Network?

I am learning cs231n Convolutional Neural Networks for Visual Recognition. The lecture notes introduce the concepts of width, height, depth. For example, In CIFAR-10, images are only of size ...
5
votes
2answers
1k views

how to apply similarity algorithm(or comparision) of over one million vectors with other one million vectors?

How can I apply similarity algorithm (or comparison) of over one million vectors with another one million vectors? I am following this pyimage search tutorial but don't know how to scale up the ...
5
votes
1answer
317 views

Data augmentation parameters

When I use data augmentation to increase the train dataset, should I use all augmentation techniques (parameters in keras)? Which data augmentation parameters should use with ...
5
votes
1answer
732 views

Spatial Transformer Networks vs Deformable Convolutions

As I understand STN as described by the the deepmind paper https://arxiv.org/abs/1506.02025 allow a neural network to learn how to perform spatial transformations on the input image in order to ...
5
votes
1answer
335 views

What is the fully-convolutional model?

What is the fully-convolutional model? Is fully-convolutional model a model that has only convolutional layers (with Batch-norm and Activation) and has not any: max-pool, fully-connected, and other ...
5
votes
2answers
439 views

How to predict on part of image after training on other part of image?

I have images of identity cards (manually taken so not of same size) and I need to extract the text in it. I used tesseract to predict bounding boxes for each letter and am successful to some extent ...
5
votes
2answers
2k views

Overfitting in Siamese Network

I am trying to train a Siamese network for an application very similar to this and this. From what I have read about training Siamese networks dissimilar pairs of images outnumber the similar pairs ...
5
votes
2answers
599 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
4answers
6k views

Is There any RNN method used for Object detection

after reading the state of the art about object detection using CNN (R-CNN Faster R-CNN ,YOLO, SSD...) I was wondering if there is a method that use RNN's or that combine the use of CNN's and RNN's ...
4
votes
4answers
3k views

Classification of very similar images

I have two groups of images, each one with 1000 samples. The speckle pattern, in this context, is the same as a random pattern or "white noise" image. So these images are fundamentally different. In ...
4
votes
2answers
292 views

Skin Detection Classifier

I have a small data set containing around 80 images for people, and the corresponding ground truth for skin regions. I want to train a classifier to be able to detect a skin, and use it later on my ...
4
votes
1answer
11k views

mAP scores on tensorboard (Tensorflow Object Detection API) are all 0 even though the loss value is low

I trained a faster-rcnn model on the tensorflow object detection API on a custom dataset. I found that the loss is ~2 after 3.5k steps. However, when I ran eval.py, the mAP scores are all almost 0 as ...
4
votes
2answers
6k views

Overfitting after first epoch

I am using convolutional neural networks (via Keras) as my model for facial expression recognition (55 subjects). My data set is quite hard and around 450k with 7 classes. I have balanced my training ...
4
votes
2answers
4k views

A deep learning approach that can calculate distance to obstacles

After reading about the most famous object detection CNN based methods: YOLO, YOLO 9000, r-cnn, faster r-cnn, etc., I was wondering if there is an architecture that can calculate the distance to the ...
4
votes
1answer
5k views

Creating a Object Detection model from scratch using Keras

I have a dataset containing 330 images which contain guns. Along with the images, I have a text file associated with each image file which contains, The number of objects ( guns ) in the image. ...

1
2 3 4 5
10