People who code: we want your input. Take the Survey

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
6
votes
2answers
583 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 ...
0
votes
1answer
910 views

Reinforcement Deep Learning for object detection [closed]

After reading the state of the Art of object detection using the CNN's(R-CNN,Faster R-CNN,YOLO,YOLOv2,SSD) I was wondering if there is an efficient method that use deep learning with reinforcement ...
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 ...
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 ...
3
votes
1answer
991 views

How to run PCA and KNN on big-data

I work with python and images of watches (examples: watch_1, watch_2, watch_3). My aim is to take a photo of a random watch and then find the most similar watches to it in my database. Obviously, one ...
1
vote
2answers
191 views

which is the most effective(accurate) face detection method in python

i try haar_cascade for face detection and LBPH for face recognition , but the result wasn't good enough, please suggest good ways to detect and recognize faces. my aim is to create an app which take ...
2
votes
1answer
536 views

Two parallel models for semantic segmentation in Keras

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

Training an AI to play Starcraft 2 with superhuman level of performance?

I'm interested in working on challenging AI problems, and after reading this article (https://deepmind.com/blog/deepmind-and-blizzard-open-starcraft-ii-ai-research-environment/) by DeepMind and ...
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 ...
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 ...
1
vote
1answer
241 views

Multi-image superresolution using CNNs [closed]

I'm trying to write a program that can take multiple low-resolution images as inputs and output a high-resolution image. My understanding is that for single-image superresolution, Convolutional ...
3
votes
1answer
35 views

Is the external memory of Differtiable Neural Computer limited?

Is there a CONSTANT limit in DNC external memory usage? Like a human brain, 7 chunks of information? Or is it some sort of a hyperparameter? How much data it can associate using that Short-Term ...
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 ...
4
votes
1answer
2k views

What does 'energy' in image processing mean?

I have been going through this paper: Seam Carving for Content-Aware Image Resizing which talks about resizing images by seam carving depending on the image energy or the energy function. Some ...
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 ...
9
votes
1answer
8k 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 (...
3
votes
2answers
124 views

Classification of jumbled images

I want to be able to create a model that would be able to classify an image that has been split into 9 parts and jumbled around. I did see a paper on it but it is quite old (7-8 years old). Could ...
2
votes
1answer
146 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 ...
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 ...
1
vote
1answer
89 views

Shape extracting on 2D geometric data

Given a set of lines, is there a way to train to extract geometric shapes. For example, the picture on left has some blue lines (with red endpoints). How can I train to extract shapes like on the ...
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 ...
0
votes
2answers
58 views

What it Would be easier Building a Deep Net From Scratch or Using an existing Architecture? [closed]

In Practice with CNN what would be easier: Building a CNN from scratch or using a an existing architecture with some updates?
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 ...
1
vote
0answers
52 views

Automatically extract original dataset from a line plot image

Given a line plot image (bitmap, png, etc) form, I'm looking to extract the set of original datapoints without any user input, as shown in the below image: The outcome should be something like below:...
32
votes
2answers
43k 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
1answer
27 views

Training machine to identify hot spots

I have a set of 1000 images of the dorsal side of the hand. I need to identify the different joints in the fingers and measure the distance between them. I have already cropped the images to same ...
0
votes
1answer
3k views

Multiple Object recognition in image using deep Learning [closed]

I am working on recognizing object classes in images using neuronal nets so I could make classifiers for cats, dogs... using Imagenet and some Conv nets famous architectures but my problems is if I ...
1
vote
1answer
565 views

Match an image from a set of images : Combine traditional Computer vision + Deep Learning/CNN

In the application I am developing, I have about 5000 product label images.(One label per product). One functionality of my application is that user can take a picture using his camera and get a ...
1
vote
1answer
67 views

Is there something like class-based object detection? Or class-based selective search?

I've been reading a lot about computer vision lately, and while there is a huge amount of info about object classification, and a lot less on object detection, I have not found anything on class-based ...
1
vote
1answer
755 views

Multi target regression when some targets have correct NA labels

I'm working on a Keras neural net that does key point prediction of body parts (left foot, left knee, left hip, etc.). For each image (X), the target (Y) is a list of coordinates for the keypoints (...
21
votes
3answers
21k 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 ...
2
votes
2answers
2k views

Keras loading images in incorrect format

So I was working with the the vgg16 model for dogs vs cats classification and I noticed that keras is not loading images in correct color format. The code is as follows: ...
7
votes
1answer
19k 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?
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 ...
5
votes
1answer
339 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 ...
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 ...
2
votes
2answers
2k views

Why do we need for Shortcut Connections to build Residual Networks?

Why do we need for Shortcut Connections to build Residual Networks, and how it help to train neural networks for classification and detection?
0
votes
1answer
1k views

Image Feature Vectors

I have downloaded a dataset from Amazon. http://jmcauley.ucsd.edu/data/amazon/ Dataset involves feature vectors of images. There are around 1.5 M feature vectors. Dataset consists of 10 characters (...
-1
votes
1answer
5k views

Animal Detection dataset

Update 1: I know that I can seperate animal,bird object annotations/images from imagenet. In fact I already filtered annotations/images that are my interested and downloaded them by URL. I searched ...
0
votes
4answers
64k views

Import Error: cannot import name 'cv2'

I want to begin exploring OpenCV in Python but I'm stuck at importing the package cv2. I have installed the package through ...
3
votes
2answers
2k views

Computer vision: Identifying different items in screenshot

Lets say I have a screenshot like this: I want to be able to detect/localize each item on the floor, however, there 1) can be any number of items in the image and 2) each item is different I have a ...
0
votes
1answer
153 views

Connection between the first pooling layer and the second convolutional layer

This is a follow-up question regarding this question. I managed to verify in python that the output of the first pooling layer will be a $14 \times 14\times 32$ ...
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 ...
1
vote
0answers
148 views

Mathematical physics applications in present-day image processing

During the past few years several important areas of image processing and image classification or generation became dominated by convolutional neural networks. I'm interested if there are any methods ...
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 (...
4
votes
1answer
1k views

Has anyone tried to use the hierarchy of ImageNet?

The classes of ImagNet have a hierarchy. Did anybody try to build a hierarchy of classifiers to use this fact? Searching for "multistage classification" leads to different results.
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 $C$ ...
0
votes
1answer
329 views

Why is video classification still not that accurate?

I was wondering, with the advent of deep learning, many tasks related to images have been solved to near human accuracy such as classification, object detection etc., however in videos, traditional ...
21
votes
3answers
30k 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 $B$ ...
0
votes
1answer
689 views

Modeling pixel intensity with the normal distribution

I was reading a machine learning book with applications in computer vision. In it, it mentioned that "in vision, it is common to ignore the fact that the intensity of a pixel is quantized and model it ...

1
6 7 8
9
10