Stack Overflow
Stack Overflow

Questions tagged [image-recognition]

Classification of a detected object into different known categories.

The classical problem in computer vision, image processing, and machine vision is that of determining whether or not the image data contains some specific object, feature, or activity. There are different varieties of this , such as object detection, Identification (like face recognition ), Content-based image retrieval ( like similar images option in google image search) etc.

1351 questions
-1
votes
1 answer

Creating a .csv with images

Say I am given a training folder. The training folder contains separate folders that has images (CNV, DME, DRUSEN, and NORMAL are all types of detections): I want to go through every image in each folder and assign every image an Unique ID and a…
Trush P
  • 43
  • 1
  • 10
-1
votes
1 answer

Detect Eyes Using Matlab

I have tryed hough circle algo but it give not acceptable out put of detecting eyes . Can we find way to get the eyes detect in image I having face front ...
Puneet Arora
  • 1
  • 1
  • 1
-1
votes
1 answer

How to achieve Image recognition using phone camera

I'm trying to build an app to make image recognition using the phone camera... I saw a lot of videos where using the camara the app identify where is the person or which feelings they have or things like that in real time. I need to do a built an…
Faabass
  • 1,394
  • 8
  • 29
  • 58
-1
votes
1 answer

javascript image recognition script

I was wondering if there is a script or function in javascript which can recognize image patterns. I want to use this for automation. It is comparable to http://sikuli.org/ but I want this to run as a Firefox extension. I think…
user366121
  • 3,203
  • 9
  • 48
  • 69
-1
votes
1 answer

What should I do to solve this cv2 error?

here is my code in python : import numpy as np import cv2 face_cascade = cv2.CascadeClassifier('haarcascade_frontalface_default.xml') eye_cascade = cv2.CascadeClassifier('haarcascade_eye.xml') img = cv2.imread('human.png') gray = cv2.cvtColor(img,…
Antoine
  • 23
  • 1
  • 5
-1
votes
1 answer

High accuracy with testing data in neural network but bad outputs when trying to recognise an image

so my neural network (784 input nodes, 64 hidden nodes, 10 output nodes) has an accuracy of 95% when it recognises 28*28 images of hand written digits, but when i actually write a digit myself, it guesses right in about 1/5 of the cases. Does anyone…
geomikeo
  • 19
  • 4
-1
votes
2 answers

Is it normal that transfer learning (VGG16) performs worse on CIFAR-10?

Note: I am not sure this is the right website to ask these kind of questions. Please tell me where I should ask them before downvoting this "because this isn't the right place to ask". Thanks! I am currently experimenting with deep learning using…
wohe1
  • 755
  • 7
  • 26
-1
votes
3 answers

Transfer Learning - Val_loss strange behaviour

I am trying to use transfer-learning on MobileNetV2 from keras.application in phyton. My images belongs to 4 classes with an amount of 8000, 7000, 8000 and 8000 images in the first, second, third and last class. My images are gray-scaled and resized…
mathemagier
  • 11
  • 3
-1
votes
2 answers

How to create a MLImageClassifier in Xcode 10

I'm trying to build a Machine Learning - Image Recognition using Create ML in Xcode 10.1 Playground but I'm having some problems to put my data in the model. I have a folder with images numbered from 1 to 1336 and a .csv file with 2 columns (the…
Leonardo
  • 1
  • 3
-1
votes
1 answer

Is there anyway to send data through RPi and the Mac OS X wirelessly?

I am trying to build a robot that captures images from the RPi camera that is in installed, and try to sent it over to my Mac to do the image recognition and sent the result back. The robot was controlled by the Raspberry Pi 3 Model B. I have tried…
Eshaan Barkataki
  • 35
  • 1
  • 7
-1
votes
1 answer

VB.Net Image Recognition

Basically, I want a 'If image.contains(image2)...' sort of thing. For example if image 1: is found to contain in image 2: Then it will return it's x/y co-ordinate, is this possible in VB.Net?
Tom Hall
  • 19
  • 3
  • 8
-1
votes
2 answers

Saving an image for image recognition via REST on raspberryPi

I am doing a project for image recognition. I want to send an image or a video from an android app to the raspberryPi, that is my server (I use flask), and make the recognition on the server and then send back the result to android. I want to do…
MariannaP
  • 1
  • 1
-1
votes
1 answer

How to verify the shape drawn by user in Unity

I am creating an app in Unity, where the user will be presented by alphabets images and user will be able to trace the character in the image using his finger. I know how to do the tracing part in Unity but what I don't know is how to verify…
Vivek Mishra
  • 5,669
  • 9
  • 46
  • 84
-1
votes
1 answer

Is it okay to have a higher dev set accuracy than train set accuracy?

I was training a Densnet121 architecture on about 102 flower classes. The data was about 10-20 images in training, valid and testing set for each of the 102 classes. I did add some dropout about 0.5, and I noticed that training accuracy is about 70%…
Aakash Behl
  • 1
  • 2
-1
votes
1 answer

Image classification task between left, central and right part of a fixed object

I am trying to train a learning model to recognize which part (left/central/right) of a known object is represented in an image, assuming that the model's input can be one of the following: an image of the left part of the object (whole left part or…
Carlo De Simone
  • 1
1 2 3
…
90 91