Stack Overflow
Stack Overflow

Questions tagged [object-recognition]

The computer vision task of finding and identifying objects in an image or video sequence

The computer vision task of finding and identifying objects in an image or video sequence is often conducted consistent with one of two approaches:

  • Appearance-based methods

    • Use example images (called templates or exemplars) of the objects to perform recognition

    • Objects look different under varying conditions:

  • Feature-based method

    • a search is used to find feasible matches between object features and image features.

    • the primary constraint is that a single position of the object must account for all of the feasible matches.

http://en.wikipedia.org/wiki/Outline_of_object_recognition

316 questions
0
votes
0 answers

Pros and Cons of using DNN and CNN in both image classification and object recognition

I totally agree the CNN has been used as the basic structure of R-CNN, Fact R-CNN, and YOLO. My question is that if we have big enough data, is it still good to use DNN? If not so, what is the negative side of using DNN? How about object…
Amn Kh
  • 531
  • 3
  • 7
  • 19
0
votes
2 answers

How to we add a new face into trained face recognition model(inception/resnet/vgg) without retraining complete model?

Is it possible to add a new face features into trained face recognition model, without retraining it with previous faces? Currently am using facenet architecture,
Yesh
  • 1
  • 2
0
votes
1 answer

Is there any way to build an iOS app for Industrial Augmented Reality?

I want to develop superimposition-based AR app (the device recognises a real world 3d object and overlays AR content) for manufacturing and/or automobile industry. How to develop such kind of apps in iOS? Are there available apps using iOS or any…
BSB
  • 277
  • 1
  • 10
0
votes
1 answer

Invalid Argument Error Tensorflow Object Detection Training

I am training tensor flow object detection following the tensor flow API. I have trained many models in the past using the exact same steps. This model however keeps giving me the error message below. The error message references…
J. Ray
  • 11
  • 3
0
votes
1 answer

How can I solve this "UserWarning: Attempting to use a closed FileWriter " error when trying to train my object detection model

I have made an object detection model which trained perfectly but now I removed some images from the training set to add newer better images and I'm getting the following errors C:\Users\Swayam\Anaconda3\envs\tensor\lib\site-…
user11405997
0
votes
1 answer

How to do a training and matching for 3D object recognition from Viewpoint Feature Histogram?

I would like to build a 3D object recognition for my project reaserch, I have clustered for each object that I will recognize, and I have also calculated the VFH. My question is, after that what should I do?, how to make training data to make the…
Kevin I Apriandy
  • 1
  • 3
0
votes
2 answers

How to fix "calibration_pb2 from 'object_detection.protos' " error (Windows)

I've tried to run the below code but it always gives a set of errors. I tried searching the answers but none work for my code, there are two files named 'object_detection' one in the research folder and other in the object_detection-0.1-py3.7.egg…
user11405997
0
votes
1 answer

Computer vision - two frames, overlapping bounding boxes

Situation: A bed is there in a room at some x, y position. On the bed, there's an apple at the center of the bed. Now my code should give an output that there's an apple at the center of the bed, or like an apple on the top left corner of the…
kush_shah
  • 137
  • 2
  • 9
0
votes
1 answer

Darkflow: why am I getting lossy/incomplete output images ( I trained with my own data )

I have trained darkflow yolo with my own data, the description of dataset: dataset size: 3 images classes:1 classname: coca-cola edited the yolo.cfg file to be yolo_custom.cfg: classes = 1 filters = 30 command to train: python3 flow…
Gayatri Purandhar
  • 1
  • 1
0
votes
1 answer

How to obtain from a musical score the different pentagrams(openCV)

For the detection and processing of a picture of a score and then of each of the staves, I proceed as follows: I take the picture and we stay with the horizontal components to stay alone with the lines of the staff, we eliminate the unnecessary…
francisco javier baez ruido
  • 1
0
votes
1 answer

Can images containing single cell be used to train a model to detect and localize multiple cells in the test image

I have a dataset containing images, each image has a single cell along with some smaller inconsequential cells in the background. Can this dataset be used to train a model to detect and recognize multiple target cells in a single test…
Athirooban
  • 11
  • 1
0
votes
0 answers

Object recognition with OpenCV in Python in utility meter images

I wrote a code which finds utility meter measurement result part and crops it. The problem is it does the resize of image. How can I do it without resizing and at the end I need parameters of found part of images, such as width, heith, center x and…
Perizat Abduraimova
  • 9
  • 2
0
votes
2 answers

DNN - Is it a good idea to use grayscale images instead of RGB for training

I am trying to train a DNN for a purpose of object detection (vehicle detection and recognition). Since the colors does not matter for recognition, is it a good idea to use grayscale images for training? This is likely to have the following…
ma.mehralian
  • 1,274
  • 2
  • 13
  • 29
0
votes
1 answer

Cityscapes Trafficsigns no box- or mask- detection with TF Object Detection API

I'd be thankful for all thoughts, tips or links on this: Using TF 1.10 and the recent object detection-API (github, 2018-08-18) I can do box- and mask prediction using the PETS dataset as well as using my own proof of concept data-set: But when…
RuDevel
  • 694
  • 3
  • 14
0
votes
2 answers

AWS-DeepLens: How to access the pre-trained model for object recognition in S3

I am using AWS with the DeepLens device and I want to fine-tune a model for object-recognition. Because DeepLens still has limitations with the layers it can support I want to start from the same model that the demo project has. According to the…
MattSt
  • 1,024
  • 2
  • 16
  • 35
1 2 3
…
21 22